System

Abstract

A system is provided.SOLUTION: The system includes a means for receiving feedback information inputted from a superior, a means for analyzing the received feedback information, a means for generating feedback contents on the basis of an analysis result, and a means for transmitting the generated feedback contents to a subordinate at appropriate timing.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's workplace, managers often hesitate to provide feedback to their subordinates due to the risk of power harassment. This makes it difficult for subordinates to maintain their motivation to grow while accurately identifying areas for improvement. Furthermore, it is often difficult for managers to determine the appropriate timing and content of feedback, preventing effective guidance. The purpose of this invention is to solve these problems and provide a system that allows managers to provide appropriate feedback to their subordinates without hesitation. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means. A system is provided that includes means for receiving feedback information input by a superior, means for analyzing the received feedback information, means for generating feedback content based on the analysis results, and means for transmitting the generated feedback content to a subordinate at an appropriate timing. The system also includes means for storing the generated feedback content in a queue together with an appropriate transmission timing, and means for transmitting the feedback content stored in the queue to a subordinate terminal at a determined timing. The system is further provided with means for analyzing the feedback information input by the superior using a natural language processing engine, and means for generating optimal feedback for the subordinate based on the analysis results. This makes it possible to effectively promote the growth of subordinates while reducing the risk of the superior having to directly point out problems to the subordinate.

[0006] The "boss terminal" is a device or application that allows a boss to input feedback information for a subordinate.

[0007] "Feedback information" refers to comments and opinions entered by a supervisor about a subordinate's behavior or performance.

[0008] The "receiving means" is a part that has a function for the server to receive feedback information sent from the superior terminal.

[0009] The "analysis means" is a part that has the function of understanding the received feedback information using natural language processing or other techniques and extracting important information.

[0010] "AI model" refers to artificial intelligence technology that analyzes feedback content and generates optimal feedback for subordinates.

[0011] The "means for generating" is a part that has the function of creating specific feedback content based on the analysis results.

[0012] The "right time" refers to the most effective time for your subordinate to receive feedback.

[0013] The "transmitting means" is a part having a function for transmitting the generated feedback content to the subordinate terminal.

[0014] The "means for storing in a queue" is a part having a function for temporarily storing the generated feedback content and its transmission timing.

[0015] "Determined timing" refers to the time for sending feedback that is determined to be most appropriate based on analysis and other factors.

[0016] A "subordinate terminal" is a device or application that a subordinate uses to receive feedback. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system that uses AI technology to provide effective and safe feedback from superiors to subordinates. This system consists of three main components: the superior's terminal, the server, and the subordinate's terminal. Below, we will explain the specific operating procedures for each component and the operation of the entire system.

[0039] Operations on the boss's terminal

[0040] A supervisor enters feedback information about a subordinate using a terminal with a dedicated application installed. The supervisor accesses the feedback input screen, selects the subordinate's name, and enters the feedback content in the text box. When the supervisor clicks the "Send" button, the feedback information is sent to the server. As a concrete example, let's say the supervisor enters, "Your comments in the recent meeting were accurate, but I would like you to say more."

[0041] Processing on the server

[0042] The server receives feedback information from the manager's device. The received information is stored in a database and then passed to a natural language processing engine. The engine analyzes the feedback content and extracts important key phrases such as "quiet but accurate." The AI ​​model then generates specific feedback content based on the analysis results. An example of feedback in this case would be "Try to share more ideas with confidence."

[0043] The generated feedback content is stored in a queue along with the appropriate timing. For example, if it is determined that the subordinate would best receive the feedback when they arrive at work in the morning, the server will schedule the feedback to be sent to the subordinate's device at that time.

[0044] Operations on subordinate devices

[0045] When a subordinate's device receives feedback from the server, the content is immediately saved in its internal memory. At the appropriate time, the feedback content is displayed to the subordinate through the user interface. For example, when a subordinate starts work in the morning, they will see the feedback displayed as "Try to share more ideas with confidence."

[0046] Overall system operation

[0047] This system reduces the risk of a supervisor giving direct feedback to a subordinate and provides a mechanism for subordinates to receive feedback that will lead to their growth at an appropriate and effective time. Feedback information entered from the supervisor's device is sent to a server, where it is analyzed and feedback generated by an AI model is sent to the subordinate's device at the optimal time. As a result, communication between the supervisor and subordinate becomes smoother, promoting the subordinate's growth.

[0048] This is the overall system configuration for implementing the present invention.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] The supervisor launches the dedicated app or web app. The supervisor selects the "Enter Feedback" option from the main menu, and the feedback entry screen appears.

[0052] Step 2:

[0053] The manager selects the subordinate's name from the drop-down menu, then enters the feedback in the text box (e.g., "Your comments in recent meetings were accurate, but I'd like to see more of you."), and clicks the "Send" button.

[0054] Step 3:

[0055] The boss's device catches the click event of the send button, converts the feedback content and the subordinate's identification information into JSON format, and sends an HTTP POST request to the server's API endpoint.

[0056] Step 4:

[0057] The server receives an HTTP POST request at the specified API endpoint, parses the received JSON data, and extracts the feedback content and subordinate's identification information.

[0058] Step 5:

[0059] The server passes the extracted feedback to a natural language processing (NLP) engine, which analyzes the meaning of the feedback and extracts key information (e.g., "Small but accurate").

[0060] Step 6:

[0061] The server inputs the analysis results into the AI ​​model, which then generates optimal feedback for the subordinate based on the analysis results (e.g., "Try to share more ideas with confidence").

[0062] Step 7:

[0063] The server compares the generated feedback content with the subordinate's timetable database to determine the optimal transmission timing, and stores the determined feedback content and transmission timing in a queue.

[0064] Step 8:

[0065] Based on the determined timing, the server retrieves the feedback content from the queue and sends an HTTP POST request to the subordinate terminal.

[0066] Step 9:

[0067] The subordinate device receives an HTTP POST request from the server, analyzes the received JSON data, and extracts the feedback content.

[0068] Step 10:

[0069] The subordinate's device uses an appropriate user interface to display the feedback content on the screen. The subordinate checks the displayed feedback and considers possible actions.

[0070] Example 1

[0071] 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."

