System

Abstract

A system is provided.SOLUTION: A system including means for receiving profile data of a user, means for storing the received profile data in a database, means for learning a machine learning model based on the stored profile data, means for proposing an optimal goal for the user using the learned machine learning model, means for converting a goal selected by the user into a specific sentence, means for displaying the converted goal sentence to the user, and means for submitting the goal confirmed and corrected by the user to the system.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 companies require employees to submit their own goals every six months, which poses the following challenges: it is difficult for employees to find goals that suit them, and it takes time and effort to clearly and specifically verbalize goals. There is also the problem of productivity decreasing due to the inefficiency of the goal-setting process. This invention aims to solve these challenges and support efficient goal setting. [Means for solving the problem]

[0005] The present invention provides a means for receiving user profile data and storing the received data in a database. It also includes a means for training a machine learning model based on the stored data and using the trained model to suggest optimal goals for the user. It utilizes generative AI technology to convert user-selected goals into concrete sentences, and develops a means for displaying the converted goal sentences to the user. It also provides a means for users to submit confirmed and revised goals to the system. This streamlines the goal-setting process and improves employee productivity.

[0006] "Profile data" is information related to an individual, such as a user's skills, work history, goal history, personality data, etc.

[0007] A "database" is a system for organizing and storing information so that it can be searched and accessed as needed.

[0008] A "machine learning model" is an algorithm or structure that analyzes and learns from data, extracts specific patterns and features, and makes inferences and predictions.

[0009] "Generative AI" is an artificial intelligence technology that uses a certain algorithm to generate sentences that feel natural to humans.

[0010] "Goal suggestion" refers to suggesting goals that are appropriate for a user based on the user's profile data.

[0011] A "goal statement" is a document that specifically and clearly describes the text related to the proposed goal.

[0012] "Confirmation and correction" refers to the act of the user checking the displayed target sentence and correcting the content if necessary.

[0013] A "system" is an overall mechanism that integrates multiple means and functions to provide a technical combination for achieving a specific purpose. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention is a system for supporting users in planning and documenting goals to be submitted every six months. This system is implemented by the following procedures and components.

[0036] Profile Data Collection

[0037] 1. A user logs into the system and enters or uploads profile data, such as their skills, work history, past goal history, personality data, etc. This data details the user's abilities and characteristics.

[0038] 2. The device (user's computer or smartphone) sends the entered profile data to the server.

[0039] Data analysis and learning

[0040] 3. The server stores the received profile data in a database.

[0041] 4. The server trains a machine learning model based on the stored data, which involves analyzing how the user's skills, past goal history, and personality data affect goal achievement.

[0042] Generate goal suggestions

[0043] 5. The user submits a goal suggestion request.

[0044] 6. The server uses machine learning models to suggest optimal goals for the user, which are automatically generated based on the user's profile data and the trained models.

[0045] 7. The server returns the generated goal proposals to the terminal, which displays them to the user.

[0046] Selecting and documenting goals

[0047] 8. The user selects the appropriate goal from the proposed goals.

[0048] 9. The terminal sends the selection results to the server.

[0049] 10. The server utilizes generative AI technology to translate the selected goals into concrete sentences, thereby converting vague or subjective expressions into concrete and clear language.

[0050] 11. The server returns the generated target sentence to the terminal, which displays it to the user.

[0051] Final confirmation and submission of goals

[0052] 12. The user checks the displayed target sentence and makes corrections if necessary.

[0053] 13. After the user finalizes the goal, they submit it to the system.

[0054] 14. The terminal sends the submitted target sentence to the server, which stores it in a database.

[0055] Specific examples

[0056] For example, a user might enter a goal into the system: "I want to improve my data analysis skills using Python." First, the device sends this information to the server, which uses a machine learning model to analyze similar past data. Next, a specific goal might be generated: "Over the next six months, successfully complete three projects related to data analysis using Python and share the results in an internal presentation." This goal statement is then sent to the user via the device, where the user can finally review and submit it.

[0057] The above is an embodiment of the present invention, and in this way the efficiency of the user's goal setting work is improved.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] A user logs in to the system.

[0061] Step 2:

[0062] The user enters or uploads their profile data (skills, work history, past goal history, personality data, etc.).

[0063] Step 3:

[0064] The terminal transmits the entered profile data to the server.

[0065] Step 4:

[0066] The server stores the received profile data in a database.

[0067] Step 5:

[0068] The server trains the machine learning model based on the stored data, which includes analyzing the impact of the user's skills and goal history on goal achievement.

[0069] Step 6:

[0070] A user sends a goal suggestion request to a server.

[0071] Step 7:

[0072] The server uses a trained machine learning model to generate optimal goals for the user.

[0073] Step 8:

[0074] The server transmits the generated goal proposals to the terminal.

[0075] Step 9:

[0076] The terminal displays the received goal suggestions to the user.

[0077] Step 10:

[0078] The user selects from the proposed goals.

[0079] Step 11:

[0080] The terminal transmits the selected target to the server.

[0081] Step 12:

[0082] The server uses generative AI technology to convert the selected goals into concrete sentences, which converts ambiguous expressions into clear and specific sentences.

[0083] Step 13:

[0084] The server sends the generated target sentence to the terminal.

[0085] Step 14:

[0086] The terminal displays the generated target sentence to the user.

[0087] Step 15:

[0088] The user checks the generated target sentence and makes corrections if necessary.

[0089] Step 16:

[0090] The user submits the final confirmed goal to the system.

[0091] Step 17:

[0092] The terminal transmits the final confirmed target to the server.

[0093] Step 18:

[0094] The server stores the submitted goals in a database.

[0095] This series of steps allows users to efficiently set their own optimal goals and submit those goals in clear writing.

[0096] Example 1

[0097] 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."

[0098] In conventional goal setting systems, it takes a great deal of time and effort for users to individually set goals and translate them into concrete sentences. Furthermore, the system lacks the ability to utilize the user's past data to suggest optimal goals, and the suggested goals often do not match the user's actual situation. Furthermore, there is a lack of support for converting the suggested goals from vague expressions into specific, clear expressions. This results in inefficient goal setting and hinders the improvement of users' performance.

[0099] 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.

[0100] In this invention, the server includes means for receiving a user's profile data, means for storing the received profile data in a database, means for training a machine learning model based on the stored profile data, means for suggesting optimal goals to the user using the trained machine learning model, means for converting the user's selected goals into specific sentences using generative AI technology, means for displaying the converted goal sentences to the user, means for the user to submit goals confirmed and revised by the user to the system, and means for storing the submitted goals in the database. This enables users to efficiently set goals and describe them in specific and clear terms. Furthermore, optimal goal suggestions can be realized by utilizing the user's past goal history, work history, skill data, and personality data, enabling goal setting that is tailored to the user's actual situation.

[0101] "User profile data" is a general term for information that indicates the user's abilities and characteristics, such as the user's skills, work history, past goal history, and personality data.

[0102] The "means for receiving" refers to a function that utilizes a network, among other things, for incorporating data provided by a user into the system.

[0103] "Means for saving in a database" refers to a function for centrally storing received data and managing it so that it can be retrieved as needed.

[0104] "Means for training a machine learning model" means a function for training a model based on an algorithm using received and stored data to improve analytical capabilities.

[0105] The "means of suggesting optimal goals to the user" is a function that uses a trained machine learning model to extract and present goals that are considered optimal based on the user's profile data.

[0106] "Generative AI technology" is a technology that uses artificial intelligence techniques such as deep learning to generate new information and content (in this case, specific target sentences) based on input data.

[0107] "Means for converting into concrete sentences" is a function that uses generative AI technology to convert the goal selected by the user into detailed and clear language expression.

[0108] The "display means" is a function for displaying the generated target sentence so that the user can view and confirm it.

[0109] "Means for submitting to the system" is a function that allows the user to confirm and modify the goals, send them to the server, and register them.

[0110] "Storage means" is a function that stores the submitted target sentences in a database again, keeping them available for future reference and use.

[0111] The present invention is a system that supports users in planning and documenting their semi-annual goals. The system receives user profile data, trains a machine learning model based on the data, and generates specific goal documents using generative AI technology.

[0112] The embodiment of the present invention is specifically implemented as follows.

[0113] Profile Data Collection

[0114] Users access the system's login screen and log in by entering their user ID and password. Next, they enter or upload profile data such as their skills, work history, past goal history, and personality data. The hardware used is the user's own device, such as a computer or smartphone. The device encrypts the entered profile data and sends it to the server using the HTTPS protocol.

[0115] Data analysis and learning

[0116] The server stores the received profile data in a relational database (e.g., MySQL (registered trademark) or PostgreSQL). The server preprocesses the data (e.g., imputing missing values, standardizing, encoding categorical variables, etc.) and trains a machine learning model (e.g., using Scikit-learn or TENSORFLOW (registered trademark)) based on the data. This process includes analyzing how the user's skills, past goal history, and personality data affect goal achievement.

[0117] Generate goal suggestions

[0118] The user submits a goal suggestion request through the system's UI. After clicking the "Suggest a goal" button, the device sends the goal suggestion request to the server. The server uses a machine learning model to generate a list of optimal goals based on the user's profile data. The generated goal suggestions are sent back to the device in JSON format, and the device displays them in the UI.

[0119] Selecting and documenting goals

[0120] The user selects an appropriate goal from the displayed suggested goals. For example, a user may select "Improve my data analysis skills using Python" from multiple goals. The device sends the selection results to the server, which then converts the selected goal into a specific sentence using generative AI technology (e.g., OpenAI® GPT model). For example, the sentence may be "Successfully complete three projects related to data analysis using Python over the next six months and share the results in an internal presentation." This sentence is then displayed to the user via the device.

[0121] Final confirmation and submission of goals

[0122] The user checks the displayed target sentence and makes corrections if necessary. After final confirmation, the user clicks the "Submit target" button, and the terminal sends the submitted target sentence to the server. The server stores the submitted target sentence in a relational database and returns a confirmation message to the terminal. The terminal displays the confirmation message to the user.

[0123] Prompt Sentence Examples

[0124] For example, here are some examples of prompts that suggest specific, achievable goals based on a user's profile data:

[0125] "Based on the user's profile data, suggest specific, achievable goals. For example, if a user has a goal of 'I want to improve my data analysis skills using Python,' suggest specific steps they should take over the next six months."

[0126] The above is an embodiment of the present invention. This system makes it possible for users to set goals more efficiently and achieve specific and clear goals.

[0127] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0128] Step 1:

[0129] The user accesses the system's login screen and enters their user ID and password. The terminal sends the entered authentication information to the server. At this time, the input data (user ID, password) becomes input from the terminal, and the output is the sent authentication information. The server receives this information and compares it with a database to determine whether the authentication was successful.

[0130] Step 2:

[0131] The server checks the authentication information against the database. The database stores the user's ID and password, and the server checks whether they match this data. If authentication is successful, the server generates an authentication success message and sends it back to the terminal. The input is the authentication information and user information from the database, and the output is an authentication result message.

[0132] Step 3:

[0133] The user enters or uploads profile data in the system. The input data includes skills, work history, past goal history, personality data, etc. The device encrypts this profile data and securely transmits it to the server using the HTTPS protocol. The input is the profile data provided by the user, and the output is the transmission of encrypted data.

[0134] Step 4:

[0135] The server stores the received profile data in a database. When storing, it checks the format of the data and cleanses it if necessary. The input is the encrypted profile data, and the output is the clean data stored in the database.

[0136] Step 5:

[0137] The server performs data preprocessing based on the stored data, specifically imputing missing values, standardizing, encoding categorical variables, etc. The input is the stored profile data, and the output is the preprocessed data.

[0138] Step 6:

[0139] The server uses the preprocessed data to train a machine learning model. For example, it uses Scikit-learn or TensorFlow to apply algorithms to analyze how the user's skills, past goal history, and personality data affect goal achievement. The input is the preprocessed data, and the output is the trained machine learning model.

[0140] Step 7:

[0141] The user submits a goal suggestion request from the system UI. By clicking the "Suggest a goal" button, the device sends the request to the server. The input is the user's request, and the output is the transmission of the request data.

[0142] Step 8:

[0143] The server uses a machine learning model to generate optimal goals based on the user's profile data. Specifically, the model compares past data with the user's current profile and suggests goals with a high success rate. The input is the user's profile data and the machine learning model, and the output is a list of suggested goals.

[0144] Step 9:

[0145] The server returns the generated goal suggestions in JSON format to the device, which displays them in the UI for the user to review. The input is a list of suggested goals, and the output is the goal suggestions displayed in the UI.

[0146] Step 10:

[0147] The user selects an appropriate goal from the suggested goals displayed. For example, the user can select the goal "Improve my data analysis skills using Python." The input is a list of suggested goals, and the output is the selected goal.

[0148] Step 11:

[0149] The terminal sends the selected target to the server. The input is the selected target and the output is the transmission to the server.

[0150] Step 12:

[0151] The server converts the selected goal into a concrete sentence using generative AI technology. For example, the OpenAI GPT model is used to generate a concrete goal sentence such as "Over the next six months, successfully complete three projects related to data analysis using Python and share the results in an internal presentation." The input is the selected goal, and the output is the generated concrete goal sentence.

[0152] Step 13:

[0153] The server returns the generated target sentence in JSON format to the terminal, which displays it in the UI for the user to confirm. The input is the specific target sentence generated, and the output is the target sentence displayed in the UI.

[0154] Step 14:

[0155] The user checks the displayed target sentence and makes corrections if necessary. After final confirmation, the user clicks the "Submit target" button. The input is the generated target sentence and corrections, and the output is the final target sentence.

[0156] Step 15:

[0157] The terminal sends the submitted target sentence to the server. The input is the final target sentence and the output is the transmission to the server.

[0158] Step 16:

[0159] The server saves the submitted target sentence in a relational database. The server confirms that the saving is complete and generates a confirmation message to send back to the terminal. The input is the final target sentence, and the output is the confirmation message.

[0160] Step 17:

[0161] The terminal displays a confirmation message to the user. The input is the confirmation message received from the server, and the output is the message displayed on the user's screen.

[0162] (Application example 1)

[0163] 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."

[0164] The process of factory robot operators setting effective goals based on their own skills and work history and converting these into specific instruction sentences takes time and effort. Furthermore, if appropriate goals are not set, production efficiency may decrease and it may be difficult to achieve the goals. To solve this problem, a system is needed that automatically suggests optimal goals based on the operator's profile data and converts those goals into specific instruction sentences.

[0165] 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.

[0166] In this invention, the server includes means for receiving user profile data, means for saving the received profile data in a database, means for training a machine learning model based on the saved profile data, means for suggesting optimal goals to the user using the trained machine learning model, means for converting the user's selected goals into specific sentences, means for displaying the converted goal sentences to the user, means for the user to submit goals confirmed and revised by the user to the system, means for suggesting production goals based on the robot operator's profile data, and means for converting the proposed production goals into specific instruction sentences. This allows factory robot operators to easily set goals that are optimal for their own attributes, and by converting the goals into specific instruction sentences, it becomes possible to improve production efficiency.

[0167] "User" refers to an individual or group that uses the system, and in the present invention particularly includes operators of factory robots.

[0168] "Profile Data" refers to information detailing a user's abilities and characteristics, such as the user's skills, work history, past goal history, and personality data.

[0169] "Database" refers to an information storage system that systematically stores received profile data and later uses it for training machine learning models, etc.

[0170] A "machine learning model" is a model that uses algorithms to learn from stored data and analyze user profile data.

[0171] "Goal suggestion" refers to the process of using machine learning models to suggest optimal goals to a user.

[0172] "Specific sentences" refer to text data in which the proposed goals are converted from vague or subjective expressions into concrete and clear language.

[0173] "Production goals" refer to specific goals aimed at improving production activities and work efficiency that factory robot operators aim to achieve.

[0174] "Instruction text" refers to text that converts proposed production targets into specific instructions and provides easy-to-understand instructions to operators or robots.

[0175] "Translation" refers to the process of turning a user's chosen goal into a more specific, actionable statement.

[0176] This invention is a system that enables factory robot operators to effectively set production goals based on their own profile data and converts those goals into specific instruction sentences. This system is configured as follows and supports goal setting through a specific process.

[0177] System program configuration

[0178] 1. Collection of profile data

[0179] Users input profile data including their skills, work history, past goal history, personality data, etc. This data is sent to the server via an internet-enabled device (e.g., smartphone, PC).

[0180] 2. Data storage

[0181] The server stores the received profile data in a database, which is constructed using a relational database management system such as SQL.

[0182] 3. Data Analysis and Machine Learning

[0183] The server uses the stored data to train a machine learning model using machine learning libraries such as Python and TensorFlow, which analyzes patterns based on the user's skills and historical data to influence goal achievement.

[0184] 4. Generating goal proposals

[0185] When a user submits a goal suggestion request, the server uses machine learning models to suggest optimal goals, which are automatically generated based on pre-processed user profile data and the trained model.

[0186] 5. Write down your goals in concrete terms

[0187] Once the user selects a suggested goal, the server uses generative AI technology (e.g., GPT-2) to convert the selected goal into a specific instruction sentence. The generative AI model generates text based on the prompt sentence through a tokenizer and model training.

[0188] 6. Final confirmation and submission of goals

[0189] The user checks the displayed instruction text and corrects it if necessary. The final confirmed goal is submitted to the server via the terminal and stored in the database.

[0190] Specific examples

[0191] For example, suppose a user inputs a goal such as "I want to improve the operating efficiency of the manufacturing line by 10%." The device sends this information to the server, which then uses a machine learning model to analyze similar past data. The server then generates a specific goal: "Over the next six months, successfully complete three projects to improve the operating efficiency of the manufacturing line by 10% and share the results at a team meeting." This goal statement is then displayed to the user via the device, who then finally confirms and submits it.

[0192] Prompt Sentence Examples

[0193] "My next goal: to complete a project that will increase production efficiency by 10%."

[0194] Based on this prompt, the generative AI model generates clear and specific instructions for the user, making it easier for factory robot operators to set goals and efficiently take specific actions to achieve them.

[0195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0196] Step 1:

[0197] The user uses a device to enter profile data (e.g., skills, work history, past goal history, personality data) and sends the data to the server. The entered profile data is sent to the server in JSON format, and after receiving it, it is saved in a database. This allows detailed attribute information about the user to be accumulated.

[0198] Step 2:

[0199] The server then stores the received profile data in a database, using a relational database management system such as SQL to store the data in a structured format, which prepares the data for later data analysis and machine learning training.

[0200] Step 3:

[0201] The server trains a machine learning model based on the stored data. It uses Python and machine learning libraries such as TensorFlow to analyze patterns that influence goal achievement based on the user's skills and historical data. The data is preprocessed for learning, features are extracted, and the model is trained. The result is a model capable of suggesting optimal goals based on the user's attributes.

[0202] Step 4:

[0203] The user submits a goal suggestion request. This request is sent to the server via the terminal. The server, upon receiving the request, uses the learned machine learning model to suggest optimal goals for the user. The server receives the user's profile data as input, predicts goals based on the data, and generates the results as suggested goals.

[0204] Step 5:

[0205] The server sends the generated goal suggestions back to the terminal, which then displays them to the user. The user selects the most appropriate goal from the suggested goals. The selected goal is then sent back to the server via the terminal. This step involves the user's confirmation and selection process.

[0206] Step 6:

[0207] The server utilizes generative AI technology (e.g., GPT-2) to convert the selected goal into specific instruction sentences. Specifically, the selected goal is used as a prompt sentence, and the generative AI model generates specific instruction sentences based on the prompt sentence. The input to the generation process is the prompt sentence, and the output is the instruction sentence. For example, if the prompt sentence is "Complete a project that will improve production efficiency by 10%," the generative AI model will use this as a basis to generate sentences containing specific work instructions.

[0208] Step 7:

[0209] The generated instruction sentence is displayed to the user, who can then confirm and edit it. Once the edits are complete, the final confirmed target sentence is submitted to the server via the terminal. At this time, the user can make edits until they are satisfied, and the final confirmed target sentence is sent to the server.

[0210] Step 8:

[0211] The server stores the final confirmed goal sentences in a database, which can then be used for future evaluations and confirmations. This process enables factory robot operators to easily set specific, achievable goals and receive highly effective instructions for achieving them.

[0212] 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.