[0072] Typically, when a manager provides direct feedback to a subordinate, the timing and content are often inappropriate, which results in the subordinate's growth being unsatisfactory. There is also a risk that the manager's feedback may be inappropriate or the subordinate may feel uncomfortable due to poor choice of words. There is a need for a system that can solve these issues and provide feedback to subordinates more effectively and safely.

[0073] 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.

[0074] In this invention, the server includes means for receiving feedback information input from a superior, means for saving the received feedback information in a storage device, means for analyzing the saved feedback information using natural language processing technology, means for generating feedback content based on the analysis result using a generative AI model, and means for sending the generated feedback content to a subordinate at an appropriate time. This makes it possible to analyze feedback from a superior in an appropriate manner, generate optimal feedback content, and provide it to a subordinate at an appropriate time.

[0075] A "supervisor" is an individual in an organization who is in a position to give direct instructions and manage subordinates.

[0076] A "subordinate" is an individual in an organization who is in a position to receive instructions and management from a superior.

[0077] "Feedback information" refers to the content of evaluations, comments, advice, etc. that a superior provides to a subordinate.

[0078] The "receiving means" is a function for taking the feedback information sent from the superior terminal into the server.

[0079] The "storing means" is a function for storing received feedback information in a database or storage device.

[0080] "Natural language processing technology" is a technology for analyzing text data in natural language and converting it into a form that humans can understand.

[0081] "Means of analysis" refers to the function of understanding and analyzing feedback information using natural language processing technology.

[0082] A "generative AI model" is an artificial intelligence model that has been trained in advance using large amounts of data and generates feedback content based on input information.

[0083] "Means for generation" refers to a function for creating feedback content using a generative AI model based on the analysis results.

[0084] The "transmitting means" is a function for sending the generated feedback content to the subordinate terminal.

[0085] The "means for storing in a queue" is a function for temporarily storing the generated feedback content so that it can be sent at an appropriate time.

[0086] "Transmission timing" refers to the optimal time and conditions for transmitting the feedback content to the subordinate terminal.

[0087] "Subordinate terminal" refers to a terminal device used by a subordinate to receive and display feedback.

[0088] MODE FOR CARRYING OUT THE INVENTION

[0089] This invention is a system that uses AI technology to provide feedback from superiors to subordinates effectively and safely. This system consists of three main components: a superior terminal, a server, and a subordinate terminal. The specific operating procedures and the operation of the entire system are explained in detail below.

[0090] Operations on the boss's terminal

[0091] The supervisor uses a device with a dedicated application installed. This device can be a PC or smartphone. To enter feedback information, the supervisor accesses the feedback input screen of the dedicated application, selects the subordinate's name, and enters the feedback content in the text box. For example, the supervisor might enter, "Your comments in the recent meeting were accurate, but I would like you to say more." Once this input is complete, the supervisor clicks the "Send" button to transfer the feedback information to the server.

[0092] Processing on the server

[0093] The server receives the feedback information sent from the supervisor's device. The received feedback information is first stored in a database (e.g., MySQL). The feedback content is then analyzed using a natural language processing engine (e.g., spaCy, NLTK). Through the analysis, important key phrases such as "You speak little, but accurately" are extracted. The server then passes the extracted key phrases to a generative AI model (e.g., GPT-3, BERT) to generate specific feedback content. For example, feedback such as "Try to share more ideas with confidence" is generated.

[0094] The generated feedback is scheduled with the appropriate timing for the subordinate to receive it. The server determines the optimal timing for sending the feedback (e.g., when the subordinate arrives at work in the morning) based on the subordinate's behavioral patterns and preferences, and stores the feedback in a queue.

[0095] Operations on subordinate devices

[0096] The subordinate's device receives the feedback sent from the server. The received feedback is stored in the internal memory and displayed to the subordinate through the user interface at the appropriate time. For example, when the subordinate starts work in the morning, the feedback "Try to share more ideas with confidence" is displayed.

[0097] Examples and prompts

[0098] For example, let's say your boss writes, "Your contributions to the recent project have been great, but you could do better if you paid more attention to the details." This feedback information is parsed and generated as follows:

[0099] Analysis results of the natural language processing engine:

[0100] "Great contributions but attention to detail"

[0101] Feedback generated by the generative AI model:

[0102] "The results are excellent, but with more attention to detail the results would be even better."

[0103] Example prompt for a generative AI model:

[0104] Prompt: Your contribution to your recent project has been great, but it could be even better with a little more attention to detail.

[0105] Output: Good results, but more attention to detail would produce even better results.

[0106] This system reduces the risk involved when a manager gives direct feedback to a subordinate and enables effective feedback to be given at the right time, resulting in smoother communication between managers and subordinates and promoting the growth of subordinates.

[0107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0108] Step 1: Enter and send feedback on the supervisor's device

[0109] Input: Launch the dedicated application installed on the supervisor's device and access the feedback input screen.

[0110] How it works: A manager selects a subordinate's name and enters specific feedback in the text box.

[0111] Output: When the manager clicks the "Send" button, the feedback information is converted into a data packet and sent to the server.

[0112] Step 2: Receiving and storing feedback information on the server

[0113] Input: Receives data packets sent from the boss's terminal.

[0114] Operation: The server parses the received data packets and extracts the feedback information.

[0115] Output: Save the feedback information to a database (e.g. MySQL).

[0116] Step 3: Analysis using natural language processing on the server

[0117] Input: Feedback information stored in the database.

[0118] How it works: The server passes the feedback information to a natural language processing engine (e.g. spaCy, NLTK) for content analysis.

[0119] A natural language processing engine extracts important key phrases from the feedback.

[0120] Output: As a result of the analysis, we obtain key phrases such as "few comments but accurate."

[0121] Step 4: Feedback generation by the AI ​​model on the server

[0122] Input: Analysis results (important key phrases) obtained from the natural language processing engine.

[0123] How it works: The server inputs the analysis results into a generative AI model (e.g., GPT-3, BERT).

[0124] A generative AI model generates specific feedback content based on key phrases.

[0125] Output: For example, you get feedback such as "Try to share more ideas with confidence."

[0126] Step 5: Registering the schedule on the server

[0127] Input: The specific feedback generated.

[0128] How it works: The server determines the best time to send feedback (e.g., when a subordinate arrives at work).

[0129] Queue feedback and when to send it.

[0130] Output: Feedback stored along with the timing of sending.

[0131] Step 6: Receive and display feedback on subordinate devices

[0132] Input: Feedback information sent by the server.

[0133] Operation: The subordinate device receives the feedback information and stores it in its internal memory.

[0134] Providing feedback through the user interface at the appropriate time.

[0135] Output: For example, a message is displayed to the subordinate saying, "Try to share more ideas with confidence."

[0136] This enables a series of steps to be taken, in which feedback information entered from the superior's device is analyzed and generated on the server, and then sent to the subordinate's device at the optimal timing.

[0137] (Application example 1)

[0138] 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."

[0139] In modern factories, real-time feedback is necessary to efficiently improve the behavior and performance of robots. However, when supervisors provide feedback directly to factory robots, it is difficult to instruct effective actions at the appropriate time. Furthermore, advanced technology is required to accurately analyze the robot's operating status and provide appropriate improvement instructions. A means to effectively solve these issues is needed.

[0140] 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.

[0141] In this invention, the server includes means for receiving feedback information input from a superior, means for analyzing the received feedback information, means for generating feedback content based on the analysis results, and means for transmitting the generated feedback content to the device at an appropriate time, thereby enabling the superior to provide timely and effective feedback to the factory robot and improving the robot's operation and performance.

[0142] "Superior" refers to the person responsible for providing feedback to the system.

[0143] "Feedback information" refers to the content of evaluations and advice for the subject, such as text or audio entered by superiors.

[0144] "Means for receiving" refers to the function that allows the system to incorporate feedback information provided by superiors.

[0145] "Means for analysis" refers to the function of analyzing received feedback information using a natural language processing engine or the like and extracting meaning.

[0146] The "means for generating feedback content" refers to a function for generating specific and appropriate feedback messages based on the analysis results.

[0147] "Device" refers to a robot or other automated device that receives feedback.

[0148] "Appropriate timing" refers to the time and situation in which feedback should be most effectively reflected in the device.

[0149] "Means for transmitting" refers to the network and communication technologies for transmitting the generated feedback to the device.

[0150] The "means for storing in a queue" refers to a function for temporarily storing the generated feedback content until the appropriate time to send it.

[0151] "Determined timing" refers to the time and conditions for executing feedback based on analysis and external conditions.

[0152] A "natural language processing engine" refers to artificial intelligence technology that analyzes feedback information and extracts important information and key phrases.

[0153] "Generating based on the analysis results" refers to the process of constructing specific feedback content based on the analyzed information.

[0154] This invention is a system that provides timely and effective feedback from a superior to equipment (such as a factory robot). The system consists of three main components: a superior terminal, a server, and an equipment terminal.

[0155] Operation on the host terminal

[0156] The supervisor installs a dedicated application on the terminal and inputs feedback information for the device. For example, if the supervisor inputs feedback such as "Please increase the operating speed," the information is sent to the server.

[0157] Processing on the server

[0158] When the server receives feedback information from the host terminal, the received information is first stored in a database. The feedback content is then analyzed using a natural language processing engine (such as BERT). As a result, key phrases are extracted, and "Please increase the movement speed" is recognized as a specific improvement instruction. Next, the AI ​​model generates the feedback content based on the analysis results. As a specific example, the AI ​​model generates the instruction "Please increase the robot's movement speed by 20%."

[0159] The generated feedback content is stored in a queue along with the optimal transmission timing, for example, the time when the device terminal can optimally receive the feedback is determined, and the feedback is scheduled to be transmitted at that time.

[0160] Operation on the device terminal

[0161] When a device terminal receives feedback from the server, the content is immediately saved in its internal memory. At the appropriate time, the feedback content is reflected in the device's control system. For example, if a device terminal receives an instruction such as "Increase the robot's movement speed by 20%, it will adjust the movement speed accordingly.

[0162] Overall system operation

[0163] The feedback information entered by the supervisor is analyzed on the server, and specific feedback content is generated by an AI model and sent to the equipment terminal at the optimal timing. This system enables the supervisor to provide timely and effective feedback to factory robots. An example of an input prompt sentence is shown below as a concrete example.

[0164] Prompt Sentence Examples

[0165] "I would like to increase the operating speed of Robot X. Its current operating speed is slow, which is reducing the efficiency of the entire production line."

[0166] Based on such prompts, the AI ​​generates specific feedback such as "Please increase Robot X's movement speed by 20%," and the server sends the instructions to the device terminal at the appropriate time.

[0167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0168] Step 1:

[0169] The superior inputs feedback information from the terminal. As an example, "Please increase the speed of operation" is entered into the text box. The input data is sent to the server by clicking the "Send" button. The input is text data, and the output is feedback information sent to the server.

[0170] Step 2:

[0171] The server stores the feedback information received from the host terminal in a database. Storing the feedback information in a database ensures that the feedback information is managed continuously and safely. The input is the feedback information received from the terminal, and the output is the feedback information stored in the database.

[0172] Step 3:

[0173] The server extracts feedback information from the database and analyzes it using a natural language processing engine (NLP model). Important key phrases are extracted through the analysis. For example, the key phrases "movement speed" and "please increase it" are obtained. The input is the feedback information extracted from the database, and the output is the analysis results in the form of key phrases.

[0174] Step 4:

[0175] Based on the analysis results, the server uses a generative AI model to generate specific feedback. For example, a specific instruction such as "Increase the robot's movement speed by 20%" is generated. The input is the analysis result obtained through natural language processing, and the output is the specific feedback generated.

[0176] Step 5:

[0177] The server stores the generated feedback in a queue along with the appropriate transmission timing, for example, setting it to be sent at the start of the next production shift. The input is the generated feedback, and the output is the feedback stored in the queue and the transmission timing.

[0178] Step 6:

[0179] The server sends the feedback stored in the queue to the equipment terminal based on the timing it determines, for example, when the next shift starts. The input is the feedback stored in the queue and its sending timing, and the output is the feedback sent to the equipment terminal.