[0213] This invention is a system that supports users in planning and documenting their goals to be submitted every six months, and further combines it with an emotion engine that recognizes the user's emotional state to set more personalized goals. This system includes the following specific steps and components:

[0214] Collection and storage of profile data

[0215] 1. A user logs into the system and enters or uploads their profile data (skills, work history, past goal history, personality data, etc.), which includes information detailing the user's abilities and characteristics.

[0216] 2. The device sends the entered profile data to the server.

[0217] 3. The server stores the received profile data in a database.

[0218] Data analysis and learning

[0219] 4. The server trains a machine learning model based on the stored data, analyzing the impact of the user's skills and goal history on goal achievement.

[0220] Emotion recognition and data addition using the emotion engine

[0221] 5. When a user uses the system, the emotion engine recognizes the user's emotional state from their facial expressions, voice, etc.

[0222] 6. The device sends the recognized emotional state data to the server.

[0223] 7. The server adds the emotional state data to the profile data and stores it in a database.

[0224] Goal suggestions and emotional influences

[0225] 8. The user sends a goal suggestion request to the server.

[0226] 9. The server generates optimal goals for the user based on the machine learning model and emotional state data. These suggestions are generated automatically based on the user's profile data, emotional state, and the trained model.

[0227] 10. The server sends the generated goal proposal to the terminal, which displays it to the user.

[0228] Selecting and documenting goals

[0229] 11. The user selects the appropriate goal from the proposed goals.

[0230] 12. The terminal sends the selection results to the server.

[0231] 13. The server uses generative AI technology to convert the selected goal into concrete sentences. Generative AI converts vague expressions into clear and concrete sentences.

[0232] 14. The server sends the generated target sentence to the terminal, which displays it to the user.

[0233] Final confirmation and submission of goals

[0234] 15. The user checks the generated target sentences and makes corrections if necessary.

[0235] 16. The user submits the final confirmed goal to the system.

[0236] 17. The device sends the final confirmed target to the server.

[0237] 18. The server stores the submitted goals in a database.

[0238] Specific examples

[0239] A user logs into the system and enters their profile data and past goal history. The device sends this data to the server, which stores it in a database. Next, when the user uses the system to set goals, the emotion engine analyzes the user's facial expressions and voice to ascertain their emotional state. For example, if the user is feeling stressed, that emotional state is reflected in the system. Based on this data, the server suggests goals that are achievable and less stressful for the user. For example, a specific goal might be suggested: "Successfully complete three projects related to data analysis using Python over the next six months and share the results in an internal presentation." The generated goal text is then sent to the user via the device, where the user can finally review, revise, and submit it.

[0240] The present invention makes it possible to set individual optimal goals that take into consideration the user's emotional state, and is expected to enable efficient and effective goal achievement.

[0241] The processing flow will be explained below.

[0242] Step 1:

[0243] A user logs in to the system.

[0244] Step 2:

[0245] The user enters or uploads their profile data (skills, work history, past goal history, personality data, etc.).

[0246] Step 3:

[0247] The terminal transmits the entered profile data to the server.

[0248] Step 4:

[0249] The server stores the received profile data in a database.

[0250] Step 5:

[0251] The server trains the machine learning model based on the stored data, which includes analyzing the impact of the user's skills and goal history on goal achievement.

[0252] Step 6:

[0253] The emotion engine recognizes the user's emotional state from data such as facial expressions and voice.

[0254] Step 7:

[0255] The terminal transmits the emotional state data recognized by the emotion engine to the server.

[0256] Step 8:

[0257] The server adds the emotional state data to the profile data and stores it in a database.

[0258] Step 9:

[0259] A user sends a goal suggestion request to a server.

[0260] Step 10:

[0261] The server generates optimal goals for the user based on the machine learning model and emotional state data. These goal suggestions are automatically generated based on the user's profile data, emotional state, and the trained model.

[0262] Step 11:

[0263] The server transmits the generated goal proposals to the terminal.

[0264] Step 12:

[0265] The terminal displays the received goal suggestions to the user.

[0266] Step 13:

[0267] The user selects the appropriate goal from the proposed goals.

[0268] Step 14:

[0269] The terminal transmits the selected target to the server.

[0270] Step 15:

[0271] The server uses generative AI technology to convert the selected goals into concrete sentences, which converts ambiguous expressions into clear and specific sentences.

[0272] Step 16:

[0273] The server sends the generated target sentence to the terminal.

[0274] Step 17:

[0275] The terminal displays the generated target sentence to the user.

[0276] Step 18:

[0277] The user checks the generated target sentences and makes corrections as necessary.

[0278] Step 19:

[0279] The user submits the final confirmed goal to the system.

[0280] Step 20:

[0281] The terminal transmits the final confirmed target to the server.

[0282] Step 21:

[0283] The server stores the submitted goals in a database.

[0284] This series of steps allows users to efficiently set optimal goals and submit them in clear written form. Taking into account the user's emotional state, we can set goals that are appropriate for each individual, leading to more effective goal achievement.

[0285] Example 2

[0286] 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."

[0287] Conventional goal setting systems offer a means for suggesting goals based on a user's profile data and past work history, but they are unable to take into account the emotional state of each individual user, making it difficult to set appropriate and achievable goals. This can lead to users being unable to achieve their set goals, resulting in a loss of motivation and stress. The present invention aims to solve this problem.

[0288] 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.

[0289] In this invention, the server includes means for receiving user profile data, means for storing the received profile data in a database, means for training a machine learning model based on the stored profile data, means for recognizing the user's emotional state, means for adding the recognized emotional state data to the profile data and storing it, means for proposing optimal goals to the user using the trained machine learning model and the emotional state data, means for converting the user's selected goal into a specific sentence, means for displaying the converted goal sentence to the user, and means for submitting the user's confirmed and revised goal to the system, thereby enabling individually optimal goal setting that takes the user's emotional state into consideration.

[0290] "User" refers to an individual or organization that uses the System.

[0291] "Profile Data" refers to detailed information about a user, such as the user's skills, work history, past goal history, and personality data.

[0292] "Database" refers to a system or technology that efficiently stores and manages data received by a system and makes it accessible as needed.

[0293] A "machine learning model" is a model that automatically learns statistical patterns and rules based on data and uses them to make predictions and classifications.

[0294] "Emotional state" refers to the current emotional state of the user as analyzed from the user's facial expressions, voice, etc. Examples include joy, sadness, stress, etc.

[0295] "Generative AI" refers to artificial intelligence technology that performs natural language processing such as sentence generation based on provided input data.

[0296] "Goal proposal" means that the system presents specific goals and work plans to the user.

[0297] "Goal sentence" refers to a text that expresses the proposed goal in a specific and detailed manner.

[0298] "Submission means" refers to a means by which a user finally transmits the confirmed and corrected goals to the system.

[0299] "Terminal" refers to a device that allows a user to access the system, input data, and display results. Examples include personal computers and smartphones.

[0300] "Server" refers to the central processing unit of a system, which processes, stores, analyzes, etc. data.

[0301] This invention is a system that supports the user in planning and documenting semi-annual goals and recognizes the user's emotional state. Specific embodiments of this system are described below. Each step clearly indicates the type of hardware or software used to process or calculate data.

[0302] System Configuration

[0303] The system consists of a user terminal, a server, a database, an emotion recognition engine, and a generative AI model.

[0304] User devices include PCs, tablets, smartphones, etc., through which users access the system to enter data and check results. The devices communicate with the server via the Internet.

[0305] The server is a central processing unit that processes data, stores data, trains machine learning models, recognizes emotional states, generates text using generative AI models, etc. Specific examples commonly used include cloud services such as AWS (registered trademark) (Amazon Web Services) and Google (registered trademark) Cloud.

[0306] The database manages the saved profile data, emotional state data, machine learning models, and generated target sentences. Specifically, a relational database such as PostgreSQL is used.

[0307] The emotion recognition engine provides technology to recognize the user's emotional state in real time by analyzing their facial expressions and voice. It uses a facial recognition library such as OpenCV and a Python voice analysis library.

[0308] A generative AI model is an artificial intelligence technology that generates specific target sentences based on a user's profile data and emotional state. Specific examples include natural language processing models such as OpenAI's GPT-3 (registered trademark).

[0309] Program processing explanation

[0310] The system starts when a user logs in and enters and uploads their profile data. The user's device sends this data to the server, which stores it in a database.

[0311] The server then trains a machine learning model based on the stored data, using Python libraries such as scikit-learn and TensorFlow. The trained model is then saved on the server for further processing.

[0312] When a user uses the system, the emotion recognition engine recognizes the user's emotional state from their facial expressions and voice. The user device sends the recognized emotional state data to the server, which then stores it in a database.

[0313] The server generates optimal goals for the user based on the machine learning model and the stored emotional state data. This process takes into account the user's skills, past goal history, and current emotional state. The generated goal suggestions are sent to the user's device and displayed to the user.

[0314] The user selects the appropriate goal from the proposed set of goals, and the results are sent to the server. The server then uses generative AI technology to convert the selected goal into concrete sentences. OpenAI's GPT-3 is commonly used in this process.

[0315] The generated target sentences are sent back to the user's terminal for confirmation and correction. Once the final target is determined, it is sent from the user's terminal to the server and stored in the database.

[0316] Specific examples

[0317] A user logs into the system and uploads profile data, including past work history and skills. The device sends this data to the server, which stores it in a database. Next, when the user sets goals, an emotion recognition engine analyzes the user's facial expressions and voice to recognize their emotional state. For example, if the user is feeling stressed, the system will reflect that emotional state. Based on this data, the server suggests achievable goals that are less stressful for the user.

[0318] For example, a specific goal is proposed: "Over the next six months, successfully complete three projects related to data analysis using Python and share the results in an internal presentation." This generated goal statement is sent to the user via the terminal, and the user finally reviews, corrects, and submits it.

[0319] Prompt Sentence Examples

[0320] "Generate goals based on this user's profile data and emotional state."

[0321] "Please translate the user's selected goal into a concrete sentence."

[0322] This embodiment enables optimal individual goal setting that takes into account the emotional state of the user, and is expected to lead to efficient and effective goal achievement.

[0323] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0324] Step 1:

[0325] A user logs in to the system. The user enters a username and password on the login screen, and if authentication is successful, the screen moves to the next screen. The input is the username and password, and the output is a flag indicating successful authentication. Specifically, this includes the action of clicking the "Login" button in the upper right corner.

[0326] Step 2:

[0327] The user enters or uploads profile data. Profile data includes skills, work history, past goal history, personality data, etc. Input is text or a file (e.g., Excel), and output is a confirmation screen displayed on the device. Specifically, this includes the actions of filling in each input field and clicking the "Upload" button.

[0328] Step 3:

[0329] The device sends the entered profile data to the server. The input is the data entered or uploaded by the user, and the output is a message confirming the data was sent to the server. The data is sent in JSON format.

[0330] Step 4:

[0331] The server saves the received profile data in a database. The input is the profile data sent from the device, and the output is the ID of the data saved in the database. Specifically, a write process is performed on the database.

[0332] Step 5:

[0333] The server trains a machine learning model based on the stored data. The input is the profile data stored in the database, and the output is the trained machine learning model. The model is trained using Python's scikit-learn and TensorFlow.

[0334] Step 6:

[0335] The server saves the learned machine learning model. The input is the trained machine learning model, and the output is the path to the saved model. Specifically, it includes the operation of saving the model as a file.

[0336] Step 7:

[0337] While the user is using the system, the emotion recognition engine analyzes the user's facial expressions and voice in real time. The input is the user's camera footage and audio data, and the output is the recognized emotional state. Specifically, this includes turning on the camera to analyze facial expressions and collecting audio using the microphone.

[0338] Step 8:

[0339] The device sends the recognized emotional state data to the server. The input is the emotional state data generated by the emotion recognition engine, and the output is a confirmation message sent to the server. The voice analysis results are sent as text data.

[0340] Step 9:

[0341] The server adds the emotional state data to the profile data and saves it in the database. The input is the newly acquired emotional state data, and the output is the updated profile data. The writing process is performed in the database.

[0342] Step 10:

[0343] The user sends a goal proposal request to the server. The input is the user clicking the goal proposal button, and the output is the request data sent to the server.

[0344] Step 11:

[0345] The server uses the machine learning model and emotional state data to generate optimal goals for the user. The input is the trained model, saved profile data, and emotional state data, and the output is the generated goal suggestions.

[0346] Step 12:

[0347] The server sends the generated goal proposals to the terminal, which then displays them to the user. The input is the generated goal proposals, and the output is the displayed goal proposals.

[0348] Step 13:

[0349] The user selects an appropriate goal from the proposed goals. The input is a displayed list of multiple goal suggestions, and the output is the selected goal. Specifically, the action involves clicking and selecting one from the list of goals.

[0350] Step 14:

[0351] The terminal sends the selection result to the server. The input is the ID of the selected target, and the output is a confirmation message to the server.

[0352] Step 15:

[0353] The server uses generative AI technology to convert the selected goal into a specific sentence. The input is the selected goal data, and the output is the specific goal sentence. OpenAI's GPT-3 and other generative AI models are used.

[0354] Step 16:

[0355] The server sends the generated target sentence to the terminal, which displays it to the user. The input is the generated target sentence, and the output is the displayed target sentence.

[0356] Step 17:

[0357] The user reviews the generated target sentence and makes corrections if necessary. The input is the displayed target sentence, and the output is the corrected target sentence. Specifically, this involves editing the sentence by typing into a text field.

[0358] Step 18:

[0359] The user submits the finalized goal to the system. The input is the finalized goal text, and the output is a submission request to the server. This includes clicking the "Submit" button.

[0360] Step 19:

[0361] The terminal sends the final confirmed goal to the server. The input is the final confirmed goal text, and the output is a transmission confirmation message to the server.

[0362] Step 20:

[0363] The server saves the submitted goal in the database. The input is the final confirmed goal text, and the output is the ID of the saved goal data. The write process is performed in the database.

[0364] (Application example 2)

[0365] 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."

[0366] In modern self-driving vehicles, it is difficult to provide appropriate driving guidance and goal setting that takes into account the driver's emotional state. Furthermore, there is no system in place to recognize the driver's emotional state in real time and provide appropriate advice, meaning that support for continuing safe driving when the driver feels stressed or fatigued is insufficient. The present invention aims to solve these problems by providing a system that provides individually optimized driving goals and advice to drivers.

[0367] 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.

[0368] In this invention, the server includes means for receiving user profile data, means for storing the received profile data in a database, means for training a machine learning model based on the stored profile data, means for suggesting optimal goals to the user using the trained machine learning model, means for recognizing the user's emotional state while driving, means for generating driving advice in real time based on the recognized emotional state, means for displaying the generated advice to the user, means for converting the user's selected goal into a specific sentence, means for displaying the converted goal sentence to the user, and means for submitting the user's confirmed and revised goal to the system. This enables individually optimal driving instruction and goal setting that take the driver's emotional state into consideration, thereby realizing safe and efficient driving assistance.

[0369] "User profile data" refers to information about an individual, such as driver skills, driving experience, past driving history, and personality data.

[0370] "Database" refers to a collection of information for managing stored profile data and emotional data.

[0371] A "machine learning model" is an algorithm that learns from collected data and generates patterns and predictions.

[0372] "Optimal goals" refer to achievable, specific driving goals that are set based on the user's profile data and emotional state.

[0373] "Emotional state" refers to a driver's psychological and emotional state while driving, which is usually recognized through facial expressions and tone of voice.

[0374] "Means for generating driving advice in real time" refers to a method for instantly analyzing the driver's emotional state and providing driving guidance or advice based on that.

[0375] "Means of converting into concrete sentences" refers to a method of using generative AI to convert abstract goals and guidelines into clear and concrete sentences.

[0376] "Generative AI" refers to a technology that uses generative artificial intelligence technology to generate sentences in natural language based on input information.

[0377] The present invention provides a system for recognizing a user's emotional state while driving and providing appropriate driving goals and advice in real time. This system includes the following specific programs and components:

[0378] Program processing

[0379] 1. Collection and storage of profile data

[0380] A user logs into the system installed in the vehicle and enters their profile data (driving experience, skills, past driving history, personality data, etc.). This data is sent from the in-vehicle terminal to a server and stored in a database. This database contains detailed information about each individual driver.

[0381] 2. Data analysis and learning

[0382] The server trains a machine learning model based on the stored profile data. The machine learning model (e.g., TensorFlow) analyzes this data to learn the user's driving patterns and skill level. The model uses data from driving history and driving behavior to discover patterns related to goal achievement.

[0383] 3. Emotion recognition and data addition using the emotion engine

[0384] While driving, the camera and microphone inside the vehicle capture the driver's facial expressions and voice and send this to an emotion recognition engine (e.g., Microsoft® Azure® Emotion API). The emotion recognition engine analyzes this data and identifies the driver's emotional state in real time. The identified emotion data is sent from the in-vehicle terminal to a server and stored in a database.

[0385] 4. Real-time goal suggestions and emotional influence

[0386] When a user requests a goal suggestion from the system, the server generates appropriate driving goals and advice based on machine learning models and real-time emotion data. This generation process uses a generative AI model (e.g., OpenAI GPT-4 (registered trademark)). The generated advice and goals are displayed on the in-car display.

[0387] 5. Identifying and documenting goals

[0388] The user selects suggested goals and advice and sends the results from the in-car device to the server. The server then uses generative AI to convert the abstract goals into concrete sentences. In this process, the generative AI generates documents in natural language based on the input information. The generated goal sentences are then displayed on the in-car display.

[0389] 6. Final review and feedback

[0390] The user reviews the generated goal sentences and makes any necessary corrections. The final goal is then submitted to the system and stored in the database.

[0391] Specific examples

[0392] A user logs into the system and enters their profile data and past driving history, including driving skills (e.g., highway driving, city driving), past accident history, and current driving goals. While driving, an in-vehicle camera recognizes facial expressions, and their emotional state (e.g., nervous, relaxed) is stored in a database. When the user requests "driving goals for the next hour," the system suggests specific goals, such as "obey the speed limit and avoid sudden acceleration and braking." A generative AI model is used to elaborate on these goal statements, which the user then confirms.

[0393] Prompt Sentence Examples

[0394] "Suggest a driving goal for the next hour."

[0395] "What should I pay attention to while driving?"

[0396] I need some advice on how to relax.

[0397] This system can provide individually optimized driving assistance by combining the user's profile data with their emotional state while driving.

[0398] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0399] Step 1:

[0400] The user logs into the system installed in the vehicle. The user enters profile data such as their driving experience, skills, past driving history, and personality data. This data is sent by the terminal to the server and stored in a database. This allows detailed information about each user to be stored in a central database.

[0401] Input: User profile data (driving experience, skills, past driving history, personality data)

[0402] Output: Profile data stored in a database

[0403] Step 2:

[0404] The server trains a machine learning model based on the stored profile data. The machine learning model (e.g., TensorFlow) analyzes the driver's characteristics and patterns from this data and generates a personalized driving profile for each user, which then reflects their driving habits and skill level in the model.

[0405] Input: Profile data stored in the database

[0406] Output: A trained machine learning model

[0407] Step 3:

[0408] While the user is driving the vehicle, the camera and microphone inside the vehicle capture the user's facial expressions and voice. The device sends this data to an emotion recognition engine (e.g., Microsoft Azure Emotion API) to analyze the user's emotional state in real time. The analyzed emotional data is then sent to a server and stored in a database.

[0409] Input: User's facial expression and voice data

[0410] Output: Real-time analyzed emotional state data

[0411] Step 4:

[0412] When a user requests a goal suggestion, the server generates appropriate driving goals and advice based on machine learning models and real-time emotion data. This generation process uses a generative AI model (e.g., OpenAI GPT-4). The generated advice and goals are displayed on the in-car display.

[0413] Input: User goal suggestion request, machine learning model, real-time sentiment data

[0414] Output: Generated driving goals and advice sentences

[0415] Step 5:

[0416] Once the user selects a suggested goal sentence or piece of advice, the device sends the result to the server, which then uses generative AI to convert the abstract goal into a concrete sentence, thereby clarifying any ambiguity in the goal. The generated goal sentence is then displayed on the vehicle's display.

[0417] Input: User selection results, generated AI model

[0418] Output: Specific target sentence

[0419] Step 6:

[0420] The user checks the generated goal sentences and makes corrections as necessary. The final version of the goal is submitted to the system via the terminal and stored in the database. This allows the optimal goal to be set in a way that satisfies the user.

[0421] Input: User confirmation and correction details

[0422] Output: Final target sentence stored in the database

[0423] Through these steps, individually optimized driving assistance that takes into account the user's emotional state is realized.