[0180] Step 7:

[0181] The device terminal stores the feedback received from the server in its internal memory. The stored content is reflected in the device's control system at the appropriate time. The input is the feedback received from the server, and the output is the feedback stored in the device's internal memory.

[0182] Step 8:

[0183] The device executes operations based on the feedback stored in its internal memory. For example, an instruction to "increase the robot's movement speed by 20%" is reflected in the actual movement control. The input is the feedback stored in the internal memory, and the output is the actual robot movement.

[0184] 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.

[0185] This invention is a system that uses AI and emotion recognition technology to provide effective and safe feedback from superiors to subordinates. This system consists of three main components: a superior terminal, a server, and a subordinate terminal. By combining these with an emotion engine, the system can dynamically adjust the feedback content based on the user's emotions.

[0186] Operations on the boss's terminal

[0187] A supervisor enters feedback information about a subordinate using a device with a dedicated application installed. The supervisor accesses the feedback input screen, selects the subordinate's name, and enters the feedback content in the text box. When the supervisor clicks the "Send" button, the feedback information is sent to the server. Furthermore, during this process, the emotion engine recognizes the emotion the supervisor was feeling when entering the feedback and modifies the tone and expression of the feedback content as appropriate. For example, if a supervisor enters "Your comments in the recent meeting were accurate, but I would like you to say more," and the emotion engine recognizes the supervisor's positive emotion, it will modify the feedback to read, "Your comments in the recent meeting were very accurate. Please try to speak more."

[0188] Processing on the server

[0189] The server receives feedback information from the superior's device. The received information is stored in a database and then passed to a natural language processing engine. The engine analyzes the feedback content and extracts important key phrases such as "You speak little, but accurately." The AI ​​model then generates specific feedback content based on the analysis results. During this process, the emotion engine checks whether the generated feedback content is appropriate for the subordinate and modifies it if necessary. The generated feedback content is "Try to share more ideas with confidence."

[0190] The generated feedback content is stored in a queue along with the appropriate timing. For example, if it is determined that the subordinate would best receive the feedback when they arrive at work in the morning, the server will schedule the feedback to be sent to the subordinate's device at that time.

[0191] Operations on subordinate devices

[0192] When a subordinate's device receives feedback from the server, the content is immediately saved in its internal memory and displayed to the subordinate through the user interface at the appropriate time. During this process, the subordinate's emotions are recognized by the emotion engine, and the follow-up content is modified depending on how the feedback was received. For example, if a subordinate reacts positively to the feedback displayed at the start of work in the morning, "Try to share more ideas with confidence," the follow-up message will be, "We look forward to hearing your opinion."

[0193] Overall system operation

[0194] This system reduces the risk of a supervisor giving direct feedback to a subordinate, and provides a mechanism for subordinates to receive feedback that will lead to their growth at an appropriate and effective time. Feedback information entered from the supervisor's device is sent to a server, where it is analyzed and feedback is generated using an AI model, after which the emotion engine is checked and corrected. It is then sent to the subordinate's device at the optimal time. This results in smoother communication between the supervisor and subordinate, promoting the subordinate's growth.

[0195] This is the overall system configuration for implementing the present invention.

[0196] The processing flow will be explained below.

[0197] Step 1:

[0198] The supervisor launches the dedicated app or web app. The supervisor selects the "Enter Feedback" option from the main menu, and the feedback entry screen appears.

[0199] Step 2:

[0200] The manager selects the subordinate's name from a drop-down menu, then enters feedback in the text box (e.g., "Your comments in recent meetings were accurate, but I'd like to see more of you.").

[0201] Step 3:

[0202] The boss's device uses an emotion engine to recognize the boss's emotions as they are being input. The emotion engine evaluates the boss's emotional state (e.g., positive, negative) and modifies the feedback content as necessary. For example, if the boss is inputting with a positive emotion, the feedback content will be modified to "Your comments in the recent meeting were very accurate. Please try to speak up more."

[0203] Step 4:

[0204] After the supervisor checks the revised feedback content, he / she clicks the "Send" button. The supervisor's device catches the click event of the Send button, converts the feedback content and the subordinate's identification information into JSON format, and sends an HTTP POST request to the server's API endpoint.

[0205] Step 5:

[0206] The server receives an HTTP POST request at the specified API endpoint, parses the received JSON data, and extracts the feedback content and subordinate's identification information.

[0207] Step 6:

[0208] The server passes the extracted feedback to a natural language processing (NLP) engine, which analyzes the meaning of the feedback and extracts key information (e.g., "Small but accurate").

[0209] Step 7:

[0210] The server inputs the analysis results into the AI ​​model, which then generates optimal feedback for the subordinate based on the analysis results (e.g., "Try to share more ideas with confidence").

[0211] Step 8:

[0212] The generated feedback is passed to the emotion engine, which evaluates whether the tone and expression of the feedback are appropriate and makes corrections as necessary. For example, the tone may be changed to a gentler tone to prevent the subordinate from feeling overly stressed.

[0213] Step 9:

[0214] The server stores the generated feedback content in a queue along with the appropriate delivery timing. The queue contains feedback content to be sent and its delivery timing.

[0215] Step 10:

[0216] Based on the determined timing, the server retrieves the feedback content from the queue and sends an HTTP POST request to the subordinate terminal.

[0217] Step 11:

[0218] The subordinate device receives an HTTP POST request from the server, analyzes the received JSON data, and extracts the feedback content.

[0219] Step 12:

[0220] The subordinate's device uses an appropriate user interface to display the feedback content on the screen. The subordinate then checks the displayed feedback.

[0221] Step 13:

[0222] The subordinate's device recognizes the subordinate's reaction to the feedback using an emotion engine. The emotion engine evaluates the subordinate's emotional state and provides follow-up feedback as needed. For example, if the subordinate reacts positively, a further encouraging message is displayed.

[0223] Example 2

[0224] 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."

[0225] When a manager gives feedback to a subordinate, it is often necessary to convey emotion and express it appropriately. However, inconsistencies in emotion or timing can sometimes result in feedback having the opposite effect. Furthermore, if the feedback is too formal and lacks specificity, it is difficult to promote the subordinate's growth. Conventional systems often fail to adequately resolve these issues.

[0226] 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.

[0227] In this invention, the server includes means for receiving feedback information input from a superior, means for analyzing the received feedback information, recognizing emotions, and modifying the tone and expression of the feedback content, means for generating feedback content based on the analysis results, and means for transmitting the generated feedback content to a subordinate at an appropriate timing. This enables appropriate feedback according to the superior's emotions and timing, and promotes the growth of the subordinate.

[0228] "Feedback information" refers to information that includes evaluations, comments, advice, etc., given by superiors to subordinates.

[0229] The "receiving means" is a function that allows the server to receive feedback information sent from the superior terminal.

[0230] "Means for analysis" refers to the function for processing and analyzing received feedback information and extracting necessary key phrases and emotions.

[0231] "Means of recognizing emotions" refers to a technology that analyzes the emotional aspects of the feedback entered by a supervisor and makes adjustments based on that.

[0232] The "means for generating feedback content" is a function that creates specific feedback appropriate for subordinates based on the analyzed data.

[0233] The "means for transmitting the generated feedback content" is a function for transmitting the feedback content to the subordinate terminal at an appropriate timing.

[0234] The "means for storing in a queue" is a technique for temporarily storing the generated feedback content and managing it so that it can be sent at a specified timing.

[0235] A "key phrase" is a set of short sentences or words that indicate particularly important parts of the feedback information.

[0236] A "generative AI model" is an artificial intelligence algorithm used to automatically generate feedback content.

[0237] A "natural language processing engine" is a technology for analyzing text data and extracting meaning and key phrases.

[0238] An "emotion engine" is a technology that analyzes emotions from text and voice and adjusts the feedback content based on that information.

[0239] The "user interface" is the part of the system that provides the screen and operation methods for subordinates to view the feedback content.

[0240] This invention is a system that uses AI and emotion recognition technology to provide effective and safe feedback from superiors to subordinates. This system consists of three main components: a superior terminal, a server, and a subordinate terminal. By combining these components with an emotion engine, the system can dynamically adjust the feedback content based on the user's emotions.

[0241] Operations on the boss's terminal

[0242] A supervisor uses a device with dedicated software installed to enter feedback information about a subordinate. The supervisor accesses the feedback entry screen, selects the subordinate's name, and enters the feedback content in the text box. For example, the supervisor can enter, "Your comments in the recent meeting were accurate, but I would like you to speak up more." When the supervisor clicks the "Send" button, the feedback information is sent from the terminal to the server. During this process, the emotion engine recognizes the emotion the supervisor was feeling when entering the feedback and modifies the tone and expression of the feedback content accordingly. For example, if the emotion engine recognizes the supervisor's positive emotion, it will modify the feedback to, "Your comments in the recent meeting were very accurate. Please speak up more."

[0243] Processing on the server

[0244] The server receives feedback information from the supervisor's device. The received information is stored in a database such as MySQL. It is then passed to a natural language processing engine (e.g., SpaCy). The natural language processing engine analyzes the feedback content and extracts important key phrases such as "quiet but accurate."

[0245] Next, an AI model (e.g., GPT-4) generates specific feedback content based on the analysis results. During this process, an emotion engine (e.g., Affectiva) checks whether the generated feedback content is appropriate for the subordinate and modifies it if necessary. For example, the generated feedback content could be, "Try to share more ideas with confidence."

[0246] The generated feedback content is stored in a queue along with the appropriate timing. For example, if it is determined that the subordinate would best receive the feedback when they arrive at work in the morning, the server will schedule the feedback to be sent to the subordinate's device at that time.

[0247] Operations on subordinate devices

[0248] When a subordinate's device receives feedback from the server, the content is immediately saved in internal memory (for example, an SQLite database). At the appropriate time, the feedback content is displayed to the subordinate through the user interface. During this process, the emotion engine recognizes the subordinate's emotions and modifies the follow-up content depending on how the feedback was received. For example, if a subordinate reacts positively to the feedback displayed at the start of work in the morning, "Try to share more ideas with confidence," the follow-up message will be "We look forward to your opinion."

[0249] Examples of prompts for generative AI models

[0250] "Use this feedback, 'You don't say much, but you get it. I wish you'd be more confident and share your ideas,' to generate more positive feedback that's appropriate for your employee."

[0251] This system reduces the risk of a supervisor giving direct feedback to a subordinate and provides a mechanism for subordinates to receive feedback that leads to growth at an appropriate and effective time. Feedback information entered from the supervisor's device is sent to a server, where it is analyzed and feedback is generated using an AI model, after which the emotion engine is checked and corrected. This information is then sent to the subordinate's device at the optimal time, facilitating smooth communication between the supervisor and subordinate and promoting the subordinate's growth. This system contributes to improving the quality of feedback in companies and organizations.

[0252] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0253] Step 1:

[0254] The user launches the dedicated application and accesses the feedback input screen. After selecting the subordinate's name, they enter their feedback in the text box. Once they've finished entering their feedback, they click the "Send" button. The supervisor's device passes this input to an emotion engine, which analyzes the content while recognizing the supervisor's emotions. As a result, the tone and expression of the feedback are adjusted.

[0255] Input: Feedback entered by the manager (e.g., "Your comments in recent meetings were accurate, but I'd like you to say more.")

[0256] Output: Corrected feedback (e.g., "You were very accurate in your recent meeting. Please try speaking up more.")

[0257] Step 2:

[0258] The device sends the corrected feedback to the server, which receives the data and stores it in a database. A relational database such as MySQL is used to store the feedback data.

[0259] Input: Corrected feedback

[0260] Output: Feedback information stored in a database

[0261] Step 3:

[0262] The server retrieves the feedback information from the database and passes it to a natural language processing engine (e.g., SpaCy) for analysis. The engine analyzes the feedback content and extracts important key phrases. For example, the key phrase extracted is "quiet but accurate."

[0263] Input: Feedback information stored in the database

[0264] Output: Extracted key phrases (e.g., "Small but precise")

[0265] Step 4:

[0266] The server then passes the extracted key phrases to a generative AI model (e.g., GPT-4) as prompts to generate specific feedback. The generated feedback is then checked by an emotion engine and corrected if necessary.