[0424] 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.

[0425] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0426] 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.

[0427] [Second embodiment]

[0428] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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."

[0440] The present invention is a system for supporting users in planning and documenting goals to be submitted every six months. This system is implemented by the following procedures and components.

[0441] Profile Data Collection

[0442] 1. A user logs into the system and enters or uploads profile data, such as their skills, work history, past goal history, personality data, etc. This data details the user's abilities and characteristics.

[0443] 2. The device (user's computer or smartphone) sends the entered profile data to the server.

[0444] Data analysis and learning

[0445] 3. The server stores the received profile data in a database.

[0446] 4. The server trains a machine learning model based on the stored data, which involves analyzing how the user's skills, past goal history, and personality data affect goal achievement.

[0447] Generate goal suggestions

[0448] 5. The user submits a goal suggestion request.

[0449] 6. The server uses machine learning models to suggest optimal goals for the user, which are automatically generated based on the user's profile data and the trained models.

[0450] 7. The server returns the generated goal proposals to the terminal, which displays them to the user.

[0451] Selecting and documenting goals

[0452] 8. The user selects the appropriate goal from the proposed goals.

[0453] 9. The terminal sends the selection results to the server.

[0454] 10. The server utilizes generative AI technology to translate the selected goals into concrete sentences, thereby converting vague or subjective expressions into concrete and clear language.

[0455] 11. The server returns the generated target sentence to the terminal, which displays it to the user.

[0456] Final confirmation and submission of goals

[0457] 12. The user checks the displayed target sentence and makes corrections if necessary.

[0458] 13. After the user finalizes the goal, they submit it to the system.

[0459] 14. The terminal sends the submitted target sentence to the server, which stores it in a database.

[0460] Specific examples

[0461] For example, a user might enter a goal into the system: "I want to improve my data analysis skills using Python." First, the device sends this information to the server, which uses a machine learning model to analyze similar past data. Next, a specific goal might be generated: "Over the next six months, successfully complete three projects related to data analysis using Python and share the results in an internal presentation." This goal statement is then sent to the user via the device, where the user can finally review and submit it.

[0462] The above is an embodiment of the present invention, and in this way the efficiency of the user's goal setting work is improved.

[0463] The processing flow will be explained below.

[0464] Step 1:

[0465] A user logs in to the system.

[0466] Step 2:

[0467] The user enters or uploads their profile data (skills, work history, past goal history, personality data, etc.).

[0468] Step 3:

[0469] The terminal transmits the entered profile data to the server.

[0470] Step 4:

[0471] The server stores the received profile data in a database.

[0472] Step 5:

[0473] The server trains the machine learning model based on the stored data, which includes analyzing the impact of the user's skills and goal history on goal achievement.

[0474] Step 6:

[0475] A user sends a goal suggestion request to a server.

[0476] Step 7:

[0477] The server uses a trained machine learning model to generate optimal goals for the user.

[0478] Step 8:

[0479] The server transmits the generated goal proposals to the terminal.

[0480] Step 9:

[0481] The terminal displays the received goal suggestions to the user.

[0482] Step 10:

[0483] The user selects from the proposed goals.

[0484] Step 11:

[0485] The terminal transmits the selected target to the server.

[0486] Step 12:

[0487] The server uses generative AI technology to convert the selected goals into concrete sentences, which converts ambiguous expressions into clear and specific sentences.

[0488] Step 13:

[0489] The server sends the generated target sentence to the terminal.

[0490] Step 14:

[0491] The terminal displays the generated target sentence to the user.

[0492] Step 15:

[0493] The user checks the generated target sentence and makes corrections if necessary.

[0494] Step 16:

[0495] The user submits the final confirmed goal to the system.

[0496] Step 17:

[0497] The terminal transmits the final confirmed target to the server.

[0498] Step 18:

[0499] The server stores the submitted goals in a database.

[0500] This series of steps allows users to efficiently set their own optimal goals and submit those goals in clear writing.

[0501] Example 1

[0502] 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."

[0503] In conventional goal setting systems, it takes a great deal of time and effort for users to individually set goals and translate them into concrete sentences. Furthermore, the system lacks the ability to utilize the user's past data to suggest optimal goals, and the suggested goals often do not match the user's actual situation. Furthermore, there is a lack of support for converting the suggested goals from vague expressions into specific, clear expressions. This results in inefficient goal setting and hinders the improvement of users' performance.

[0504] 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.

[0505] In this invention, the server includes means for receiving a user's profile data, means for storing the received profile data in a database, means for training a machine learning model based on the stored profile data, means for suggesting optimal goals to the user using the trained machine learning model, means for converting the user's selected goals into specific sentences using generative AI technology, means for displaying the converted goal sentences to the user, means for the user to submit goals confirmed and revised by the user to the system, and means for storing the submitted goals in the database. This enables users to efficiently set goals and describe them in specific and clear terms. Furthermore, optimal goal suggestions can be realized by utilizing the user's past goal history, work history, skill data, and personality data, enabling goal setting that is tailored to the user's actual situation.

[0506] "User profile data" is a general term for information that indicates the user's abilities and characteristics, such as the user's skills, work history, past goal history, and personality data.

[0507] The "means for receiving" refers to a function that utilizes a network, among other things, for incorporating data provided by a user into the system.

[0508] "Means for saving in a database" refers to a function for centrally storing received data and managing it so that it can be retrieved as needed.

[0509] "Means for training a machine learning model" means a function for training a model based on an algorithm using received and stored data to improve analytical capabilities.

[0510] The "means of suggesting optimal goals to the user" is a function that uses a trained machine learning model to extract and present goals that are considered optimal based on the user's profile data.

[0511] "Generative AI technology" is a technology that uses artificial intelligence techniques such as deep learning to generate new information and content (in this case, specific target sentences) based on input data.

[0512] "Means for converting into concrete sentences" is a function that uses generative AI technology to convert the goal selected by the user into detailed and clear language expression.

[0513] The "display means" is a function for displaying the generated target sentence so that the user can view and confirm it.

[0514] "Means for submitting to the system" is a function that allows the user to confirm and modify the goals, send them to the server, and register them.

[0515] "Storage means" is a function that stores the submitted target sentences in a database again, keeping them available for future reference and use.

[0516] The present invention is a system that supports users in planning and documenting their semi-annual goals. The system receives user profile data, trains a machine learning model based on the data, and generates specific goal documents using generative AI technology.

[0517] The embodiment of the present invention is specifically implemented as follows.

[0518] Profile Data Collection

[0519] Users access the system's login screen and log in by entering their user ID and password. Next, they enter or upload profile data such as their skills, work history, past goal history, and personality data. The hardware used is the user's own device, such as a computer or smartphone. The device encrypts the entered profile data and sends it to the server using the HTTPS protocol.

[0520] Data analysis and learning

[0521] The server stores the received profile data in a relational database (e.g., MySQL or PostgreSQL). The server preprocesses the data (e.g., imputing missing values, standardizing, encoding categorical variables) and trains a machine learning model (e.g., using Scikit-learn or TensorFlow) based on the data. This process includes analyzing how the user's skills, past goal history, and personality data affect goal achievement.

[0522] Generate goal suggestions

[0523] The user submits a goal suggestion request through the system's UI. After clicking the "Suggest a goal" button, the device sends the goal suggestion request to the server. The server uses a machine learning model to generate a list of optimal goals based on the user's profile data. The generated goal suggestions are sent back to the device in JSON format, and the device displays them in the UI.

[0524] Selecting and documenting goals

[0525] The user selects an appropriate goal from the displayed suggested goals. For example, a user may select "Improve my data analysis skills using Python" from multiple goals. The device sends the selection results to the server, which then converts the selected goal into a specific sentence using generative AI technology (e.g., OpenAI GPT model). For example, the sentence may be "Successfully complete three projects related to data analysis using Python over the next six months and share the results in an internal presentation." This sentence is then displayed to the user via the device.

[0526] Final confirmation and submission of goals

[0527] The user checks the displayed target sentence and makes corrections if necessary. After final confirmation, the user clicks the "Submit target" button, and the terminal sends the submitted target sentence to the server. The server stores the submitted target sentence in a relational database and returns a confirmation message to the terminal. The terminal displays the confirmation message to the user.

[0528] Prompt Sentence Examples

[0529] For example, here are some examples of prompts that suggest specific, achievable goals based on a user's profile data:

[0530] "Based on the user's profile data, suggest specific, achievable goals. For example, if a user has a goal of 'I want to improve my data analysis skills using Python,' suggest specific steps they should take over the next six months."

[0531] The above is an embodiment of the present invention. This system makes it possible for users to set goals more efficiently and achieve specific and clear goals.

[0532] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0533] Step 1:

[0534] The user accesses the system's login screen and enters their user ID and password. The terminal sends the entered authentication information to the server. At this time, the input data (user ID, password) becomes input from the terminal, and the output is the sent authentication information. The server receives this information and compares it with a database to determine whether the authentication was successful.

[0535] Step 2:

[0536] The server checks the authentication information against the database. The database stores the user's ID and password, and the server checks whether they match this data. If authentication is successful, the server generates an authentication success message and sends it back to the terminal. The input is the authentication information and user information from the database, and the output is an authentication result message.

[0537] Step 3:

[0538] The user enters or uploads profile data in the system. The input data includes skills, work history, past goal history, personality data, etc. The device encrypts this profile data and securely transmits it to the server using the HTTPS protocol. The input is the profile data provided by the user, and the output is the transmission of encrypted data.

[0539] Step 4:

[0540] The server stores the received profile data in a database. When storing, it checks the format of the data and cleanses it if necessary. The input is the encrypted profile data, and the output is the clean data stored in the database.

[0541] Step 5:

[0542] The server performs data preprocessing based on the stored data, specifically imputing missing values, standardizing, encoding categorical variables, etc. The input is the stored profile data, and the output is the preprocessed data.

[0543] Step 6:

[0544] The server uses the preprocessed data to train a machine learning model. For example, it uses Scikit-learn or TensorFlow to apply algorithms to analyze how the user's skills, past goal history, and personality data affect goal achievement. The input is the preprocessed data, and the output is the trained machine learning model.

[0545] Step 7:

[0546] The user submits a goal suggestion request from the system UI. By clicking the "Suggest a goal" button, the device sends the request to the server. The input is the user's request, and the output is the transmission of the request data.

[0547] Step 8:

[0548] The server uses a machine learning model to generate optimal goals based on the user's profile data. Specifically, the model compares past data with the user's current profile and suggests goals with a high success rate. The input is the user's profile data and the machine learning model, and the output is a list of suggested goals.

[0549] Step 9:

[0550] The server returns the generated goal suggestions in JSON format to the device, which displays them in the UI for the user to review. The input is a list of suggested goals, and the output is the goal suggestions displayed in the UI.

[0551] Step 10:

[0552] The user selects an appropriate goal from the suggested goals displayed. For example, the user can select the goal "Improve my data analysis skills using Python." The input is a list of suggested goals, and the output is the selected goal.

[0553] Step 11:

[0554] The terminal sends the selected target to the server. The input is the selected target and the output is the transmission to the server.

[0555] Step 12:

[0556] The server converts the selected goal into a concrete sentence using generative AI technology. For example, the OpenAI GPT model is used to generate a concrete goal sentence such as "Over the next six months, successfully complete three projects related to data analysis using Python and share the results in an internal presentation." The input is the selected goal, and the output is the generated concrete goal sentence.

[0557] Step 13:

[0558] The server returns the generated target sentence in JSON format to the terminal, which displays it in the UI for the user to confirm. The input is the specific target sentence generated, and the output is the target sentence displayed in the UI.

[0559] Step 14:

[0560] The user checks the displayed target sentence and makes corrections if necessary. After final confirmation, the user clicks the "Submit target" button. The input is the generated target sentence and corrections, and the output is the final target sentence.

[0561] Step 15:

[0562] The terminal sends the submitted target sentence to the server. The input is the final target sentence and the output is the transmission to the server.

[0563] Step 16:

[0564] The server saves the submitted target sentence in a relational database. The server confirms that the saving is complete and generates a confirmation message to send back to the terminal. The input is the final target sentence, and the output is the confirmation message.

[0565] Step 17:

[0566] The terminal displays a confirmation message to the user. The input is the confirmation message received from the server, and the output is the message displayed on the user's screen.

[0567] (Application example 1)

[0568] 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."

[0569] The process of factory robot operators setting effective goals based on their own skills and work history and converting these into specific instruction sentences takes time and effort. Furthermore, if appropriate goals are not set, production efficiency may decrease and it may be difficult to achieve the goals. To solve this problem, a system is needed that automatically suggests optimal goals based on the operator's profile data and converts those goals into specific instruction sentences.

[0570] 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.

[0571] In this invention, the server includes means for receiving user profile data, means for saving the received profile data in a database, means for training a machine learning model based on the saved profile data, means for suggesting optimal goals to the user using the trained machine learning model, means for converting the user's selected goals into specific sentences, means for displaying the converted goal sentences to the user, means for the user to submit goals confirmed and revised by the user to the system, means for suggesting production goals based on the robot operator's profile data, and means for converting the proposed production goals into specific instruction sentences. This allows factory robot operators to easily set goals that are optimal for their own attributes, and by converting the goals into specific instruction sentences, it becomes possible to improve production efficiency.

[0572] "User" refers to an individual or group that uses the system, and in the present invention particularly includes operators of factory robots.

[0573] "Profile Data" refers to information detailing a user's abilities and characteristics, such as the user's skills, work history, past goal history, and personality data.

[0574] "Database" refers to an information storage system that systematically stores received profile data and later uses it for training machine learning models, etc.

[0575] A "machine learning model" is a model that uses algorithms to learn from stored data and analyze user profile data.

[0576] "Goal suggestion" refers to the process of using machine learning models to suggest optimal goals to a user.

[0577] "Specific sentences" refer to text data in which the proposed goals are converted from vague or subjective expressions into concrete and clear language.

[0578] "Production goals" refer to specific goals aimed at improving production activities and work efficiency that factory robot operators aim to achieve.

[0579] "Instruction text" refers to text that converts proposed production targets into specific instructions and provides easy-to-understand instructions to operators or robots.

[0580] "Translation" refers to the process of turning a user's chosen goal into a more specific, actionable statement.

[0581] This invention is a system that enables factory robot operators to effectively set production goals based on their own profile data and converts those goals into specific instruction sentences. This system is configured as follows and supports goal setting through a specific process.

[0582] System program configuration

[0583] 1. Collection of profile data

[0584] Users input profile data including their skills, work history, past goal history, personality data, etc. This data is sent to the server via an internet-enabled device (e.g., smartphone, PC).

[0585] 2. Data storage

[0586] The server stores the received profile data in a database, which is constructed using a relational database management system such as SQL.

[0587] 3. Data Analysis and Machine Learning

[0588] The server uses the stored data to train a machine learning model using machine learning libraries such as Python and TensorFlow, which analyzes patterns based on the user's skills and historical data to influence goal achievement.

[0589] 4. Generating goal proposals

[0590] When a user submits a goal suggestion request, the server uses machine learning models to suggest optimal goals, which are automatically generated based on pre-processed user profile data and the trained model.

[0591] 5. Write down your goals in concrete terms

[0592] Once the user selects a suggested goal, the server uses generative AI technology (e.g., GPT-2) to convert the selected goal into a specific instruction sentence. The generative AI model generates text based on the prompt sentence through a tokenizer and model training.

[0593] 6. Final confirmation and submission of goals

[0594] The user checks the displayed instruction text and corrects it if necessary. The final confirmed goal is submitted to the server via the terminal and stored in the database.

[0595] Specific examples

[0596] For example, suppose a user inputs a goal such as "I want to improve the operating efficiency of the manufacturing line by 10%." The device sends this information to the server, which then uses a machine learning model to analyze similar past data. The server then generates a specific goal: "Over the next six months, successfully complete three projects to improve the operating efficiency of the manufacturing line by 10% and share the results at a team meeting." This goal statement is then displayed to the user via the device, who then finally confirms and submits it.

[0597] Prompt Sentence Examples

[0598] "My next goal: to complete a project that will increase production efficiency by 10%."

[0599] Based on this prompt, the generative AI model generates clear and specific instructions for the user, making it easier for factory robot operators to set goals and efficiently take specific actions to achieve them.

[0600] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0601] Step 1:

[0602] The user uses a device to enter profile data (e.g., skills, work history, past goal history, personality data) and sends the data to the server. The entered profile data is sent to the server in JSON format, and after receiving it, it is saved in a database. This allows detailed attribute information about the user to be accumulated.

[0603] Step 2:

[0604] The server then stores the received profile data in a database, using a relational database management system such as SQL to store the data in a structured format, which prepares the data for later data analysis and machine learning training.

[0605] Step 3:

[0606] The server trains a machine learning model based on the stored data. It uses Python and machine learning libraries such as TensorFlow to analyze patterns that influence goal achievement based on the user's skills and historical data. The data is preprocessed for learning, features are extracted, and the model is trained. The result is a model capable of suggesting optimal goals based on the user's attributes.

[0607] Step 4:

[0608] The user submits a goal suggestion request. This request is sent to the server via the terminal. The server, upon receiving the request, uses the learned machine learning model to suggest optimal goals for the user. The server receives the user's profile data as input, predicts goals based on the data, and generates the results as suggested goals.

[0609] Step 5:

[0610] The server sends the generated goal suggestions back to the terminal, which then displays them to the user. The user selects the most appropriate goal from the suggested goals. The selected goal is then sent back to the server via the terminal. This step involves the user's confirmation and selection process.

[0611] Step 6:

[0612] The server utilizes generative AI technology (e.g., GPT-2) to convert the selected goal into specific instruction sentences. Specifically, the selected goal is used as a prompt sentence, and the generative AI model generates specific instruction sentences based on the prompt sentence. The input to the generation process is the prompt sentence, and the output is the instruction sentence. For example, if the prompt sentence is "Complete a project that will improve production efficiency by 10%," the generative AI model will use this as a basis to generate sentences containing specific work instructions.

[0613] Step 7:

[0614] The generated instruction sentence is displayed to the user, who can then confirm and edit it. Once the edits are complete, the final confirmed target sentence is submitted to the server via the terminal. At this time, the user can make edits until they are satisfied, and the final confirmed target sentence is sent to the server.

[0615] Step 8:

[0616] The server stores the final confirmed goal sentences in a database, which can then be used for future evaluations and confirmations. This process enables factory robot operators to easily set specific, achievable goals and receive highly effective instructions for achieving them.

[0617] 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.

[0618] This invention is a system that supports users in planning and documenting their goals to be submitted every six months, and further combines it with an emotion engine that recognizes the user's emotional state to set more personalized goals. This system includes the following specific steps and components:

[0619] Collection and storage of profile data

[0620] 1. A user logs into the system and enters or uploads their profile data (skills, work history, past goal history, personality data, etc.), which includes information detailing the user's abilities and characteristics.

[0621] 2. The device sends the entered profile data to the server.

[0622] 3. The server stores the received profile data in a database.

[0623] Data analysis and learning

[0624] 4. The server trains a machine learning model based on the stored data, analyzing the impact of the user's skills and goal history on goal achievement.

[0625] Emotion recognition and data addition using the emotion engine

[0626] 5. When a user uses the system, the emotion engine recognizes the user's emotional state from their facial expressions, voice, etc.

[0627] 6. The device sends the recognized emotional state data to the server.

[0628] 7. The server adds the emotional state data to the profile data and stores it in a database.

[0629] Goal suggestions and emotional influences

[0630] 8. The user sends a goal suggestion request to the server.

[0631] 9. The server generates optimal goals for the user based on the machine learning model and emotional state data. These suggestions are generated automatically based on the user's profile data, emotional state, and the trained model.

[0632] 10. The server sends the generated goal proposal to the terminal, which displays it to the user.

[0633] Selecting and documenting goals

[0634] 11. The user selects the appropriate goal from the proposed goals.

[0635] 12. The terminal sends the selection results to the server.

[0636] 13. The server uses generative AI technology to convert the selected goal into concrete sentences. Generative AI converts vague expressions into clear and concrete sentences.

[0637] 14. The server sends the generated target sentence to the terminal, which displays it to the user.

[0638] Final confirmation and submission of goals

[0639] 15. The user checks the generated target sentences and makes corrections if necessary.

[0640] 16. The user submits the final confirmed goal to the system.

[0641] 17. The device sends the final confirmed target to the server.

[0642] 18. The server stores the submitted goals in a database.

[0643] Specific examples

[0644] A user logs into the system and enters their profile data and past goal history. The device sends this data to the server, which stores it in a database. Next, when the user uses the system to set goals, the emotion engine analyzes the user's facial expressions and voice to ascertain their emotional state. For example, if the user is feeling stressed, that emotional state is reflected in the system. Based on this data, the server suggests goals that are achievable and less stressful for the user. For example, a specific goal might be suggested: "Successfully complete three projects related to data analysis using Python over the next six months and share the results in an internal presentation." The generated goal text is then sent to the user via the device, where the user can finally review, revise, and submit it.

[0645] The present invention makes it possible to set individual optimal goals that take into consideration the user's emotional state, and is expected to enable efficient and effective goal achievement.

[0646] The processing flow will be explained below.

[0647] Step 1:

[0648] A user logs in to the system.

[0649] Step 2:

[0650] The user enters or uploads their profile data (skills, work history, past goal history, personality data, etc.).

[0651] Step 3:

[0652] The terminal transmits the entered profile data to the server.

[0653] Step 4:

[0654] The server stores the received profile data in a database.

[0655] Step 5:

[0656] The server trains the machine learning model based on the stored data, which includes analyzing the impact of the user's skills and goal history on goal achievement.

[0657] Step 6:

[0658] The emotion engine recognizes the user's emotional state from data such as facial expressions and voice.

[0659] Step 7:

[0660] The terminal transmits the emotional state data recognized by the emotion engine to the server.

[0661] Step 8:

[0662] The server adds the emotional state data to the profile data and stores it in a database.

[0663] Step 9:

[0664] A user sends a goal suggestion request to a server.

[0665] Step 10:

[0666] The server generates optimal goals for the user based on the machine learning model and emotional state data. These goal suggestions are automatically generated based on the user's profile data, emotional state, and the trained model.

[0667] Step 11:

[0668] The server transmits the generated goal proposals to the terminal.

[0669] Step 12:

[0670] The terminal displays the received goal suggestions to the user.

[0671] Step 13:

[0672] The user selects the appropriate goal from the proposed goals.

[0673] Step 14:

[0674] The terminal transmits the selected target to the server.

[0675] Step 15:

[0676] The server uses generative AI technology to convert the selected goals into concrete sentences, which converts ambiguous expressions into clear and specific sentences.

[0677] Step 16:

[0678] The server sends the generated target sentence to the terminal.

[0679] Step 17:

[0680] The terminal displays the generated target sentence to the user.

[0681] Step 18:

[0682] The user checks the generated target sentences and makes corrections as necessary.

[0683] Step 19:

[0684] The user submits the final confirmed goal to the system.

[0685] Step 20:

[0686] The terminal transmits the final confirmed target to the server.

[0687] Step 21:

[0688] The server stores the submitted goals in a database.

[0689] This series of steps allows users to efficiently set optimal goals and submit them in clear written form. Taking into account the user's emotional state, we can set goals that are appropriate for each individual, leading to more effective goal achievement.

[0690] Example 2

[0691] 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."

[0692] Conventional goal setting systems offer a means for suggesting goals based on a user's profile data and past work history, but they are unable to take into account the emotional state of each individual user, making it difficult to set appropriate and achievable goals. This can lead to users being unable to achieve their set goals, resulting in a loss of motivation and stress. The present invention aims to solve this problem.

[0693] 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.

[0694] In this invention, the server includes means for receiving user profile data, means for storing the received profile data in a database, means for training a machine learning model based on the stored profile data, means for recognizing the user's emotional state, means for adding the recognized emotional state data to the profile data and storing it, means for proposing optimal goals to the user using the trained machine learning model and the emotional state data, means for converting the user's selected goal into a specific sentence, means for displaying the converted goal sentence to the user, and means for submitting the user's confirmed and revised goal to the system, thereby enabling individually optimal goal setting that takes the user's emotional state into consideration.

[0695] "User" refers to an individual or organization that uses the System.

[0696] "Profile Data" refers to detailed information about a user, such as the user's skills, work history, past goal history, and personality data.

[0697] "Database" refers to a system or technology that efficiently stores and manages data received by a system and makes it accessible as needed.

[0698] A "machine learning model" is a model that automatically learns statistical patterns and rules based on data and uses them to make predictions and classifications.

[0699] "Emotional state" refers to the current emotional state of the user as analyzed from the user's facial expressions, voice, etc. Examples include joy, sadness, stress, etc.

[0700] "Generative AI" refers to artificial intelligence technology that performs natural language processing such as sentence generation based on provided input data.

[0701] "Goal proposal" means that the system presents specific goals and work plans to the user.

[0702] "Goal sentence" refers to a text that expresses the proposed goal in a specific and detailed manner.

[0703] "Submission means" refers to a means by which a user finally transmits the confirmed and corrected goals to the system.

[0704] "Terminal" refers to a device that allows a user to access the system, input data, and display results. Examples include personal computers and smartphones.

[0705] "Server" refers to the central processing unit of a system, which processes, stores, analyzes, etc. data.

[0706] This invention is a system that supports the user in planning and documenting semi-annual goals and recognizes the user's emotional state. Specific embodiments of this system are described below. Each step clearly indicates the type of hardware or software used to process or calculate data.

[0707] System Configuration

[0708] The system consists of a user terminal, a server, a database, an emotion recognition engine, and a generative AI model.

[0709] User devices include PCs, tablets, smartphones, etc., through which users access the system to enter data and check results. The devices communicate with the server via the Internet.

[0710] The server is a central processing unit that processes data, stores data, trains machine learning models, recognizes emotional states, generates text using generative AI models, etc. Specific examples commonly used include cloud services such as AWS (Amazon Web Services) and Google Cloud.

[0711] The database manages the saved profile data, emotional state data, machine learning models, and generated target sentences. Specifically, a relational database such as PostgreSQL is used.

[0712] The emotion recognition engine provides technology to recognize the user's emotional state in real time by analyzing their facial expressions and voice. It uses a facial recognition library such as OpenCV and a Python voice analysis library.

[0713] A generative AI model is an artificial intelligence technology that generates specific target sentences based on a user's profile data and emotional state. Examples of such models include natural language processing models such as OpenAI's GPT-3.

[0714] Program processing explanation

[0715] The system starts when a user logs in and enters and uploads their profile data. The user's device sends this data to the server, which stores it in a database.

[0716] The server then trains a machine learning model based on the stored data, using Python libraries such as scikit-learn and TensorFlow. The trained model is then saved on the server for further processing.

[0717] When a user uses the system, the emotion recognition engine recognizes the user's emotional state from their facial expressions and voice. The user device sends the recognized emotional state data to the server, which then stores it in a database.

[0718] The server generates optimal goals for the user based on the machine learning model and the stored emotional state data. This process takes into account the user's skills, past goal history, and current emotional state. The generated goal suggestions are sent to the user's device and displayed to the user.

[0719] The user selects the appropriate goal from the proposed set of goals, and the results are sent to the server. The server then uses generative AI technology to convert the selected goal into concrete sentences. OpenAI's GPT-3 is commonly used in this process.

[0720] The generated target sentences are sent back to the user's terminal for confirmation and correction. Once the final target is determined, it is sent from the user's terminal to the server and stored in the database.

[0721] Specific examples

[0722] A user logs into the system and uploads profile data, including past work history and skills. The device sends this data to the server, which stores it in a database. Next, when the user sets goals, an emotion recognition engine analyzes the user's facial expressions and voice to recognize their emotional state. For example, if the user is feeling stressed, the system will reflect that emotional state. Based on this data, the server suggests achievable goals that are less stressful for the user.

[0723] For example, a specific goal is proposed: "Over the next six months, successfully complete three projects related to data analysis using Python and share the results in an internal presentation." This generated goal statement is sent to the user via the terminal, and the user finally reviews, corrects, and submits it.

[0724] Prompt Sentence Examples

[0725] "Generate goals based on this user's profile data and emotional state."

[0726] "Please translate the user's selected goal into a concrete sentence."

[0727] This embodiment enables optimal individual goal setting that takes into account the emotional state of the user, and is expected to lead to efficient and effective goal achievement.

[0728] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0729] Step 1:

[0730] A user logs in to the system. The user enters a username and password on the login screen, and if authentication is successful, the screen moves to the next screen. The input is the username and password, and the output is a flag indicating successful authentication. Specifically, this includes the action of clicking the "Login" button in the upper right corner.

[0731] Step 2:

[0732] The user enters or uploads profile data. Profile data includes skills, work history, past goal history, personality data, etc. Input is text or a file (e.g., Excel), and output is a confirmation screen displayed on the device. Specifically, this includes the actions of filling in each input field and clicking the "Upload" button.

[0733] Step 3:

[0734] The device sends the entered profile data to the server. The input is the data entered or uploaded by the user, and the output is a message confirming the data was sent to the server. The data is sent in JSON format.

[0735] Step 4:

[0736] The server saves the received profile data in a database. The input is the profile data sent from the device, and the output is the ID of the data saved in the database. Specifically, a write process is performed on the database.

[0737] Step 5:

[0738] The server trains a machine learning model based on the stored data. The input is the profile data stored in the database, and the output is the trained machine learning model. The model is trained using Python's scikit-learn and TensorFlow.

[0739] Step 6:

[0740] The server saves the learned machine learning model. The input is the trained machine learning model, and the output is the path to the saved model. Specifically, it includes the operation of saving the model as a file.

[0741] Step 7:

[0742] While the user is using the system, the emotion recognition engine analyzes the user's facial expressions and voice in real time. The input is the user's camera footage and audio data, and the output is the recognized emotional state. Specifically, this includes turning on the camera to analyze facial expressions and collecting audio using the microphone.

[0743] Step 8:

[0744] The device sends the recognized emotional state data to the server. The input is the emotional state data generated by the emotion recognition engine, and the output is a confirmation message sent to the server. The voice analysis results are sent as text data.

[0745] Step 9:

[0746] The server adds the emotional state data to the profile data and saves it in the database. The input is the newly acquired emotional state data, and the output is the updated profile data. The writing process is performed in the database.

[0747] Step 10:

[0748] The user sends a goal proposal request to the server. The input is the user clicking the goal proposal button, and the output is the request data sent to the server.

[0749] Step 11:

[0750] The server uses the machine learning model and emotional state data to generate optimal goals for the user. The input is the trained model, saved profile data, and emotional state data, and the output is the generated goal suggestions.

[0751] Step 12:

[0752] The server sends the generated goal proposals to the terminal, which then displays them to the user. The input is the generated goal proposals, and the output is the displayed goal proposals.

[0753] Step 13:

[0754] The user selects an appropriate goal from the proposed goals. The input is a displayed list of multiple goal suggestions, and the output is the selected goal. Specifically, the action involves clicking and selecting one from the list of goals.

[0755] Step 14:

[0756] The terminal sends the selection result to the server. The input is the ID of the selected target, and the output is a confirmation message to the server.

[0757] Step 15:

[0758] The server uses generative AI technology to convert the selected goal into a specific sentence. The input is the selected goal data, and the output is the specific goal sentence. OpenAI's GPT-3 and other generative AI models are used.

[0759] Step 16:

[0760] The server sends the generated target sentence to the terminal, which displays it to the user. The input is the generated target sentence, and the output is the displayed target sentence.

[0761] Step 17:

[0762] The user reviews the generated target sentence and makes corrections if necessary. The input is the displayed target sentence, and the output is the corrected target sentence. Specifically, this involves editing the sentence by typing into a text field.

[0763] Step 18:

[0764] The user submits the finalized goal to the system. The input is the finalized goal text, and the output is a submission request to the server. This includes clicking the "Submit" button.

[0765] Step 19:

[0766] The terminal sends the final confirmed goal to the server. The input is the final confirmed goal text, and the output is a transmission confirmation message to the server.

[0767] Step 20:

[0768] The server saves the submitted goal in the database. The input is the final confirmed goal text, and the output is the ID of the saved goal data. The write process is performed in the database.

[0769] (Application example 2)

[0770] 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."

[0771] In modern self-driving vehicles, it is difficult to provide appropriate driving guidance and goal setting that takes into account the driver's emotional state. Furthermore, there is no system in place to recognize the driver's emotional state in real time and provide appropriate advice, meaning that support for continuing safe driving when the driver feels stressed or fatigued is insufficient. The present invention aims to solve these problems by providing a system that provides individually optimized driving goals and advice to drivers.

[0772] 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.

[0773] In this invention, the server includes means for receiving user profile data, means for storing the received profile data in a database, means for training a machine learning model based on the stored profile data, means for suggesting optimal goals to the user using the trained machine learning model, means for recognizing the user's emotional state while driving, means for generating driving advice in real time based on the recognized emotional state, means for displaying the generated advice to the user, means for converting the user's selected goal into a specific sentence, means for displaying the converted goal sentence to the user, and means for submitting the user's confirmed and revised goal to the system. This enables individually optimal driving instruction and goal setting that take the driver's emotional state into consideration, thereby realizing safe and efficient driving assistance.

[0774] "User profile data" refers to information about an individual, such as driver skills, driving experience, past driving history, and personality data.

[0775] "Database" refers to a collection of information for managing stored profile data and emotional data.

[0776] A "machine learning model" is an algorithm that learns from collected data and generates patterns and predictions.

[0777] "Optimal goals" refer to achievable, specific driving goals that are set based on the user's profile data and emotional state.

[0778] "Emotional state" refers to a driver's psychological and emotional state while driving, which is usually recognized through facial expressions and tone of voice.

[0779] "Means for generating driving advice in real time" refers to a method for instantly analyzing the driver's emotional state and providing driving guidance or advice based on that.

[0780] "Means of converting into concrete sentences" refers to a method of using generative AI to convert abstract goals and guidelines into clear and concrete sentences.

[0781] "Generative AI" refers to a technology that uses generative artificial intelligence technology to generate sentences in natural language based on input information.

[0782] The present invention provides a system for recognizing a user's emotional state while driving and providing appropriate driving goals and advice in real time. This system includes the following specific programs and components:

[0783] Program processing

[0784] 1. Collection and storage of profile data

[0785] A user logs into the system installed in the vehicle and enters their profile data (driving experience, skills, past driving history, personality data, etc.). This data is sent from the in-vehicle terminal to a server and stored in a database. This database contains detailed information about each individual driver.

[0786] 2. Data analysis and learning

[0787] The server trains a machine learning model based on the stored profile data. The machine learning model (e.g., TensorFlow) analyzes this data to learn the user's driving patterns and skill level. The model uses data from driving history and driving behavior to discover patterns related to goal achievement.

[0788] 3. Emotion recognition and data addition using the emotion engine

[0789] While driving, the vehicle's cameras and microphones capture the driver's facial expressions and voice and send them to an emotion recognition engine (e.g., Microsoft Azure Emotion API). The emotion recognition engine analyzes this data and identifies the driver's emotional state in real time. The identified emotion data is sent from the in-vehicle terminal to a server and stored in a database.

[0790] 4. Real-time goal suggestions and emotional influence

[0791] When a user requests a goal suggestion from the system, the server generates appropriate driving goals and advice based on machine learning models and real-time emotion data. This generation process uses a generative AI model (e.g., OpenAI GPT-4). The generated advice and goals are displayed on the in-car display.

[0792] 5. Identifying and documenting goals

[0793] The user selects suggested goals and advice and sends the results from the in-car device to the server. The server then uses generative AI to convert the abstract goals into concrete sentences. In this process, the generative AI generates documents in natural language based on the input information. The generated goal sentences are then displayed on the in-car display.

[0794] 6. Final review and feedback

[0795] The user reviews the generated goal sentences and makes any necessary corrections. The final goal is then submitted to the system and stored in the database.

[0796] Specific examples

[0797] A user logs into the system and enters their profile data and past driving history, including driving skills (e.g., highway driving, city driving), past accident history, and current driving goals. While driving, an in-vehicle camera recognizes facial expressions, and their emotional state (e.g., nervous, relaxed) is stored in a database. When the user requests "driving goals for the next hour," the system suggests specific goals, such as "obey the speed limit and avoid sudden acceleration and braking." A generative AI model is used to elaborate on these goal statements, which the user then confirms.

[0798] Prompt Sentence Examples

[0799] "Suggest a driving goal for the next hour."

[0800] "What should I pay attention to while driving?"

[0801] I need some advice on how to relax.

[0802] This system can provide individually optimized driving assistance by combining the user's profile data with their emotional state while driving.

[0803] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0804] Step 1:

[0805] The user logs into the system installed in the vehicle. The user enters profile data such as their driving experience, skills, past driving history, and personality data. This data is sent by the terminal to the server and stored in a database. This allows detailed information about each user to be stored in a central database.

[0806] Input: User profile data (driving experience, skills, past driving history, personality data)

[0807] Output: Profile data stored in a database

[0808] Step 2:

[0809] The server trains a machine learning model based on the stored profile data. The machine learning model (e.g., TensorFlow) analyzes the driver's characteristics and patterns from this data and generates a personalized driving profile for each user, which then reflects their driving habits and skill level in the model.

[0810] Input: Profile data stored in the database

[0811] Output: A trained machine learning model

[0812] Step 3:

[0813] While the user is driving the vehicle, the camera and microphone inside the vehicle capture the user's facial expressions and voice. The device sends this data to an emotion recognition engine (e.g., Microsoft Azure Emotion API) to analyze the user's emotional state in real time. The analyzed emotional data is then sent to a server and stored in a database.

[0814] Input: User's facial expression and voice data

[0815] Output: Real-time analyzed emotional state data

[0816] Step 4:

[0817] When a user requests a goal suggestion, the server generates appropriate driving goals and advice based on machine learning models and real-time emotion data. This generation process uses a generative AI model (e.g., OpenAI GPT-4). The generated advice and goals are displayed on the in-car display.

[0818] Input: User goal suggestion request, machine learning model, real-time sentiment data

[0819] Output: Generated driving goals and advice sentences

[0820] Step 5:

[0821] Once the user selects a suggested goal sentence or piece of advice, the device sends the result to the server, which then uses generative AI to convert the abstract goal into a concrete sentence, thereby clarifying any ambiguity in the goal. The generated goal sentence is then displayed on the vehicle's display.

[0822] Input: User selection results, generated AI model

[0823] Output: Specific target sentence

[0824] Step 6:

[0825] The user checks the generated goal sentences and makes corrections as necessary. The final version of the goal is submitted to the system via the terminal and stored in the database. This allows the optimal goal to be set in a way that satisfies the user.

[0826] Input: User confirmation and correction details

[0827] Output: Final target sentence stored in the database

[0828] Through these steps, individually optimized driving assistance that takes into account the user's emotional state is realized.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] [Third embodiment]

[0833] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0834] 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.

[0835] 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).

[0836] 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.

[0837] 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.

[0838] 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).

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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."

[0845] The present invention is a system for supporting users in planning and documenting goals to be submitted every six months. This system is implemented by the following procedures and components.

[0846] Profile Data Collection

[0847] 1. A user logs into the system and enters or uploads profile data, such as their skills, work history, past goal history, personality data, etc. This data details the user's abilities and characteristics.

[0848] 2. The device (user's computer or smartphone) sends the entered profile data to the server.

[0849] Data analysis and learning

[0850] 3. The server stores the received profile data in a database.

[0851] 4. The server trains a machine learning model based on the stored data, which involves analyzing how the user's skills, past goal history, and personality data affect goal achievement.

[0852] Generate goal suggestions

[0853] 5. The user submits a goal suggestion request.

[0854] 6. The server uses machine learning models to suggest optimal goals for the user, which are automatically generated based on the user's profile data and the trained models.

[0855] 7. The server returns the generated goal proposals to the terminal, which displays them to the user.

[0856] Selecting and documenting goals

[0857] 8. The user selects the appropriate goal from the proposed goals.

[0858] 9. The terminal sends the selection results to the server.

[0859] 10. The server utilizes generative AI technology to translate the selected goals into concrete sentences, thereby converting vague or subjective expressions into concrete and clear language.

[0860] 11. The server returns the generated target sentence to the terminal, which displays it to the user.

[0861] Final confirmation and submission of goals

[0862] 12. The user checks the displayed target sentence and makes corrections if necessary.

[0863] 13. After the user finalizes the goal, they submit it to the system.

[0864] 14. The terminal sends the submitted target sentence to the server, which stores it in a database.