[0267] Input: Extracted key phrases

[0268] Output: Generated and revised feedback (e.g., "Try to be more confident and share more ideas")

[0269] Step 5:

[0270] The server stores the generated and modified feedback in a queue and schedules appropriate times for sending it, for example, when subordinates arrive at work in the morning.

[0271] Input: Generated and revised feedback

[0272] Output: Queued feedback

[0273] Step 6:

[0274] The subordinate's device receives the feedback content at the specified time. The received content is immediately saved in the internal memory (SQLite database) and displayed on the user interface at the appropriate time. When the subordinate confirms the feedback, the emotion engine analyzes the subordinate's emotions and performs adaptive follow-up.

[0275] Input: Feedback sent from the queue

[0276] Output: Feedback displayed on the subordinate's device, along with any necessary follow-up (e.g., "I look forward to hearing your opinion.")

[0277] The above is the specific processing flow of this system. This system effectively supports communication between superiors and subordinates and promotes the growth of subordinates.

[0278] (Application example 2)

[0279] 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."

[0280] When using robots in factories, it is important for managers to provide appropriate feedback to robots. However, conventional systems do not accurately reflect the manager's emotions and intentions, making it difficult to appropriately improve the robot's work efficiency and performance. Furthermore, there is a lack of mechanisms for the robot to respond appropriately to the feedback it receives, making it difficult to optimize work efficiency. Furthermore, continuous improvement is hindered by insufficient follow-up based on how the feedback is received.

[0281] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving feedback information input from a superior, means for analyzing the received feedback information, and means for generating feedback content based on the analysis results. This makes it possible to modify the tone and expression of the feedback using an emotion recognition engine. In addition, by including means for sending the feedback content stored in the queue to a subordinate terminal at a determined timing, analyzing the subordinate's emotions in response to the feedback received by the subordinate terminal, and modifying the follow-up content, it becomes possible for the robot to adjust its work efficiency and performance based on the feedback content received. This provides a system in which the manager's intentions are accurately reflected, the robot's work efficiency is improved, and continuous improvement is achieved.

[0282] "Feedback information entered by a superior" refers to evaluations, comments, and advice entered by a manager in the factory based on the robot's work status.

[0283] An "emotion recognition engine" is a technology that analyzes emotions from input text or voice and modifies the tone and expression of information based on those emotions.

[0284] "Feedback content generated based on the analysis results" refers to information that has been reconstructed as appropriate feedback content based on the results of analysis using a natural language processing engine.

[0285] A "subordinate terminal" is a device for receiving and displaying feedback content, and in this case refers to a robot that performs work in a factory.

[0286] A "natural language processing engine" is an algorithm or process that analyzes input text data and understands its content and meaning.

[0287] A "queue" is a data structure for temporarily storing information such as feedback content and transmission timing.

[0288] "Follow-up" refers to ongoing confirmation and advice after the initial feedback, adjusted based on the subordinate's response.

[0289] "Means for adjusting work efficiency and performance" refers to methods and mechanisms by which a robot receives feedback and improves and optimizes its own movements and the way it carries out its work.

[0290] This invention is specifically implemented as a feedback system for robot work in a factory. The system mainly consists of a supervisor terminal, a server, and subordinate terminals (factory work robots).

[0291] Overall system configuration

[0292] Supervisor's terminal: A supervisor uses a smartphone or other device to input feedback information based on the robot's work status. The supervisor's terminal is equipped with an emotion recognition engine that analyzes the emotions expressed during input and includes a function to modify the tone and expression of the feedback.

[0293] Server: Receives feedback information and stores it in a database. Furthermore, it analyzes the data using a natural language processing engine and generates feedback content based on the analysis results. The generated feedback content is corrected to an appropriate tone using an emotion recognition engine and stored in a queue based on the appropriate sending timing. The server uses software such as Flask (web framework), TextBlob (natural language processing), and emotion_recognition (emotion recognition).

[0294] Subordinate terminal (factory robot): This terminal receives feedback from the server, and is played by the factory robot. The robot adjusts its work efficiency and performance based on the received feedback. The robot's reaction to the feedback (if it analyzes emotions) is also sent to the server, and appropriate follow-up is carried out.

[0295] Specific examples

[0296] Example of administrator input: An administrator enters feedback such as "Your work speed is a little slow."

[0297] Emotion recognition and correction: The emotion recognition engine analyzes the input feedback as having a "neutral" emotion and corrects it to "Please be careful to speed up your work."

[0298] Server processing: The feedback information sent to the server is analyzed by a natural language processing engine, which identifies the key phrase "speed" and generates and modifies appropriate improvement suggestions.

[0299] Robot response: The robot receives feedback and makes adjustments to improve its speed of work.

[0300] Prompt Sentence Examples

[0301] Example of feedback provided by the administrator:

[0302] Admin Feedback: I feel like I'm repeating myself

[0303] Expected output:

[0304] Think about your work efficiency and look for areas for improvement.

[0305] Hardware and software used

[0306] Hardware: Smartphone (supervisor's device), server (database and analysis processing), robots that work in the factory (subordinate devices).

[0307] Software: Flask (web framework for server), TextBlob (natural language processing), emotion_recognition (emotion recognition engine).

[0308] This system allows the manager's intentions to be accurately reflected in the robot, improving the robot's work efficiency and enabling continuous adaptation and improvement.

[0309] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0310] Step 1:

[0311] Feedback input on the boss's terminal:

[0312] A user (manager) uses a supervisor's device such as a smartphone to input textual feedback on the performance of a factory robot. This textual input is passed to an emotion recognition engine, which analyzes the tone and expression of the feedback and corrects it as necessary. The feedback text is given as input, and tone-corrected feedback text is generated as output.

[0313] Example: If a manager types "I'm a little slow at work," it will be corrected to "Please pay attention to speeding up your work."

[0314] Step 2:

[0315] Send feedback information:

[0316] The feedback text corrected on the supervisor's terminal is sent to the server. The corrected feedback text is used as input, and the text is transferred to the server as output.

[0317] Example: "Pay attention to speeding up your work" feedback is sent to the server.