[0865] Specific examples

[0866] For example, a user might enter a goal into the system: "I want to improve my data analysis skills using Python." First, the device sends this information to the server, which uses a machine learning model to analyze similar past data. Next, a specific goal might be generated: "Over the next six months, successfully complete three projects related to data analysis using Python and share the results in an internal presentation." This goal statement is then sent to the user via the device, where the user can finally review and submit it.

[0867] The above is an embodiment of the present invention, and in this way the efficiency of the user's goal setting work is improved.

[0868] The processing flow will be explained below.

[0869] Step 1:

[0870] A user logs in to the system.

[0871] Step 2:

[0872] The user enters or uploads their profile data (skills, work history, past goal history, personality data, etc.).

[0873] Step 3:

[0874] The terminal transmits the entered profile data to the server.

[0875] Step 4:

[0876] The server stores the received profile data in a database.

[0877] Step 5:

[0878] The server trains the machine learning model based on the stored data, which includes analyzing the impact of the user's skills and goal history on goal achievement.

[0879] Step 6:

[0880] A user sends a goal suggestion request to a server.

[0881] Step 7:

[0882] The server uses a trained machine learning model to generate optimal goals for the user.

[0883] Step 8:

[0884] The server transmits the generated goal proposals to the terminal.

[0885] Step 9:

[0886] The terminal displays the received goal suggestions to the user.

[0887] Step 10:

[0888] The user selects from the proposed goals.

[0889] Step 11:

[0890] The terminal transmits the selected target to the server.

[0891] Step 12:

[0892] The server uses generative AI technology to convert the selected goals into concrete sentences, which converts ambiguous expressions into clear and specific sentences.

[0893] Step 13:

[0894] The server sends the generated target sentence to the terminal.

[0895] Step 14:

[0896] The terminal displays the generated target sentence to the user.

[0897] Step 15:

[0898] The user checks the generated target sentence and makes corrections if necessary.

[0899] Step 16:

[0900] The user submits the final confirmed goal to the system.

[0901] Step 17:

[0902] The terminal transmits the final confirmed target to the server.

[0903] Step 18:

[0904] The server stores the submitted goals in a database.

[0905] This series of steps allows users to efficiently set their own optimal goals and submit those goals in clear writing.

[0906] Example 1

[0907] 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."

[0908] In conventional goal setting systems, it takes a great deal of time and effort for users to individually set goals and translate them into concrete sentences. Furthermore, the system lacks the ability to utilize the user's past data to suggest optimal goals, and the suggested goals often do not match the user's actual situation. Furthermore, there is a lack of support for converting the suggested goals from vague expressions into specific, clear expressions. This results in inefficient goal setting and hinders the improvement of users' performance.

[0909] 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.

[0910] In this invention, the server includes means for receiving a user's profile data, means for storing the received profile data in a database, means for training a machine learning model based on the stored profile data, means for suggesting optimal goals to the user using the trained machine learning model, means for converting the user's selected goals into specific sentences using generative AI technology, means for displaying the converted goal sentences to the user, means for the user to submit goals confirmed and revised by the user to the system, and means for storing the submitted goals in the database. This enables users to efficiently set goals and describe them in specific and clear terms. Furthermore, optimal goal suggestions can be realized by utilizing the user's past goal history, work history, skill data, and personality data, enabling goal setting that is tailored to the user's actual situation.

[0911] "User profile data" is a general term for information that indicates the user's abilities and characteristics, such as the user's skills, work history, past goal history, and personality data.

[0912] The "means for receiving" refers to a function that utilizes a network, among other things, for incorporating data provided by a user into the system.

[0913] "Means for saving in a database" refers to a function for centrally storing received data and managing it so that it can be retrieved as needed.

[0914] "Means for training a machine learning model" means a function for training a model based on an algorithm using received and stored data to improve analytical capabilities.

[0915] The "means of suggesting optimal goals to the user" is a function that uses a trained machine learning model to extract and present goals that are considered optimal based on the user's profile data.

[0916] "Generative AI technology" is a technology that uses artificial intelligence techniques such as deep learning to generate new information and content (in this case, specific target sentences) based on input data.

[0917] "Means for converting into concrete sentences" is a function that uses generative AI technology to convert the goal selected by the user into detailed and clear language expression.

[0918] The "display means" is a function for displaying the generated target sentence so that the user can view and confirm it.

[0919] "Means for submitting to the system" is a function that allows the user to confirm and modify the goals, send them to the server, and register them.

[0920] "Storage means" is a function that stores the submitted target sentences in a database again, keeping them available for future reference and use.

[0921] The present invention is a system that supports users in planning and documenting their semi-annual goals. The system receives user profile data, trains a machine learning model based on the data, and generates specific goal documents using generative AI technology.

[0922] The embodiment of the present invention is specifically implemented as follows.

[0923] Profile Data Collection

[0924] Users access the system's login screen and log in by entering their user ID and password. Next, they enter or upload profile data such as their skills, work history, past goal history, and personality data. The hardware used is the user's own device, such as a computer or smartphone. The device encrypts the entered profile data and sends it to the server using the HTTPS protocol.

[0925] Data analysis and learning

[0926] The server stores the received profile data in a relational database (e.g., MySQL or PostgreSQL). The server preprocesses the data (e.g., imputing missing values, standardizing, encoding categorical variables) and trains a machine learning model (e.g., using Scikit-learn or TensorFlow) based on the data. This process includes analyzing how the user's skills, past goal history, and personality data affect goal achievement.

[0927] Generate goal suggestions

[0928] The user submits a goal suggestion request through the system's UI. After clicking the "Suggest a goal" button, the device sends the goal suggestion request to the server. The server uses a machine learning model to generate a list of optimal goals based on the user's profile data. The generated goal suggestions are sent back to the device in JSON format, and the device displays them in the UI.

[0929] Selecting and documenting goals

[0930] The user selects an appropriate goal from the displayed suggested goals. For example, a user may select "Improve my data analysis skills using Python" from multiple goals. The device sends the selection results to the server, which then converts the selected goal into a specific sentence using generative AI technology (e.g., OpenAI GPT model). For example, the sentence may be "Successfully complete three projects related to data analysis using Python over the next six months and share the results in an internal presentation." This sentence is then displayed to the user via the device.

[0931] Final confirmation and submission of goals

[0932] The user checks the displayed target sentence and makes corrections if necessary. After final confirmation, the user clicks the "Submit target" button, and the terminal sends the submitted target sentence to the server. The server stores the submitted target sentence in a relational database and returns a confirmation message to the terminal. The terminal displays the confirmation message to the user.

[0933] Prompt Sentence Examples

[0934] For example, here are some examples of prompts that suggest specific, achievable goals based on a user's profile data:

[0935] "Based on the user's profile data, suggest specific, achievable goals. For example, if a user has a goal of 'I want to improve my data analysis skills using Python,' suggest specific steps they should take over the next six months."

[0936] The above is an embodiment of the present invention. This system makes it possible for users to set goals more efficiently and achieve specific and clear goals.

[0937] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0938] Step 1:

[0939] The user accesses the system's login screen and enters their user ID and password. The terminal sends the entered authentication information to the server. At this time, the input data (user ID, password) becomes input from the terminal, and the output is the sent authentication information. The server receives this information and compares it with a database to determine whether the authentication was successful.

[0940] Step 2:

[0941] The server checks the authentication information against the database. The database stores the user's ID and password, and the server checks whether they match this data. If authentication is successful, the server generates an authentication success message and sends it back to the terminal. The input is the authentication information and user information from the database, and the output is an authentication result message.

[0942] Step 3:

[0943] The user enters or uploads profile data in the system. The input data includes skills, work history, past goal history, personality data, etc. The device encrypts this profile data and securely transmits it to the server using the HTTPS protocol. The input is the profile data provided by the user, and the output is the transmission of encrypted data.

[0944] Step 4:

[0945] The server stores the received profile data in a database. When storing, it checks the format of the data and cleanses it if necessary. The input is the encrypted profile data, and the output is the clean data stored in the database.

[0946] Step 5:

[0947] The server performs data preprocessing based on the stored data, specifically imputing missing values, standardizing, encoding categorical variables, etc. The input is the stored profile data, and the output is the preprocessed data.

[0948] Step 6:

[0949] The server uses the preprocessed data to train a machine learning model. For example, it uses Scikit-learn or TensorFlow to apply algorithms to analyze how the user's skills, past goal history, and personality data affect goal achievement. The input is the preprocessed data, and the output is the trained machine learning model.

[0950] Step 7:

[0951] The user submits a goal suggestion request from the system UI. By clicking the "Suggest a goal" button, the device sends the request to the server. The input is the user's request, and the output is the transmission of the request data.

[0952] Step 8:

[0953] The server uses a machine learning model to generate optimal goals based on the user's profile data. Specifically, the model compares past data with the user's current profile and suggests goals with a high success rate. The input is the user's profile data and the machine learning model, and the output is a list of suggested goals.

[0954] Step 9:

[0955] The server returns the generated goal suggestions in JSON format to the device, which displays them in the UI for the user to review. The input is a list of suggested goals, and the output is the goal suggestions displayed in the UI.

[0956] Step 10:

[0957] The user selects an appropriate goal from the suggested goals displayed. For example, the user can select the goal "Improve my data analysis skills using Python." The input is a list of suggested goals, and the output is the selected goal.

[0958] Step 11:

[0959] The terminal sends the selected target to the server. The input is the selected target and the output is the transmission to the server.

[0960] Step 12:

[0961] The server converts the selected goal into a concrete sentence using generative AI technology. For example, the OpenAI GPT model is used to generate a concrete goal sentence such as "Over the next six months, successfully complete three projects related to data analysis using Python and share the results in an internal presentation." The input is the selected goal, and the output is the generated concrete goal sentence.

[0962] Step 13:

[0963] The server returns the generated target sentence in JSON format to the terminal, which displays it in the UI for the user to confirm. The input is the specific target sentence generated, and the output is the target sentence displayed in the UI.

[0964] Step 14:

[0965] The user checks the displayed target sentence and makes corrections if necessary. After final confirmation, the user clicks the "Submit target" button. The input is the generated target sentence and corrections, and the output is the final target sentence.

[0966] Step 15:

[0967] The terminal sends the submitted target sentence to the server. The input is the final target sentence and the output is the transmission to the server.

[0968] Step 16:

[0969] The server saves the submitted target sentence in a relational database. The server confirms that the saving is complete and generates a confirmation message to send back to the terminal. The input is the final target sentence, and the output is the confirmation message.

[0970] Step 17:

[0971] The terminal displays a confirmation message to the user. The input is the confirmation message received from the server, and the output is the message displayed on the user's screen.

[0972] (Application example 1)

[0973] 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."

[0974] The process of factory robot operators setting effective goals based on their own skills and work history and converting these into specific instruction sentences takes time and effort. Furthermore, if appropriate goals are not set, production efficiency may decrease and it may be difficult to achieve the goals. To solve this problem, a system is needed that automatically suggests optimal goals based on the operator's profile data and converts those goals into specific instruction sentences.

[0975] 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.

[0976] In this invention, the server includes means for receiving user profile data, means for saving the received profile data in a database, means for training a machine learning model based on the saved profile data, means for suggesting optimal goals to the user using the trained machine learning model, means for converting the user's selected goals into specific sentences, means for displaying the converted goal sentences to the user, means for the user to submit goals confirmed and revised by the user to the system, means for suggesting production goals based on the robot operator's profile data, and means for converting the proposed production goals into specific instruction sentences. This allows factory robot operators to easily set goals that are optimal for their own attributes, and by converting the goals into specific instruction sentences, it becomes possible to improve production efficiency.

[0977] "User" refers to an individual or group that uses the system, and in the present invention particularly includes operators of factory robots.

[0978] "Profile Data" refers to information detailing a user's abilities and characteristics, such as the user's skills, work history, past goal history, and personality data.

[0979] "Database" refers to an information storage system that systematically stores received profile data and later uses it for training machine learning models, etc.

[0980] A "machine learning model" is a model that uses algorithms to learn from stored data and analyze user profile data.

[0981] "Goal suggestion" refers to the process of using machine learning models to suggest optimal goals to a user.

[0982] "Specific sentences" refer to text data in which the proposed goals are converted from vague or subjective expressions into concrete and clear language.

[0983] "Production goals" refer to specific goals aimed at improving production activities and work efficiency that factory robot operators aim to achieve.

[0984] "Instruction text" refers to text that converts proposed production targets into specific instructions and provides easy-to-understand instructions to operators or robots.

[0985] "Translation" refers to the process of turning a user's chosen goal into a more specific, actionable statement.

[0986] This invention is a system that enables factory robot operators to effectively set production goals based on their own profile data and converts those goals into specific instruction sentences. This system is configured as follows and supports goal setting through a specific process.

[0987] System program configuration

[0988] 1. Collection of profile data

[0989] Users input profile data including their skills, work history, past goal history, personality data, etc. This data is sent to the server via an internet-enabled device (e.g., smartphone, PC).

[0990] 2. Data storage

[0991] The server stores the received profile data in a database, which is constructed using a relational database management system such as SQL.

[0992] 3. Data Analysis and Machine Learning

[0993] The server uses the stored data to train a machine learning model using machine learning libraries such as Python and TensorFlow, which analyzes patterns based on the user's skills and historical data to influence goal achievement.

[0994] 4. Generating goal proposals

[0995] When a user submits a goal suggestion request, the server uses machine learning models to suggest optimal goals, which are automatically generated based on pre-processed user profile data and the trained model.

[0996] 5. Write down your goals in concrete terms

[0997] Once the user selects a suggested goal, the server uses generative AI technology (e.g., GPT-2) to convert the selected goal into a specific instruction sentence. The generative AI model generates text based on the prompt sentence through a tokenizer and model training.

[0998] 6. Final confirmation and submission of goals

[0999] The user checks the displayed instruction text and corrects it if necessary. The final confirmed goal is submitted to the server via the terminal and stored in the database.

[1000] Specific examples

[1001] For example, suppose a user inputs a goal such as "I want to improve the operating efficiency of the manufacturing line by 10%." The device sends this information to the server, which then uses a machine learning model to analyze similar past data. The server then generates a specific goal: "Over the next six months, successfully complete three projects to improve the operating efficiency of the manufacturing line by 10% and share the results at a team meeting." This goal statement is then displayed to the user via the device, who then finally confirms and submits it.

[1002] Prompt Sentence Examples

[1003] "My next goal: to complete a project that will increase production efficiency by 10%."

[1004] Based on this prompt, the generative AI model generates clear and specific instructions for the user, making it easier for factory robot operators to set goals and efficiently take specific actions to achieve them.

[1005] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1006] Step 1:

[1007] The user uses a device to enter profile data (e.g., skills, work history, past goal history, personality data) and sends the data to the server. The entered profile data is sent to the server in JSON format, and after receiving it, it is saved in a database. This allows detailed attribute information about the user to be accumulated.

[1008] Step 2:

[1009] The server then stores the received profile data in a database, using a relational database management system such as SQL to store the data in a structured format, which prepares the data for later data analysis and machine learning training.

[1010] Step 3:

[1011] The server trains a machine learning model based on the stored data. It uses Python and machine learning libraries such as TensorFlow to analyze patterns that influence goal achievement based on the user's skills and historical data. The data is preprocessed for learning, features are extracted, and the model is trained. The result is a model capable of suggesting optimal goals based on the user's attributes.

[1012] Step 4:

[1013] The user submits a goal suggestion request. This request is sent to the server via the terminal. The server, upon receiving the request, uses the learned machine learning model to suggest optimal goals for the user. The server receives the user's profile data as input, predicts goals based on the data, and generates the results as suggested goals.

[1014] Step 5:

[1015] The server sends the generated goal suggestions back to the terminal, which then displays them to the user. The user selects the most appropriate goal from the suggested goals. The selected goal is then sent back to the server via the terminal. This step involves the user's confirmation and selection process.

[1016] Step 6:

[1017] The server utilizes generative AI technology (e.g., GPT-2) to convert the selected goal into specific instruction sentences. Specifically, the selected goal is used as a prompt sentence, and the generative AI model generates specific instruction sentences based on the prompt sentence. The input to the generation process is the prompt sentence, and the output is the instruction sentence. For example, if the prompt sentence is "Complete a project that will improve production efficiency by 10%," the generative AI model will use this as a basis to generate sentences containing specific work instructions.

[1018] Step 7:

[1019] The generated instruction sentence is displayed to the user, who can then confirm and edit it. Once the edits are complete, the final confirmed target sentence is submitted to the server via the terminal. At this time, the user can make edits until they are satisfied, and the final confirmed target sentence is sent to the server.

[1020] Step 8:

[1021] The server stores the final confirmed goal sentences in a database, which can then be used for future evaluations and confirmations. This process enables factory robot operators to easily set specific, achievable goals and receive highly effective instructions for achieving them.

[1022] 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.

[1023] This invention is a system that supports users in planning and documenting their goals to be submitted every six months, and further combines it with an emotion engine that recognizes the user's emotional state to set more personalized goals. This system includes the following specific steps and components:

[1024] Collection and storage of profile data

[1025] 1. A user logs into the system and enters or uploads their profile data (skills, work history, past goal history, personality data, etc.), which includes information detailing the user's abilities and characteristics.

[1026] 2. The device sends the entered profile data to the server.

[1027] 3. The server stores the received profile data in a database.

[1028] Data analysis and learning

[1029] 4. The server trains a machine learning model based on the stored data, analyzing the impact of the user's skills and goal history on goal achievement.

[1030] Emotion recognition and data addition using the emotion engine

[1031] 5. When a user uses the system, the emotion engine recognizes the user's emotional state from their facial expressions, voice, etc.

[1032] 6. The device sends the recognized emotional state data to the server.

[1033] 7. The server adds the emotional state data to the profile data and stores it in a database.

[1034] Goal suggestions and emotional influences

[1035] 8. The user sends a goal suggestion request to the server.

[1036] 9. The server generates optimal goals for the user based on the machine learning model and emotional state data. These suggestions are generated automatically based on the user's profile data, emotional state, and the trained model.

[1037] 10. The server sends the generated goal proposal to the terminal, which displays it to the user.

[1038] Selecting and documenting goals

[1039] 11. The user selects the appropriate goal from the proposed goals.

[1040] 12. The terminal sends the selection results to the server.

[1041] 13. The server uses generative AI technology to convert the selected goal into concrete sentences. Generative AI converts vague expressions into clear and concrete sentences.

[1042] 14. The server sends the generated target sentence to the terminal, which displays it to the user.

[1043] Final confirmation and submission of goals

[1044] 15. The user checks the generated target sentences and makes corrections if necessary.

[1045] 16. The user submits the final confirmed goal to the system.

[1046] 17. The device sends the final confirmed target to the server.

[1047] 18. The server stores the submitted goals in a database.

[1048] Specific examples

[1049] A user logs into the system and enters their profile data and past goal history. The device sends this data to the server, which stores it in a database. Next, when the user uses the system to set goals, the emotion engine analyzes the user's facial expressions and voice to ascertain their emotional state. For example, if the user is feeling stressed, that emotional state is reflected in the system. Based on this data, the server suggests goals that are achievable and less stressful for the user. For example, a specific goal might be suggested: "Successfully complete three projects related to data analysis using Python over the next six months and share the results in an internal presentation." The generated goal text is then sent to the user via the device, where the user can finally review, revise, and submit it.

[1050] The present invention makes it possible to set individual optimal goals that take into consideration the user's emotional state, and is expected to enable efficient and effective goal achievement.

[1051] The processing flow will be explained below.

[1052] Step 1:

[1053] A user logs in to the system.

[1054] Step 2:

[1055] The user enters or uploads their profile data (skills, work history, past goal history, personality data, etc.).

[1056] Step 3:

[1057] The terminal transmits the entered profile data to the server.

[1058] Step 4:

[1059] The server stores the received profile data in a database.

[1060] Step 5:

[1061] The server trains the machine learning model based on the stored data, which includes analyzing the impact of the user's skills and goal history on goal achievement.

[1062] Step 6:

[1063] The emotion engine recognizes the user's emotional state from data such as facial expressions and voice.

[1064] Step 7:

[1065] The terminal transmits the emotional state data recognized by the emotion engine to the server.

[1066] Step 8:

[1067] The server adds the emotional state data to the profile data and stores it in a database.

[1068] Step 9:

[1069] A user sends a goal suggestion request to a server.