[0318] Step 3:

[0319] Feedback analysis on the server:

[0320] The server passes the received feedback text to a natural language processing engine, which analyzes the text, extracts important key phrases, and reconstructs the feedback content. The received feedback text is used as input, and the analyzed feedback content is generated as output.

[0321] Example: Identifying "speed" as a key phrase and generating an appropriate improvement suggestion such as "Try to improve your work speed."

[0322] Step 4:

[0323] Sentiment check and correction of generated feedback:

[0324] The server-generated feedback content is checked by an emotion recognition engine and the expressions are corrected if necessary. The reconstructed feedback content is used as input and the final feedback text is generated as output.

[0325] Example: "Please try to improve your work speed" is corrected to "Please try."

[0326] Step 5:

[0327] Queued feedback:

[0328] The server stores the final feedback text and send timing in a queue. The revised feedback text and send timing are used as input to generate a data entry that is stored in the queue as output.

[0329] Example: The feedback "Please try harder" is queued to be sent at 9am the next morning.

[0330] Step 6:

[0331] Send feedback from a queue:

[0332] Based on the determined timing, the feedback content is sent from the queue to the subordinate device (robot). The data entries stored in the queue are used as input, and the feedback that is sent to the robot as output is generated.

[0333] Example: The robot receives feedback saying "Please try harder" at 9am the next morning.

[0334] Step 7:

[0335] Receiving and acting on feedback in the robot:

[0336] The subordinate device (robot) stores the received feedback in its internal memory and adjusts its work efficiency and performance based on the feedback. The received feedback is used as input, and the robot's behavior is adjusted as output.

[0337] Example: A robot receives feedback saying "try harder" and adjusts its speed.

[0338] Step 8:

[0339] Analysis of the robot's response to feedback:

[0340] The robot responds to the feedback and its reaction (e.g., improved work speed) is sent to the server. The server analyzes this reaction and generates or modifies follow-up feedback as needed. The robot's response data is used as input, and the next feedback content is generated as output.

[0341] Example: A robot increases its work speed and sends the results to a server, which generates follow-up feedback such as "keep up the good work."

[0342] 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.

[0343] 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.

[0344] 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.

[0345] [Second embodiment]

[0346] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0347] 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.

[0348] 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).

[0349] 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.

[0350] 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.

[0351] 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).

[0352] 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.

[0353] 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.

[0354] 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.

[0355] 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.

[0356] 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.

[0357] 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."

[0358] This invention is a system that uses AI technology to provide effective and safe feedback from superiors to subordinates. This system consists of three main components: the superior's terminal, the server, and the subordinate's terminal. Below, we will explain the specific operating procedures for each component and the operation of the entire system.

[0359] Operations on the boss's terminal

[0360] A supervisor enters feedback information about a subordinate using a terminal with a dedicated application installed. The supervisor accesses the feedback input screen, selects the subordinate's name, and enters the feedback content in the text box. When the supervisor clicks the "Send" button, the feedback information is sent to the server. As a concrete example, let's say the supervisor enters, "Your comments in the recent meeting were accurate, but I would like you to say more."

[0361] Processing on the server

[0362] The server receives feedback information from the manager's device. The received information is stored in a database and then passed to a natural language processing engine. The engine analyzes the feedback content and extracts important key phrases such as "quiet but accurate." The AI ​​model then generates specific feedback content based on the analysis results. An example of feedback in this case would be "Try to share more ideas with confidence."

[0363] The generated feedback content is stored in a queue along with the appropriate timing. For example, if it is determined that the subordinate would best receive the feedback when they arrive at work in the morning, the server will schedule the feedback to be sent to the subordinate's device at that time.

[0364] Operations on subordinate devices

[0365] When a subordinate's device receives feedback from the server, the content is immediately saved in its internal memory. At the appropriate time, the feedback content is displayed to the subordinate through the user interface. For example, when a subordinate starts work in the morning, they will see the feedback displayed as "Try to share more ideas with confidence."

[0366] Overall system operation

[0367] This system reduces the risk of a supervisor giving direct feedback to a subordinate and provides a mechanism for subordinates to receive feedback that will lead to their growth at an appropriate and effective time. Feedback information entered from the supervisor's device is sent to a server, where it is analyzed and feedback generated by an AI model is sent to the subordinate's device at the optimal time. As a result, communication between the supervisor and subordinate becomes smoother, promoting the subordinate's growth.

[0368] This is the overall system configuration for implementing the present invention.

[0369] The processing flow will be explained below.

[0370] Step 1:

[0371] The supervisor launches the dedicated app or web app. The supervisor selects the "Enter Feedback" option from the main menu, and the feedback entry screen appears.

[0372] Step 2:

[0373] The manager selects the subordinate's name from the drop-down menu, then enters the feedback in the text box (e.g., "Your comments in recent meetings were accurate, but I'd like to see more of you."), and clicks the "Send" button.

[0374] Step 3:

[0375] The boss's device catches the click event of the send button, converts the feedback content and the subordinate's identification information into JSON format, and sends an HTTP POST request to the server's API endpoint.

[0376] Step 4:

[0377] The server receives an HTTP POST request at the specified API endpoint, parses the received JSON data, and extracts the feedback content and subordinate's identification information.

[0378] Step 5:

[0379] The server passes the extracted feedback to a natural language processing (NLP) engine, which analyzes the meaning of the feedback and extracts key information (e.g., "Small but accurate").

[0380] Step 6:

[0381] The server inputs the analysis results into the AI ​​model, which then generates optimal feedback for the subordinate based on the analysis results (e.g., "Try to share more ideas with confidence").

[0382] Step 7:

[0383] The server compares the generated feedback content with the subordinate's timetable database to determine the optimal transmission timing, and stores the determined feedback content and transmission timing in a queue.

[0384] Step 8:

[0385] Based on the determined timing, the server retrieves the feedback content from the queue and sends an HTTP POST request to the subordinate terminal.

[0386] Step 9:

[0387] The subordinate device receives an HTTP POST request from the server, analyzes the received JSON data, and extracts the feedback content.

[0388] Step 10:

[0389] The subordinate's device uses an appropriate user interface to display the feedback content on the screen. The subordinate checks the displayed feedback and considers possible actions.