[1070] Step 10:

[1071] The server generates optimal goals for the user based on the machine learning model and emotional state data. These goal suggestions are automatically generated based on the user's profile data, emotional state, and the trained model.

[1072] Step 11:

[1073] The server transmits the generated goal proposals to the terminal.

[1074] Step 12:

[1075] The terminal displays the received goal suggestions to the user.

[1076] Step 13:

[1077] The user selects the appropriate goal from the proposed goals.

[1078] Step 14:

[1079] The terminal transmits the selected target to the server.

[1080] Step 15:

[1081] The server uses generative AI technology to convert the selected goals into concrete sentences, which converts ambiguous expressions into clear and specific sentences.

[1082] Step 16:

[1083] The server sends the generated target sentence to the terminal.

[1084] Step 17:

[1085] The terminal displays the generated target sentence to the user.

[1086] Step 18:

[1087] The user checks the generated target sentences and makes corrections as necessary.

[1088] Step 19:

[1089] The user submits the final confirmed goal to the system.

[1090] Step 20:

[1091] The terminal transmits the final confirmed target to the server.

[1092] Step 21:

[1093] The server stores the submitted goals in a database.

[1094] This series of steps allows users to efficiently set optimal goals and submit them in clear written form. Taking into account the user's emotional state, we can set goals that are appropriate for each individual, leading to more effective goal achievement.

[1095] Example 2

[1096] 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."

[1097] Conventional goal setting systems offer a means for suggesting goals based on a user's profile data and past work history, but they are unable to take into account the emotional state of each individual user, making it difficult to set appropriate and achievable goals. This can lead to users being unable to achieve their set goals, resulting in a loss of motivation and stress. The present invention aims to solve this problem.

[1098] 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.

[1099] In this invention, the server includes means for receiving user profile data, means for storing the received profile data in a database, means for training a machine learning model based on the stored profile data, means for recognizing the user's emotional state, means for adding the recognized emotional state data to the profile data and storing it, means for proposing optimal goals to the user using the trained machine learning model and the emotional state data, means for converting the user's selected goal into a specific sentence, means for displaying the converted goal sentence to the user, and means for submitting the user's confirmed and revised goal to the system, thereby enabling individually optimal goal setting that takes the user's emotional state into consideration.

[1100] "User" refers to an individual or organization that uses the System.

[1101] "Profile Data" refers to detailed information about a user, such as the user's skills, work history, past goal history, and personality data.

[1102] "Database" refers to a system or technology that efficiently stores and manages data received by a system and makes it accessible as needed.

[1103] A "machine learning model" is a model that automatically learns statistical patterns and rules based on data and uses them to make predictions and classifications.

[1104] "Emotional state" refers to the current emotional state of the user as analyzed from the user's facial expressions, voice, etc. Examples include joy, sadness, stress, etc.

[1105] "Generative AI" refers to artificial intelligence technology that performs natural language processing such as sentence generation based on provided input data.

[1106] "Goal proposal" means that the system presents specific goals and work plans to the user.

[1107] "Goal sentence" refers to a text that expresses the proposed goal in a specific and detailed manner.

[1108] "Submission means" refers to a means by which a user finally transmits the confirmed and corrected goals to the system.

[1109] "Terminal" refers to a device that allows a user to access the system, input data, and display results. Examples include personal computers and smartphones.

[1110] "Server" refers to the central processing unit of a system, which processes, stores, analyzes, etc. data.

[1111] This invention is a system that supports the user in planning and documenting semi-annual goals and recognizes the user's emotional state. Specific embodiments of this system are described below. Each step clearly indicates the type of hardware or software used to process or calculate data.

[1112] System Configuration

[1113] The system consists of a user terminal, a server, a database, an emotion recognition engine, and a generative AI model.

[1114] User devices include PCs, tablets, smartphones, etc., through which users access the system to enter data and check results. The devices communicate with the server via the Internet.

[1115] The server is a central processing unit that processes data, stores data, trains machine learning models, recognizes emotional states, generates text using generative AI models, etc. Specific examples commonly used include cloud services such as AWS (Amazon Web Services) and Google Cloud.

[1116] The database manages the saved profile data, emotional state data, machine learning models, and generated target sentences. Specifically, a relational database such as PostgreSQL is used.

[1117] The emotion recognition engine provides technology to recognize the user's emotional state in real time by analyzing their facial expressions and voice. It uses a facial recognition library such as OpenCV and a Python voice analysis library.

[1118] A generative AI model is an artificial intelligence technology that generates specific target sentences based on a user's profile data and emotional state. Examples of such models include natural language processing models such as OpenAI's GPT-3.

[1119] Program processing explanation

[1120] The system starts when a user logs in and enters and uploads their profile data. The user's device sends this data to the server, which stores it in a database.

[1121] The server then trains a machine learning model based on the stored data, using Python libraries such as scikit-learn and TensorFlow. The trained model is then saved on the server for further processing.

[1122] When a user uses the system, the emotion recognition engine recognizes the user's emotional state from their facial expressions and voice. The user device sends the recognized emotional state data to the server, which then stores it in a database.

[1123] The server generates optimal goals for the user based on the machine learning model and the stored emotional state data. This process takes into account the user's skills, past goal history, and current emotional state. The generated goal suggestions are sent to the user's device and displayed to the user.

[1124] The user selects the appropriate goal from the proposed set of goals, and the results are sent to the server. The server then uses generative AI technology to convert the selected goal into concrete sentences. OpenAI's GPT-3 is commonly used in this process.

[1125] The generated target sentences are sent back to the user's terminal for confirmation and correction. Once the final target is determined, it is sent from the user's terminal to the server and stored in the database.

[1126] Specific examples

[1127] A user logs into the system and uploads profile data, including past work history and skills. The device sends this data to the server, which stores it in a database. Next, when the user sets goals, an emotion recognition engine analyzes the user's facial expressions and voice to recognize their emotional state. For example, if the user is feeling stressed, the system will reflect that emotional state. Based on this data, the server suggests achievable goals that are less stressful for the user.

[1128] For example, a specific goal is proposed: "Over the next six months, successfully complete three projects related to data analysis using Python and share the results in an internal presentation." This generated goal statement is sent to the user via the terminal, and the user finally reviews, corrects, and submits it.

[1129] Prompt Sentence Examples

[1130] "Generate goals based on this user's profile data and emotional state."

[1131] "Please translate the user's selected goal into a concrete sentence."

[1132] This embodiment enables optimal individual goal setting that takes into account the emotional state of the user, and is expected to lead to efficient and effective goal achievement.

[1133] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1134] Step 1:

[1135] A user logs in to the system. The user enters a username and password on the login screen, and if authentication is successful, the screen moves to the next screen. The input is the username and password, and the output is a flag indicating successful authentication. Specifically, this includes the action of clicking the "Login" button in the upper right corner.

[1136] Step 2:

[1137] The user enters or uploads profile data. Profile data includes skills, work history, past goal history, personality data, etc. Input is text or a file (e.g., Excel), and output is a confirmation screen displayed on the device. Specifically, this includes the actions of filling in each input field and clicking the "Upload" button.

[1138] Step 3:

[1139] The device sends the entered profile data to the server. The input is the data entered or uploaded by the user, and the output is a message confirming the data was sent to the server. The data is sent in JSON format.

[1140] Step 4:

[1141] The server saves the received profile data in a database. The input is the profile data sent from the device, and the output is the ID of the data saved in the database. Specifically, a write process is performed on the database.

[1142] Step 5:

[1143] The server trains a machine learning model based on the stored data. The input is the profile data stored in the database, and the output is the trained machine learning model. The model is trained using Python's scikit-learn and TensorFlow.

[1144] Step 6:

[1145] The server saves the learned machine learning model. The input is the trained machine learning model, and the output is the path to the saved model. Specifically, it includes the operation of saving the model as a file.

[1146] Step 7:

[1147] While the user is using the system, the emotion recognition engine analyzes the user's facial expressions and voice in real time. The input is the user's camera footage and audio data, and the output is the recognized emotional state. Specifically, this includes turning on the camera to analyze facial expressions and collecting audio using the microphone.

[1148] Step 8:

[1149] The device sends the recognized emotional state data to the server. The input is the emotional state data generated by the emotion recognition engine, and the output is a confirmation message sent to the server. The voice analysis results are sent as text data.

[1150] Step 9:

[1151] The server adds the emotional state data to the profile data and saves it in the database. The input is the newly acquired emotional state data, and the output is the updated profile data. The writing process is performed in the database.

[1152] Step 10:

[1153] The user sends a goal proposal request to the server. The input is the user clicking the goal proposal button, and the output is the request data sent to the server.

[1154] Step 11:

[1155] The server uses the machine learning model and emotional state data to generate optimal goals for the user. The input is the trained model, saved profile data, and emotional state data, and the output is the generated goal suggestions.

[1156] Step 12:

[1157] The server sends the generated goal proposals to the terminal, which then displays them to the user. The input is the generated goal proposals, and the output is the displayed goal proposals.

[1158] Step 13:

[1159] The user selects an appropriate goal from the proposed goals. The input is a displayed list of multiple goal suggestions, and the output is the selected goal. Specifically, the action involves clicking and selecting one from the list of goals.

[1160] Step 14:

[1161] The terminal sends the selection result to the server. The input is the ID of the selected target, and the output is a confirmation message to the server.

[1162] Step 15:

[1163] The server uses generative AI technology to convert the selected goal into a specific sentence. The input is the selected goal data, and the output is the specific goal sentence. OpenAI's GPT-3 and other generative AI models are used.

[1164] Step 16:

[1165] The server sends the generated target sentence to the terminal, which displays it to the user. The input is the generated target sentence, and the output is the displayed target sentence.

[1166] Step 17:

[1167] The user reviews the generated target sentence and makes corrections if necessary. The input is the displayed target sentence, and the output is the corrected target sentence. Specifically, this involves editing the sentence by typing into a text field.

[1168] Step 18:

[1169] The user submits the finalized goal to the system. The input is the finalized goal text, and the output is a submission request to the server. This includes clicking the "Submit" button.

[1170] Step 19:

[1171] The terminal sends the final confirmed goal to the server. The input is the final confirmed goal text, and the output is a transmission confirmation message to the server.

[1172] Step 20:

[1173] The server saves the submitted goal in the database. The input is the final confirmed goal text, and the output is the ID of the saved goal data. The write process is performed in the database.

[1174] (Application example 2)

[1175] 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."

[1176] In modern self-driving vehicles, it is difficult to provide appropriate driving guidance and goal setting that takes into account the driver's emotional state. Furthermore, there is no system in place to recognize the driver's emotional state in real time and provide appropriate advice, meaning that support for continuing safe driving when the driver feels stressed or fatigued is insufficient. The present invention aims to solve these problems by providing a system that provides individually optimized driving goals and advice to drivers.

[1177] 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.

[1178] In this invention, the server includes means for receiving user profile data, means for storing the received profile data in a database, means for training a machine learning model based on the stored profile data, means for suggesting optimal goals to the user using the trained machine learning model, means for recognizing the user's emotional state while driving, means for generating driving advice in real time based on the recognized emotional state, means for displaying the generated advice to the user, means for converting the user's selected goal into a specific sentence, means for displaying the converted goal sentence to the user, and means for submitting the user's confirmed and revised goal to the system. This enables individually optimal driving instruction and goal setting that take the driver's emotional state into consideration, thereby realizing safe and efficient driving assistance.

[1179] "User profile data" refers to information about an individual, such as driver skills, driving experience, past driving history, and personality data.

[1180] "Database" refers to a collection of information for managing stored profile data and emotional data.

[1181] A "machine learning model" is an algorithm that learns from collected data and generates patterns and predictions.

[1182] "Optimal goals" refer to achievable, specific driving goals that are set based on the user's profile data and emotional state.

[1183] "Emotional state" refers to a driver's psychological and emotional state while driving, which is usually recognized through facial expressions and tone of voice.

[1184] "Means for generating driving advice in real time" refers to a method for instantly analyzing the driver's emotional state and providing driving guidance or advice based on that.

[1185] "Means of converting into concrete sentences" refers to a method of using generative AI to convert abstract goals and guidelines into clear and concrete sentences.

[1186] "Generative AI" refers to a technology that uses generative artificial intelligence technology to generate sentences in natural language based on input information.

[1187] The present invention provides a system for recognizing a user's emotional state while driving and providing appropriate driving goals and advice in real time. This system includes the following specific programs and components:

[1188] Program processing

[1189] 1. Collection and storage of profile data

[1190] A user logs into the system installed in the vehicle and enters their profile data (driving experience, skills, past driving history, personality data, etc.). This data is sent from the in-vehicle terminal to a server and stored in a database. This database contains detailed information about each individual driver.

[1191] 2. Data analysis and learning

[1192] The server trains a machine learning model based on the stored profile data. The machine learning model (e.g., TensorFlow) analyzes this data to learn the user's driving patterns and skill level. The model uses data from driving history and driving behavior to discover patterns related to goal achievement.

[1193] 3. Emotion recognition and data addition using the emotion engine

[1194] While driving, the vehicle's cameras and microphones capture the driver's facial expressions and voice and send them to an emotion recognition engine (e.g., Microsoft Azure Emotion API). The emotion recognition engine analyzes this data and identifies the driver's emotional state in real time. The identified emotion data is sent from the in-vehicle terminal to a server and stored in a database.

[1195] 4. Real-time goal suggestions and emotional influence

[1196] When a user requests a goal suggestion from the system, the server generates appropriate driving goals and advice based on machine learning models and real-time emotion data. This generation process uses a generative AI model (e.g., OpenAI GPT-4). The generated advice and goals are displayed on the in-car display.

[1197] 5. Identifying and documenting goals

[1198] The user selects suggested goals and advice and sends the results from the in-car device to the server. The server then uses generative AI to convert the abstract goals into concrete sentences. In this process, the generative AI generates documents in natural language based on the input information. The generated goal sentences are then displayed on the in-car display.

[1199] 6. Final review and feedback

[1200] The user reviews the generated goal sentences and makes any necessary corrections. The final goal is then submitted to the system and stored in the database.

[1201] Specific examples

[1202] A user logs into the system and enters their profile data and past driving history, including driving skills (e.g., highway driving, city driving), past accident history, and current driving goals. While driving, an in-vehicle camera recognizes facial expressions, and their emotional state (e.g., nervous, relaxed) is stored in a database. When the user requests "driving goals for the next hour," the system suggests specific goals, such as "obey the speed limit and avoid sudden acceleration and braking." A generative AI model is used to elaborate on these goal statements, which the user then confirms.

[1203] Prompt Sentence Examples

[1204] "Suggest a driving goal for the next hour."

[1205] "What should I pay attention to while driving?"

[1206] I need some advice on how to relax.

[1207] This system can provide individually optimized driving assistance by combining the user's profile data with their emotional state while driving.

[1208] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1209] Step 1:

[1210] The user logs into the system installed in the vehicle. The user enters profile data such as their driving experience, skills, past driving history, and personality data. This data is sent by the terminal to the server and stored in a database. This allows detailed information about each user to be stored in a central database.

[1211] Input: User profile data (driving experience, skills, past driving history, personality data)

[1212] Output: Profile data stored in a database

[1213] Step 2:

[1214] The server trains a machine learning model based on the stored profile data. The machine learning model (e.g., TensorFlow) analyzes the driver's characteristics and patterns from this data and generates a personalized driving profile for each user, which then reflects their driving habits and skill level in the model.

[1215] Input: Profile data stored in the database

[1216] Output: A trained machine learning model

[1217] Step 3:

[1218] While the user is driving the vehicle, the camera and microphone inside the vehicle capture the user's facial expressions and voice. The device sends this data to an emotion recognition engine (e.g., Microsoft Azure Emotion API) to analyze the user's emotional state in real time. The analyzed emotional data is then sent to a server and stored in a database.

[1219] Input: User's facial expression and voice data

[1220] Output: Real-time analyzed emotional state data

[1221] Step 4:

[1222] When a user requests a goal suggestion, the server generates appropriate driving goals and advice based on machine learning models and real-time emotion data. This generation process uses a generative AI model (e.g., OpenAI GPT-4). The generated advice and goals are displayed on the in-car display.

[1223] Input: User goal suggestion request, machine learning model, real-time sentiment data

[1224] Output: Generated driving goals and advice sentences

[1225] Step 5:

[1226] Once the user selects a suggested goal sentence or piece of advice, the device sends the result to the server, which then uses generative AI to convert the abstract goal into a concrete sentence, thereby clarifying any ambiguity in the goal. The generated goal sentence is then displayed on the vehicle's display.

[1227] Input: User selection results, generated AI model

[1228] Output: Specific target sentence

[1229] Step 6:

[1230] The user checks the generated goal sentences and makes corrections as necessary. The final version of the goal is submitted to the system via the terminal and stored in the database. This allows the optimal goal to be set in a way that satisfies the user.

[1231] Input: User confirmation and correction details

[1232] Output: Final target sentence stored in the database

[1233] Through these steps, individually optimized driving assistance that takes into account the user's emotional state is realized.

[1234] 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.

[1235] 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.

[1236] 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.

[1237] [Fourth embodiment]

[1238] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1239] 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.

[1240] 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).

[1241] 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.

[1242] 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.

[1243] 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).

[1244] 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.

[1245] 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.

[1246] 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.

[1247] 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.

[1248] 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.

[1249] 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.

[1250] 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."

[1251] The present invention is a system for supporting users in planning and documenting goals to be submitted every six months. This system is implemented by the following procedures and components.

[1252] Profile Data Collection

[1253] 1. A user logs into the system and enters or uploads profile data, such as their skills, work history, past goal history, personality data, etc. This data details the user's abilities and characteristics.

[1254] 2. The device (user's computer or smartphone) sends the entered profile data to the server.

[1255] Data analysis and learning

[1256] 3. The server stores the received profile data in a database.

[1257] 4. The server trains a machine learning model based on the stored data, which involves analyzing how the user's skills, past goal history, and personality data affect goal achievement.

[1258] Generate goal suggestions

[1259] 5. The user submits a goal suggestion request.

[1260] 6. The server uses machine learning models to suggest optimal goals for the user, which are automatically generated based on the user's profile data and the trained models.

[1261] 7. The server returns the generated goal proposals to the terminal, which displays them to the user.

[1262] Selecting and documenting goals

[1263] 8. The user selects the appropriate goal from the proposed goals.

[1264] 9. The terminal sends the selection results to the server.

[1265] 10. The server utilizes generative AI technology to translate the selected goals into concrete sentences, thereby converting vague or subjective expressions into concrete and clear language.

[1266] 11. The server returns the generated target sentence to the terminal, which displays it to the user.

[1267] Final confirmation and submission of goals

[1268] 12. The user checks the displayed target sentence and makes corrections if necessary.

[1269] 13. After the user finalizes the goal, they submit it to the system.

[1270] 14. The terminal sends the submitted target sentence to the server, which stores it in a database.

[1271] Specific examples

[1272] For example, a user might enter a goal into the system: "I want to improve my data analysis skills using Python." First, the device sends this information to the server, which uses a machine learning model to analyze similar past data. Next, a specific goal might be generated: "Over the next six months, successfully complete three projects related to data analysis using Python and share the results in an internal presentation." This goal statement is then sent to the user via the device, where the user can finally review and submit it.

[1273] The above is an embodiment of the present invention, and in this way the efficiency of the user's goal setting work is improved.

[1274] The processing flow will be explained below.

[1275] Step 1:

[1276] A user logs in to the system.

[1277] Step 2:

[1278] The user enters or uploads their profile data (skills, work history, past goal history, personality data, etc.).

[1279] Step 3:

[1280] The terminal transmits the entered profile data to the server.

[1281] Step 4:

[1282] The server stores the received profile data in a database.

[1283] Step 5:

[1284] The server trains the machine learning model based on the stored data, which includes analyzing the impact of the user's skills and goal history on goal achievement.

[1285] Step 6:

[1286] A user sends a goal suggestion request to a server.

[1287] Step 7:

[1288] The server uses a trained machine learning model to generate optimal goals for the user.

[1289] Step 8:

[1290] The server transmits the generated goal proposals to the terminal.

[1291] Step 9:

[1292] The terminal displays the received goal suggestions to the user.

[1293] Step 10:

[1294] The user selects from the proposed goals.

[1295] Step 11:

[1296] The terminal transmits the selected target to the server.

[1297] Step 12:

[1298] The server uses generative AI technology to convert the selected goals into concrete sentences, which converts ambiguous expressions into clear and specific sentences.

[1299] Step 13:

[1300] The server sends the generated target sentence to the terminal.

[1301] Step 14:

[1302] The terminal displays the generated target sentence to the user.

[1303] Step 15:

[1304] The user checks the generated target sentence and makes corrections if necessary.

[1305] Step 16:

[1306] The user submits the final confirmed goal to the system.

[1307] Step 17:

[1308] The terminal transmits the final confirmed target to the server.

[1309] Step 18:

[1310] The server stores the submitted goals in a database.

[1311] This series of steps allows users to efficiently set their own optimal goals and submit those goals in clear writing.

[1312] Example 1

[1313] 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."

[1314] In conventional goal setting systems, it takes a great deal of time and effort for users to individually set goals and translate them into concrete sentences. Furthermore, the system lacks the ability to utilize the user's past data to suggest optimal goals, and the suggested goals often do not match the user's actual situation. Furthermore, there is a lack of support for converting the suggested goals from vague expressions into specific, clear expressions. This results in inefficient goal setting and hinders the improvement of users' performance.

[1315] 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.

[1316] In this invention, the server includes means for receiving a user's profile data, means for storing the received profile data in a database, means for training a machine learning model based on the stored profile data, means for suggesting optimal goals to the user using the trained machine learning model, means for converting the user's selected goals into specific sentences using generative AI technology, means for displaying the converted goal sentences to the user, means for the user to submit goals confirmed and revised by the user to the system, and means for storing the submitted goals in the database. This enables users to efficiently set goals and describe them in specific and clear terms. Furthermore, optimal goal suggestions can be realized by utilizing the user's past goal history, work history, skill data, and personality data, enabling goal setting that is tailored to the user's actual situation.

[1317] "User profile data" is a general term for information that indicates the user's abilities and characteristics, such as the user's skills, work history, past goal history, and personality data.

[1318] The "means for receiving" refers to a function that utilizes a network, among other things, for incorporating data provided by a user into the system.

[1319] "Means for saving in a database" refers to a function for centrally storing received data and managing it so that it can be retrieved as needed.

[1320] "Means for training a machine learning model" means a function for training a model based on an algorithm using received and stored data to improve analytical capabilities.

[1321] The "means of suggesting optimal goals to the user" is a function that uses a trained machine learning model to extract and present goals that are considered optimal based on the user's profile data.

[1322] "Generative AI technology" is a technology that uses artificial intelligence techniques such as deep learning to generate new information and content (in this case, specific target sentences) based on input data.

[1323] "Means for converting into concrete sentences" is a function that uses generative AI technology to convert the goal selected by the user into detailed and clear language expression.

[1324] The "display means" is a function for displaying the generated target sentence so that the user can view and confirm it.

[1325] "Means for submitting to the system" is a function that allows the user to confirm and modify the goals, send them to the server, and register them.

[1326] "Storage means" is a function that stores the submitted target sentences in a database again, keeping them available for future reference and use.

[1327] The present invention is a system that supports users in planning and documenting their semi-annual goals. The system receives user profile data, trains a machine learning model based on the data, and generates specific goal documents using generative AI technology.

[1328] The embodiment of the present invention is specifically implemented as follows.

[1329] Profile Data Collection

[1330] Users access the system's login screen and log in by entering their user ID and password. Next, they enter or upload profile data such as their skills, work history, past goal history, and personality data. The hardware used is the user's own device, such as a computer or smartphone. The device encrypts the entered profile data and sends it to the server using the HTTPS protocol.

[1331] Data analysis and learning

[1332] The server stores the received profile data in a relational database (e.g., MySQL or PostgreSQL). The server preprocesses the data (e.g., imputing missing values, standardizing, encoding categorical variables) and trains a machine learning model (e.g., using Scikit-learn or TensorFlow) based on the data. This process includes analyzing how the user's skills, past goal history, and personality data affect goal achievement.

[1333] Generate goal suggestions

[1334] The user submits a goal suggestion request through the system's UI. After clicking the "Suggest a goal" button, the device sends the goal suggestion request to the server. The server uses a machine learning model to generate a list of optimal goals based on the user's profile data. The generated goal suggestions are sent back to the device in JSON format, and the device displays them in the UI.

[1335] Selecting and documenting goals

[1336] The user selects an appropriate goal from the displayed suggested goals. For example, a user may select "Improve my data analysis skills using Python" from multiple goals. The device sends the selection results to the server, which then converts the selected goal into a specific sentence using generative AI technology (e.g., OpenAI GPT model). For example, the sentence may be "Successfully complete three projects related to data analysis using Python over the next six months and share the results in an internal presentation." This sentence is then displayed to the user via the device.

[1337] Final confirmation and submission of goals

[1338] The user checks the displayed target sentence and makes corrections if necessary. After final confirmation, the user clicks the "Submit target" button, and the terminal sends the submitted target sentence to the server. The server stores the submitted target sentence in a relational database and returns a confirmation message to the terminal. The terminal displays the confirmation message to the user.

[1339] Prompt Sentence Examples

[1340] For example, here are some examples of prompts that suggest specific, achievable goals based on a user's profile data:

[1341] "Based on the user's profile data, suggest specific, achievable goals. For example, if a user has a goal of 'I want to improve my data analysis skills using Python,' suggest specific steps they should take over the next six months."

[1342] The above is an embodiment of the present invention. This system makes it possible for users to set goals more efficiently and achieve specific and clear goals.

[1343] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1344] Step 1:

[1345] The user accesses the system's login screen and enters their user ID and password. The terminal sends the entered authentication information to the server. At this time, the input data (user ID, password) becomes input from the terminal, and the output is the sent authentication information. The server receives this information and compares it with a database to determine whether the authentication was successful.

[1346] Step 2:

[1347] The server checks the authentication information against the database. The database stores the user's ID and password, and the server checks whether they match this data. If authentication is successful, the server generates an authentication success message and sends it back to the terminal. The input is the authentication information and user information from the database, and the output is an authentication result message.

[1348] Step 3:

[1349] The user enters or uploads profile data in the system. The input data includes skills, work history, past goal history, personality data, etc. The device encrypts this profile data and securely transmits it to the server using the HTTPS protocol. The input is the profile data provided by the user, and the output is the transmission of encrypted data.

[1350] Step 4:

[1351] The server stores the received profile data in a database. When storing, it checks the format of the data and cleanses it if necessary. The input is the encrypted profile data, and the output is the clean data stored in the database.

[1352] Step 5:

[1353] The server performs data preprocessing based on the stored data, specifically imputing missing values, standardizing, encoding categorical variables, etc. The input is the stored profile data, and the output is the preprocessed data.

[1354] Step 6:

[1355] The server uses the preprocessed data to train a machine learning model. For example, it uses Scikit-learn or TensorFlow to apply algorithms to analyze how the user's skills, past goal history, and personality data affect goal achievement. The input is the preprocessed data, and the output is the trained machine learning model.

[1356] Step 7:

[1357] The user submits a goal suggestion request from the system UI. By clicking the "Suggest a goal" button, the device sends the request to the server. The input is the user's request, and the output is the transmission of the request data.

[1358] Step 8:

[1359] The server uses a machine learning model to generate optimal goals based on the user's profile data. Specifically, the model compares past data with the user's current profile and suggests goals with a high success rate. The input is the user's profile data and the machine learning model, and the output is a list of suggested goals.

[1360] Step 9:

[1361] The server returns the generated goal suggestions in JSON format to the device, which displays them in the UI for the user to review. The input is a list of suggested goals, and the output is the goal suggestions displayed in the UI.

[1362] Step 10:

[1363] The user selects an appropriate goal from the suggested goals displayed. For example, the user can select the goal "Improve my data analysis skills using Python." The input is a list of suggested goals, and the output is the selected goal.

[1364] Step 11:

[1365] The terminal sends the selected target to the server. The input is the selected target and the output is the transmission to the server.

[1366] Step 12:

[1367] The server converts the selected goal into a concrete sentence using generative AI technology. For example, the OpenAI GPT model is used to generate a concrete goal sentence such as "Over the next six months, successfully complete three projects related to data analysis using Python and share the results in an internal presentation." The input is the selected goal, and the output is the generated concrete goal sentence.

[1368] Step 13:

[1369] The server returns the generated target sentence in JSON format to the terminal, which displays it in the UI for the user to confirm. The input is the specific target sentence generated, and the output is the target sentence displayed in the UI.

[1370] Step 14:

[1371] The user checks the displayed target sentence and makes corrections if necessary. After final confirmation, the user clicks the "Submit target" button. The input is the generated target sentence and corrections, and the output is the final target sentence.

[1372] Step 15:

[1373] The terminal sends the submitted target sentence to the server. The input is the final target sentence and the output is the transmission to the server.

[1374] Step 16:

[1375] The server saves the submitted target sentence in a relational database. The server confirms that the saving is complete and generates a confirmation message to send back to the terminal. The input is the final target sentence, and the output is the confirmation message.

[1376] Step 17:

[1377] The terminal displays a confirmation message to the user. The input is the confirmation message received from the server, and the output is the message displayed on the user's screen.

[1378] (Application example 1)

[1379] 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."

[1380] The process of factory robot operators setting effective goals based on their own skills and work history and converting these into specific instruction sentences takes time and effort. Furthermore, if appropriate goals are not set, production efficiency may decrease and it may be difficult to achieve the goals. To solve this problem, a system is needed that automatically suggests optimal goals based on the operator's profile data and converts those goals into specific instruction sentences.

[1381] 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.

[1382] In this invention, the server includes means for receiving user profile data, means for saving the received profile data in a database, means for training a machine learning model based on the saved profile data, means for suggesting optimal goals to the user using the trained machine learning model, means for converting the user's selected goals into specific sentences, means for displaying the converted goal sentences to the user, means for the user to submit goals confirmed and revised by the user to the system, means for suggesting production goals based on the robot operator's profile data, and means for converting the proposed production goals into specific instruction sentences. This allows factory robot operators to easily set goals that are optimal for their own attributes, and by converting the goals into specific instruction sentences, it becomes possible to improve production efficiency.

[1383] "User" refers to an individual or group that uses the system, and in the present invention particularly includes operators of factory robots.

[1384] "Profile Data" refers to information detailing a user's abilities and characteristics, such as the user's skills, work history, past goal history, and personality data.

[1385] "Database" refers to an information storage system that systematically stores received profile data and later uses it for training machine learning models, etc.

[1386] A "machine learning model" is a model that uses algorithms to learn from stored data and analyze user profile data.

[1387] "Goal suggestion" refers to the process of using machine learning models to suggest optimal goals to a user.

[1388] "Specific sentences" refer to text data in which the proposed goals are converted from vague or subjective expressions into concrete and clear language.

[1389] "Production goals" refer to specific goals aimed at improving production activities and work efficiency that factory robot operators aim to achieve.

[1390] "Instruction text" refers to text that converts proposed production targets into specific instructions and provides easy-to-understand instructions to operators or robots.

[1391] "Translation" refers to the process of turning a user's chosen goal into a more specific, actionable statement.

[1392] This invention is a system that enables factory robot operators to effectively set production goals based on their own profile data and converts those goals into specific instruction sentences. This system is configured as follows and supports goal setting through a specific process.

[1393] System program configuration

[1394] 1. Collection of profile data

[1395] Users input profile data including their skills, work history, past goal history, personality data, etc. This data is sent to the server via an internet-enabled device (e.g., smartphone, PC).

[1396] 2. Data storage

[1397] The server stores the received profile data in a database, which is constructed using a relational database management system such as SQL.

[1398] 3. Data Analysis and Machine Learning

[1399] The server uses the stored data to train a machine learning model using machine learning libraries such as Python and TensorFlow, which analyzes patterns based on the user's skills and historical data to influence goal achievement.

[1400] 4. Generating goal proposals

[1401] When a user submits a goal suggestion request, the server uses machine learning models to suggest optimal goals, which are automatically generated based on pre-processed user profile data and the trained model.

[1402] 5. Write down your goals in concrete terms

[1403] Once the user selects a suggested goal, the server uses generative AI technology (e.g., GPT-2) to convert the selected goal into a specific instruction sentence. The generative AI model generates text based on the prompt sentence through a tokenizer and model training.

[1404] 6. Final confirmation and submission of goals

[1405] The user checks the displayed instruction text and corrects it if necessary. The final confirmed goal is submitted to the server via the terminal and stored in the database.

[1406] Specific examples

[1407] For example, suppose a user inputs a goal such as "I want to improve the operating efficiency of the manufacturing line by 10%." The device sends this information to the server, which then uses a machine learning model to analyze similar past data. The server then generates a specific goal: "Over the next six months, successfully complete three projects to improve the operating efficiency of the manufacturing line by 10% and share the results at a team meeting." This goal statement is then displayed to the user via the device, who then finally confirms and submits it.

[1408] Prompt Sentence Examples

[1409] "My next goal: to complete a project that will increase production efficiency by 10%."

[1410] Based on this prompt, the generative AI model generates clear and specific instructions for the user, making it easier for factory robot operators to set goals and efficiently take specific actions to achieve them.

[1411] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1412] Step 1:

[1413] The user uses a device to enter profile data (e.g., skills, work history, past goal history, personality data) and sends the data to the server. The entered profile data is sent to the server in JSON format, and after receiving it, it is saved in a database. This allows detailed attribute information about the user to be accumulated.

[1414] Step 2:

[1415] The server then stores the received profile data in a database, using a relational database management system such as SQL to store the data in a structured format, which prepares the data for later data analysis and machine learning training.

[1416] Step 3:

[1417] The server trains a machine learning model based on the stored data. It uses Python and machine learning libraries such as TensorFlow to analyze patterns that influence goal achievement based on the user's skills and historical data. The data is preprocessed for learning, features are extracted, and the model is trained. The result is a model capable of suggesting optimal goals based on the user's attributes.

[1418] Step 4:

[1419] The user submits a goal suggestion request. This request is sent to the server via the terminal. The server, upon receiving the request, uses the learned machine learning model to suggest optimal goals for the user. The server receives the user's profile data as input, predicts goals based on the data, and generates the results as suggested goals.

[1420] Step 5:

[1421] The server sends the generated goal suggestions back to the terminal, which then displays them to the user. The user selects the most appropriate goal from the suggested goals. The selected goal is then sent back to the server via the terminal. This step involves the user's confirmation and selection process.

[1422] Step 6:

[1423] The server utilizes generative AI technology (e.g., GPT-2) to convert the selected goal into specific instruction sentences. Specifically, the selected goal is used as a prompt sentence, and the generative AI model generates specific instruction sentences based on the prompt sentence. The input to the generation process is the prompt sentence, and the output is the instruction sentence. For example, if the prompt sentence is "Complete a project that will improve production efficiency by 10%," the generative AI model will use this as a basis to generate sentences containing specific work instructions.

[1424] Step 7:

[1425] The generated instruction sentence is displayed to the user, who can then confirm and edit it. Once the edits are complete, the final confirmed target sentence is submitted to the server via the terminal. At this time, the user can make edits until they are satisfied, and the final confirmed target sentence is sent to the server.

[1426] Step 8:

[1427] The server stores the final confirmed goal sentences in a database, which can then be used for future evaluations and confirmations. This process enables factory robot operators to easily set specific, achievable goals and receive highly effective instructions for achieving them.

[1428] 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.

[1429] This invention is a system that supports users in planning and documenting their goals to be submitted every six months, and further combines it with an emotion engine that recognizes the user's emotional state to set more personalized goals. This system includes the following specific steps and components:

[1430] Collection and storage of profile data

[1431] 1. A user logs into the system and enters or uploads their profile data (skills, work history, past goal history, personality data, etc.), which includes information detailing the user's abilities and characteristics.

[1432] 2. The device sends the entered profile data to the server.

[1433] 3. The server stores the received profile data in a database.

[1434] Data analysis and learning

[1435] 4. The server trains a machine learning model based on the stored data, analyzing the impact of the user's skills and goal history on goal achievement.

[1436] Emotion recognition and data addition using the emotion engine

[1437] 5. When a user uses the system, the emotion engine recognizes the user's emotional state from their facial expressions, voice, etc.

[1438] 6. The device sends the recognized emotional state data to the server.

[1439] 7. The server adds the emotional state data to the profile data and stores it in a database.

[1440] Goal suggestions and emotional influences

[1441] 8. The user sends a goal suggestion request to the server.

[1442] 9. The server generates optimal goals for the user based on the machine learning model and emotional state data. These suggestions are generated automatically based on the user's profile data, emotional state, and the trained model.

[1443] 10. The server sends the generated goal proposal to the terminal, which displays it to the user.

[1444] Selecting and documenting goals

[1445] 11. The user selects the appropriate goal from the proposed goals.

[1446] 12. The terminal sends the selection results to the server.

[1447] 13. The server uses generative AI technology to convert the selected goal into concrete sentences. Generative AI converts vague expressions into clear and concrete sentences.

[1448] 14. The server sends the generated target sentence to the terminal, which displays it to the user.

[1449] Final confirmation and submission of goals

[1450] 15. The user checks the generated target sentences and makes corrections if necessary.

[1451] 16. The user submits the final confirmed goal to the system.

[1452] 17. The device sends the final confirmed target to the server.

[1453] 18. The server stores the submitted goals in a database.

[1454] Specific examples

[1455] A user logs into the system and enters their profile data and past goal history. The device sends this data to the server, which stores it in a database. Next, when the user uses the system to set goals, the emotion engine analyzes the user's facial expressions and voice to ascertain their emotional state. For example, if the user is feeling stressed, that emotional state is reflected in the system. Based on this data, the server suggests goals that are achievable and less stressful for the user. For example, a specific goal might be suggested: "Successfully complete three projects related to data analysis using Python over the next six months and share the results in an internal presentation." The generated goal text is then sent to the user via the device, where the user can finally review, revise, and submit it.

[1456] The present invention makes it possible to set individual optimal goals that take into consideration the user's emotional state, and is expected to enable efficient and effective goal achievement.

[1457] The processing flow will be explained below.

[1458] Step 1:

[1459] A user logs in to the system.

[1460] Step 2:

[1461] The user enters or uploads their profile data (skills, work history, past goal history, personality data, etc.).

[1462] Step 3:

[1463] The terminal transmits the entered profile data to the server.

[1464] Step 4:

[1465] The server stores the received profile data in a database.

[1466] Step 5:

[1467] The server trains the machine learning model based on the stored data, which includes analyzing the impact of the user's skills and goal history on goal achievement.

[1468] Step 6:

[1469] The emotion engine recognizes the user's emotional state from data such as facial expressions and voice.

[1470] Step 7:

[1471] The terminal transmits the emotional state data recognized by the emotion engine to the server.

[1472] Step 8:

[1473] The server adds the emotional state data to the profile data and stores it in a database.

[1474] Step 9:

[1475] A user sends a goal suggestion request to a server.

[1476] Step 10:

[1477] The server generates optimal goals for the user based on the machine learning model and emotional state data. These goal suggestions are automatically generated based on the user's profile data, emotional state, and the trained model.

[1478] Step 11:

[1479] The server transmits the generated goal proposals to the terminal.

[1480] Step 12:

[1481] The terminal displays the received goal suggestions to the user.

[1482] Step 13:

[1483] The user selects the appropriate goal from the proposed goals.

[1484] Step 14:

[1485] The terminal transmits the selected target to the server.

[1486] Step 15:

[1487] The server uses generative AI technology to convert the selected goals into concrete sentences, which converts ambiguous expressions into clear and specific sentences.

[1488] Step 16:

[1489] The server sends the generated target sentence to the terminal.

[1490] Step 17:

[1491] The terminal displays the generated target sentence to the user.

[1492] Step 18:

[1493] The user checks the generated target sentences and makes corrections as necessary.

[1494] Step 19:

[1495] The user submits the final confirmed goal to the system.

[1496] Step 20:

[1497] The terminal transmits the final confirmed target to the server.

[1498] Step 21:

[1499] The server stores the submitted goals in a database.

[1500] This series of steps allows users to efficiently set optimal goals and submit them in clear written form. Taking into account the user's emotional state, we can set goals that are appropriate for each individual, leading to more effective goal achievement.

[1501] Example 2

[1502] 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."

[1503] Conventional goal setting systems offer a means for suggesting goals based on a user's profile data and past work history, but they are unable to take into account the emotional state of each individual user, making it difficult to set appropriate and achievable goals. This can lead to users being unable to achieve their set goals, resulting in a loss of motivation and stress. The present invention aims to solve this problem.

[1504] 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.

[1505] In this invention, the server includes means for receiving user profile data, means for storing the received profile data in a database, means for training a machine learning model based on the stored profile data, means for recognizing the user's emotional state, means for adding the recognized emotional state data to the profile data and storing it, means for proposing optimal goals to the user using the trained machine learning model and the emotional state data, means for converting the user's selected goal into a specific sentence, means for displaying the converted goal sentence to the user, and means for submitting the user's confirmed and revised goal to the system, thereby enabling individually optimal goal setting that takes the user's emotional state into consideration.

[1506] "User" refers to an individual or organization that uses the System.

[1507] "Profile Data" refers to detailed information about a user, such as the user's skills, work history, past goal history, and personality data.

[1508] "Database" refers to a system or technology that efficiently stores and manages data received by a system and makes it accessible as needed.

[1509] A "machine learning model" is a model that automatically learns statistical patterns and rules based on data and uses them to make predictions and classifications.

[1510] "Emotional state" refers to the current emotional state of the user as analyzed from the user's facial expressions, voice, etc. Examples include joy, sadness, stress, etc.

[1511] "Generative AI" refers to artificial intelligence technology that performs natural language processing such as sentence generation based on provided input data.

[1512] "Goal proposal" means that the system presents specific goals and work plans to the user.

[1513] "Goal sentence" refers to a text that expresses the proposed goal in a specific and detailed manner.

[1514] "Submission means" refers to a means by which a user finally transmits the confirmed and corrected goals to the system.

[1515] "Terminal" refers to a device that allows a user to access the system, input data, and display results. Examples include personal computers and smartphones.

[1516] "Server" refers to the central processing unit of a system, which processes, stores, analyzes, etc. data.

[1517] This invention is a system that supports the user in planning and documenting semi-annual goals and recognizes the user's emotional state. Specific embodiments of this system are described below. Each step clearly indicates the type of hardware or software used to process or calculate data.

[1518] System Configuration

[1519] The system consists of a user terminal, a server, a database, an emotion recognition engine, and a generative AI model.

[1520] User devices include PCs, tablets, smartphones, etc., through which users access the system to enter data and check results. The devices communicate with the server via the Internet.

[1521] The server is a central processing unit that processes data, stores data, trains machine learning models, recognizes emotional states, generates text using generative AI models, etc. Specific examples commonly used include cloud services such as AWS (Amazon Web Services) and Google Cloud.

[1522] The database manages the saved profile data, emotional state data, machine learning models, and generated target sentences. Specifically, a relational database such as PostgreSQL is used.

[1523] The emotion recognition engine provides technology to recognize the user's emotional state in real time by analyzing their facial expressions and voice. It uses a facial recognition library such as OpenCV and a Python voice analysis library.

[1524] A generative AI model is an artificial intelligence technology that generates specific target sentences based on a user's profile data and emotional state. Examples of such models include natural language processing models such as OpenAI's GPT-3.

[1525] Program processing explanation

[1526] The system starts when a user logs in and enters and uploads their profile data. The user's device sends this data to the server, which stores it in a database.

[1527] The server then trains a machine learning model based on the stored data, using Python libraries such as scikit-learn and TensorFlow. The trained model is then saved on the server for further processing.

[1528] When a user uses the system, the emotion recognition engine recognizes the user's emotional state from their facial expressions and voice. The user device sends the recognized emotional state data to the server, which then stores it in a database.

[1529] The server generates optimal goals for the user based on the machine learning model and the stored emotional state data. This process takes into account the user's skills, past goal history, and current emotional state. The generated goal suggestions are sent to the user's device and displayed to the user.

[1530] The user selects the appropriate goal from the proposed set of goals, and the results are sent to the server. The server then uses generative AI technology to convert the selected goal into concrete sentences. OpenAI's GPT-3 is commonly used in this process.

[1531] The generated target sentences are sent back to the user's terminal for confirmation and correction. Once the final target is determined, it is sent from the user's terminal to the server and stored in the database.

[1532] Specific examples

[1533] A user logs into the system and uploads profile data, including past work history and skills. The device sends this data to the server, which stores it in a database. Next, when the user sets goals, an emotion recognition engine analyzes the user's facial expressions and voice to recognize their emotional state. For example, if the user is feeling stressed, the system will reflect that emotional state. Based on this data, the server suggests achievable goals that are less stressful for the user.

[1534] For example, a specific goal is proposed: "Over the next six months, successfully complete three projects related to data analysis using Python and share the results in an internal presentation." This generated goal statement is sent to the user via the terminal, and the user finally reviews, corrects, and submits it.

[1535] Prompt Sentence Examples

[1536] "Generate goals based on this user's profile data and emotional state."

[1537] "Please translate the user's selected goal into a concrete sentence."

[1538] This embodiment enables optimal individual goal setting that takes into account the emotional state of the user, and is expected to lead to efficient and effective goal achievement.

[1539] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1540] Step 1:

[1541] A user logs in to the system. The user enters a username and password on the login screen, and if authentication is successful, the screen moves to the next screen. The input is the username and password, and the output is a flag indicating successful authentication. Specifically, this includes the action of clicking the "Login" button in the upper right corner.

[1542] Step 2:

[1543] The user enters or uploads profile data. Profile data includes skills, work history, past goal history, personality data, etc. Input is text or a file (e.g., Excel), and output is a confirmation screen displayed on the device. Specifically, this includes the actions of filling in each input field and clicking the "Upload" button.

[1544] Step 3:

[1545] The device sends the entered profile data to the server. The input is the data entered or uploaded by the user, and the output is a message confirming the data was sent to the server. The data is sent in JSON format.

[1546] Step 4:

[1547] The server saves the received profile data in a database. The input is the profile data sent from the device, and the output is the ID of the data saved in the database. Specifically, a write process is performed on the database.

[1548] Step 5:

[1549] The server trains a machine learning model based on the stored data. The input is the profile data stored in the database, and the output is the trained machine learning model. The model is trained using Python's scikit-learn and TensorFlow.

[1550] Step 6:

[1551] The server saves the learned machine learning model. The input is the trained machine learning model, and the output is the path to the saved model. Specifically, it includes the operation of saving the model as a file.

[1552] Step 7:

[1553] While the user is using the system, the emotion recognition engine analyzes the user's facial expressions and voice in real time. The input is the user's camera footage and audio data, and the output is the recognized emotional state. Specifically, this includes turning on the camera to analyze facial expressions and collecting audio using the microphone.

[1554] Step 8:

[1555] The device sends the recognized emotional state data to the server. The input is the emotional state data generated by the emotion recognition engine, and the output is a confirmation message sent to the server. The voice analysis results are sent as text data.

[1556] Step 9:

[1557] The server adds the emotional state data to the profile data and saves it in the database. The input is the newly acquired emotional state data, and the output is the updated profile data. The writing process is performed in the database.

[1558] Step 10:

[1559] The user sends a goal proposal request to the server. The input is the user clicking the goal proposal button, and the output is the request data sent to the server.

[1560] Step 11:

[1561] The server uses the machine learning model and emotional state data to generate optimal goals for the user. The input is the trained model, saved profile data, and emotional state data, and the output is the generated goal suggestions.

[1562] Step 12:

[1563] The server sends the generated goal proposals to the terminal, which then displays them to the user. The input is the generated goal proposals, and the output is the displayed goal proposals.

[1564] Step 13:

[1565] The user selects an appropriate goal from the proposed goals. The input is a displayed list of multiple goal suggestions, and the output is the selected goal. Specifically, the action involves clicking and selecting one from the list of goals.

[1566] Step 14:

[1567] The terminal sends the selection result to the server. The input is the ID of the selected target, and the output is a confirmation message to the server.

[1568] Step 15:

[1569] The server uses generative AI technology to convert the selected goal into a specific sentence. The input is the selected goal data, and the output is the specific goal sentence. OpenAI's GPT-3 and other generative AI models are used.

[1570] Step 16:

[1571] The server sends the generated target sentence to the terminal, which displays it to the user. The input is the generated target sentence, and the output is the displayed target sentence.

[1572] Step 17:

[1573] The user reviews the generated target sentence and makes corrections if necessary. The input is the displayed target sentence, and the output is the corrected target sentence. Specifically, this involves editing the sentence by typing into a text field.

[1574] Step 18:

[1575] The user submits the finalized goal to the system. The input is the finalized goal text, and the output is a submission request to the server. This includes clicking the "Submit" button.

[1576] Step 19:

[1577] The terminal sends the final confirmed goal to the server. The input is the final confirmed goal text, and the output is a transmission confirmation message to the server.

[1578] Step 20:

[1579] The server saves the submitted goal in the database. The input is the final confirmed goal text, and the output is the ID of the saved goal data. The write process is performed in the database.

[1580] (Application example 2)

[1581] 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."

[1582] In modern self-driving vehicles, it is difficult to provide appropriate driving guidance and goal setting that takes into account the driver's emotional state. Furthermore, there is no system in place to recognize the driver's emotional state in real time and provide appropriate advice, meaning that support for continuing safe driving when the driver feels stressed or fatigued is insufficient. The present invention aims to solve these problems by providing a system that provides individually optimized driving goals and advice to drivers.

[1583] 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.

[1584] In this invention, the server includes means for receiving user profile data, means for storing the received profile data in a database, means for training a machine learning model based on the stored profile data, means for suggesting optimal goals to the user using the trained machine learning model, means for recognizing the user's emotional state while driving, means for generating driving advice in real time based on the recognized emotional state, means for displaying the generated advice to the user, means for converting the user's selected goal into a specific sentence, means for displaying the converted goal sentence to the user, and means for submitting the user's confirmed and revised goal to the system. This enables individually optimal driving instruction and goal setting that take the driver's emotional state into consideration, thereby realizing safe and efficient driving assistance.

[1585] "User profile data" refers to information about an individual, such as driver skills, driving experience, past driving history, and personality data.

[1586] "Database" refers to a collection of information for managing stored profile data and emotional data.

[1587] A "machine learning model" is an algorithm that learns from collected data and generates patterns and predictions.

[1588] "Optimal goals" refer to achievable, specific driving goals that are set based on the user's profile data and emotional state.

[1589] "Emotional state" refers to a driver's psychological and emotional state while driving, which is usually recognized through facial expressions and tone of voice.

[1590] "Means for generating driving advice in real time" refers to a method for instantly analyzing the driver's emotional state and providing driving guidance or advice based on that.

[1591] "Means of converting into concrete sentences" refers to a method of using generative AI to convert abstract goals and guidelines into clear and concrete sentences.

[1592] "Generative AI" refers to a technology that uses generative artificial intelligence technology to generate sentences in natural language based on input information.

[1593] The present invention provides a system for recognizing a user's emotional state while driving and providing appropriate driving goals and advice in real time. This system includes the following specific programs and components:

[1594] Program processing

[1595] 1. Collection and storage of profile data

[1596] A user logs into the system installed in the vehicle and enters their profile data (driving experience, skills, past driving history, personality data, etc.). This data is sent from the in-vehicle terminal to a server and stored in a database. This database contains detailed information about each individual driver.

[1597] 2. Data analysis and learning

[1598] The server trains a machine learning model based on the stored profile data. The machine learning model (e.g., TensorFlow) analyzes this data to learn the user's driving patterns and skill level. The model uses data from driving history and driving behavior to discover patterns related to goal achievement.

[1599] 3. Emotion recognition and data addition using the emotion engine

[1600] While driving, the vehicle's cameras and microphones capture the driver's facial expressions and voice and send them to an emotion recognition engine (e.g., Microsoft Azure Emotion API). The emotion recognition engine analyzes this data and identifies the driver's emotional state in real time. The identified emotion data is sent from the in-vehicle terminal to a server and stored in a database.

[1601] 4. Real-time goal suggestions and emotional influence

[1602] When a user requests a goal suggestion from the system, the server generates appropriate driving goals and advice based on machine learning models and real-time emotion data. This generation process uses a generative AI model (e.g., OpenAI GPT-4). The generated advice and goals are displayed on the in-car display.

[1603] 5. Identifying and documenting goals

[1604] The user selects suggested goals and advice and sends the results from the in-car device to the server. The server then uses generative AI to convert the abstract goals into concrete sentences. In this process, the generative AI generates documents in natural language based on the input information. The generated goal sentences are then displayed on the in-car display.

[1605] 6. Final review and feedback

[1606] The user reviews the generated goal sentences and makes any necessary corrections. The final goal is then submitted to the system and stored in the database.

[1607] Specific examples

[1608] A user logs into the system and enters their profile data and past driving history, including driving skills (e.g., highway driving, city driving), past accident history, and current driving goals. While driving, an in-vehicle camera recognizes facial expressions, and their emotional state (e.g., nervous, relaxed) is stored in a database. When the user requests "driving goals for the next hour," the system suggests specific goals, such as "obey the speed limit and avoid sudden acceleration and braking." A generative AI model is used to elaborate on these goal statements, which the user then confirms.

[1609] Prompt Sentence Examples

[1610] "Suggest a driving goal for the next hour."

[1611] "What should I pay attention to while driving?"

[1612] I need some advice on how to relax.

[1613] This system can provide individually optimized driving assistance by combining the user's profile data with their emotional state while driving.

[1614] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1615] Step 1:

[1616] The user logs into the system installed in the vehicle. The user enters profile data such as their driving experience, skills, past driving history, and personality data. This data is sent by the terminal to the server and stored in a database. This allows detailed information about each user to be stored in a central database.

[1617] Input: User profile data (driving experience, skills, past driving history, personality data)

[1618] Output: Profile data stored in a database

[1619] Step 2:

[1620] The server trains a machine learning model based on the stored profile data. The machine learning model (e.g., TensorFlow) analyzes the driver's characteristics and patterns from this data and generates a personalized driving profile for each user, which then reflects their driving habits and skill level in the model.

[1621] Input: Profile data stored in the database

[1622] Output: A trained machine learning model

[1623] Step 3:

[1624] While the user is driving the vehicle, the camera and microphone inside the vehicle capture the user's facial expressions and voice. The device sends this data to an emotion recognition engine (e.g., Microsoft Azure Emotion API) to analyze the user's emotional state in real time. The analyzed emotional data is then sent to a server and stored in a database.

[1625] Input: User's facial expression and voice data

[1626] Output: Real-time analyzed emotional state data

[1627] Step 4:

[1628] When a user requests a goal suggestion, the server generates appropriate driving goals and advice based on machine learning models and real-time emotion data. This generation process uses a generative AI model (e.g., OpenAI GPT-4). The generated advice and goals are displayed on the in-car display.

[1629] Input: User goal suggestion request, machine learning model, real-time sentiment data

[1630] Output: Generated driving goals and advice sentences

[1631] Step 5:

[1632] Once the user selects a suggested goal sentence or piece of advice, the device sends the result to the server, which then uses generative AI to convert the abstract goal into a concrete sentence, thereby clarifying any ambiguity in the goal. The generated goal sentence is then displayed on the vehicle's display.

[1633] Input: User selection results, generated AI model

[1634] Output: Specific target sentence

[1635] Step 6:

[1636] The user checks the generated goal sentences and makes corrections as necessary. The final version of the goal is submitted to the system via the terminal and stored in the database. This allows the optimal goal to be set in a way that satisfies the user.

[1637] Input: User confirmation and correction details

[1638] Output: Final target sentence stored in the database

[1639] Through these steps, individually optimized driving assistance that takes into account the user's emotional state is realized.

[1640] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1641] 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.

[1642] 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 robot 414.

[1643] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1644] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1645] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1646] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1647] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1648] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1649] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1650] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1651] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1652] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1653] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1654] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1655] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1656] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1657] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1658] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1659] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1660] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1661] The following is further disclosed regarding the above embodiment.

[1662] (Claim 1)

[1663] means for receiving user profile data;

[1664] means for storing the received profile data in a database;

[1665] a means for training a machine learning model based on the stored profile data; and

[1666] A means for suggesting optimal goals to a user using the learned machine learning model; and

[1667] a means for converting the user's selected goal into a concrete statement;

[1668] means for displaying the converted target sentence to the user;

[1669] A means for users to submit confirmed and revised goals to the system;

[1670] A system including:

[1671] (Claim 2)

[1672] 10. The system of claim 1, further comprising means for training the machine learning model based on a user's past goal history.

[1673] (Claim 3)

[1674] 10. The system of claim 1, further comprising means for converting the proposed goal into a concrete sentence using generative AI.

[1675] "Example 1"

[1676] (Claim 1)

[1677] means for receiving user profile data;

[1678] means for storing the received profile data in a database;

[1679] a means for training a machine learning model based on the stored profile data; and

[1680] A means for suggesting optimal goals to a user using the learned machine learning model; and

[1681] A means for converting the user's selected goal into a concrete sentence using generative AI technology;

[1682] means for displaying the converted target sentence to the user;

[1683] A means for users to submit confirmed and revised goals to the system;

[1684] means for storing the submitted goals in a database;

[1685] A system including:

[1686] (Claim 2)

[1687] 10. The system of claim 1, further comprising means for training the machine learning model based on the user's past goal history, work history, skill data, and personality data.

[1688] (Claim 3)

[1689] 10. The system of claim 1, including means for using generative AI techniques to convert the proposed goals into specific and clear statements.

[1690] "Application Example 1"

[1691] (Claim 1)

[1692] means for receiving user profile data;

[1693] means for storing the received profile data in a database;

[1694] a means for training a machine learning model based on the stored profile data; and

[1695] A means for suggesting optimal goals to a user using the learned machine learning model; and

[1696] a means for converting the user's selected goal into a concrete statement;

[1697] means for displaying the converted target sentence to the user;

[1698] A means for users to submit confirmed and revised goals to the system;

[1699] a means for suggesting production targets based on the profile data of the robot operator;

[1700] a means of translating proposed production goals into specific instruction statements;

[1701] A system including:

[1702] (Claim 2)

[1703] 10. The system of claim 1, further comprising means for training the machine learning model based on a user's past goal history.

[1704] (Claim 3)

[1705] 10. The system of claim 1, further comprising means for converting the proposed goal into a specific instruction sentence using generative AI.

[1706] "Example 2: Combining Emotion Engines"

[1707] (Claim 1)

[1708] means for receiving user profile data;

[1709] means for storing the received profile data in a database;

[1710] a means for training a machine learning model based on the stored profile data; and

[1711] means for recognizing the emotional state of a user;

[1712] means for adding and storing the recognized emotional state data to the profile data;

[1713] a means for suggesting optimal goals to a user using the trained machine learning model and emotional state data; and

[1714] a means for converting the user's selected goal into a concrete statement;

[1715] means for displaying the converted target sentence to the user;

[1716] A means for users to submit confirmed and revised goals to the system;

[1717] A system including:

[1718] (Claim 2)

[1719] 10. The system of claim 1, further comprising means for training the machine learning model based on a user's past goal history.

[1720] (Claim 3)

[1721] 10. The system of claim 1, further comprising means for converting the proposed goal into a concrete sentence using generative AI.

[1722] "Application example 2 when combining emotion engines"

[1723] (Claim 1)

[1724] means for receiving user profile data;

[1725] means for storing the received profile data in a database;

[1726] a means for training a machine learning model based on the stored profile data; and

[1727] A means for suggesting optimal goals to a user using the learned machine learning model; and

[1728] means for recognizing a user's emotional state while driving;

[1729] means for generating driving advice in real time based on the recognized emotional state;

[1730] means for displaying the generated advice to the user;

[1731] a means for converting the user's selected goal into a concrete statement;

[1732] means for displaying the converted target sentence to the user;

[1733] A means for users to submit confirmed and revised goals to the system;

[1734] A system including:

[1735] (Claim 2)

[1736] 10. The system of claim 1, further comprising means for training the machine learning model based on a user's past goal history.

[1737] (Claim 3)

[1738] 10. The system of claim 1, further comprising means for analyzing the emotional state of a user while driving in real time using emotion recognition technology. [Explanation of symbols]

[1739] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving user profile data; means for storing the received profile data in a database; a means for training a machine learning model based on the stored profile data; and A means for suggesting optimal goals to a user using the learned machine learning model; and a means for converting the user's selected goal into a concrete statement; means for displaying the converted target sentence to the user; A means for users to submit confirmed and revised goals to the system; A system including:

2. The system of claim 1 , further comprising means for training a machine learning model based on a user's past goal history.

3. 10. The system of claim 1, further comprising means for converting the proposed goal into a concrete sentence using generative AI.

Images