[0390] Example 1

[0391] 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."

[0392] Typically, when a manager provides direct feedback to a subordinate, the timing and content are often inappropriate, which results in the subordinate's growth being unsatisfactory. There is also a risk that the manager's feedback may be inappropriate or the subordinate may feel uncomfortable due to poor choice of words. There is a need for a system that can solve these issues and provide feedback to subordinates more effectively and safely.

[0393] 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.

[0394] In this invention, the server includes means for receiving feedback information input from a superior, means for saving the received feedback information in a storage device, means for analyzing the saved feedback information using natural language processing technology, means for generating feedback content based on the analysis result using a generative AI model, and means for sending the generated feedback content to a subordinate at an appropriate time. This makes it possible to analyze feedback from a superior in an appropriate manner, generate optimal feedback content, and provide it to a subordinate at an appropriate time.

[0395] A "supervisor" is an individual in an organization who is in a position to give direct instructions and manage subordinates.

[0396] A "subordinate" is an individual in an organization who is in a position to receive instructions and management from a superior.

[0397] "Feedback information" refers to the content of evaluations, comments, advice, etc. that a superior provides to a subordinate.

[0398] The "receiving means" is a function for taking the feedback information sent from the superior terminal into the server.

[0399] The "storing means" is a function for storing received feedback information in a database or storage device.

[0400] "Natural language processing technology" is a technology for analyzing text data in natural language and converting it into a form that humans can understand.

[0401] "Means of analysis" refers to the function of understanding and analyzing feedback information using natural language processing technology.

[0402] A "generative AI model" is an artificial intelligence model that has been trained in advance using large amounts of data and generates feedback content based on input information.

[0403] "Means for generation" refers to a function for creating feedback content using a generative AI model based on the analysis results.

[0404] The "transmitting means" is a function for sending the generated feedback content to the subordinate terminal.

[0405] The "means for storing in a queue" is a function for temporarily storing the generated feedback content so that it can be sent at an appropriate time.

[0406] "Transmission timing" refers to the optimal time and conditions for transmitting the feedback content to the subordinate terminal.

[0407] "Subordinate terminal" refers to a terminal device used by a subordinate to receive and display feedback.

[0408] MODE FOR CARRYING OUT THE INVENTION

[0409] This invention is a system that uses AI technology to provide feedback from superiors to subordinates effectively and safely. This system consists of three main components: a superior terminal, a server, and a subordinate terminal. The specific operating procedures and the operation of the entire system are explained in detail below.

[0410] Operations on the boss's terminal

[0411] The supervisor uses a device with a dedicated application installed. This device can be a PC or smartphone. To enter feedback information, the supervisor accesses the feedback input screen of the dedicated application, selects the subordinate's name, and enters the feedback content in the text box. For example, the supervisor might enter, "Your comments in the recent meeting were accurate, but I would like you to say more." Once this input is complete, the supervisor clicks the "Send" button to transfer the feedback information to the server.

[0412] Processing on the server

[0413] The server receives the feedback information sent from the supervisor's device. The received feedback information is first stored in a database (e.g., MySQL). The feedback content is then analyzed using a natural language processing engine (e.g., spaCy, NLTK). Through the analysis, important key phrases such as "You speak little, but accurately" are extracted. The server then passes the extracted key phrases to a generative AI model (e.g., GPT-3, BERT) to generate specific feedback content. For example, feedback such as "Try to share more ideas with confidence" is generated.

[0414] The generated feedback is scheduled with the appropriate timing for the subordinate to receive it. The server determines the optimal timing for sending the feedback (e.g., when the subordinate arrives at work in the morning) based on the subordinate's behavioral patterns and preferences, and stores the feedback in a queue.

[0415] Operations on subordinate devices

[0416] The subordinate's device receives the feedback sent from the server. The received feedback is stored in the internal memory and displayed to the subordinate through the user interface at the appropriate time. For example, when the subordinate starts work in the morning, the feedback "Try to share more ideas with confidence" is displayed.

[0417] Examples and prompts

[0418] For example, let's say your boss writes, "Your contributions to the recent project have been great, but you could do better if you paid more attention to the details." This feedback information is parsed and generated as follows:

[0419] Analysis results of the natural language processing engine:

[0420] "Great contributions but attention to detail"

[0421] Feedback generated by the generative AI model:

[0422] "The results are excellent, but with more attention to detail the results would be even better."

[0423] Example prompt for a generative AI model:

[0424] Prompt: Your contribution to your recent project has been great, but it could be even better with a little more attention to detail.

[0425] Output: Good results, but more attention to detail would produce even better results.

[0426] This system reduces the risk involved when a manager gives direct feedback to a subordinate and enables effective feedback to be given at the right time, resulting in smoother communication between managers and subordinates and promoting the growth of subordinates.

[0427] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0428] Step 1: Enter and send feedback on the supervisor's device

[0429] Input: Launch the dedicated application installed on the supervisor's device and access the feedback input screen.

[0430] How it works: A manager selects a subordinate's name and enters specific feedback in the text box.

[0431] Output: When the manager clicks the "Send" button, the feedback information is converted into a data packet and sent to the server.

[0432] Step 2: Receiving and storing feedback information on the server

[0433] Input: Receives data packets sent from the boss's terminal.

[0434] Operation: The server parses the received data packets and extracts the feedback information.

[0435] Output: Save the feedback information to a database (e.g. MySQL).

[0436] Step 3: Analysis using natural language processing on the server

[0437] Input: Feedback information stored in the database.

[0438] How it works: The server passes the feedback information to a natural language processing engine (e.g. spaCy, NLTK) for content analysis.

[0439] A natural language processing engine extracts important key phrases from the feedback.

[0440] Output: As a result of the analysis, we obtain key phrases such as "few comments but accurate."

[0441] Step 4: Feedback generation by the AI ​​model on the server

[0442] Input: Analysis results (important key phrases) obtained from the natural language processing engine.

[0443] How it works: The server inputs the analysis results into a generative AI model (e.g., GPT-3, BERT).

[0444] A generative AI model generates specific feedback content based on key phrases.

[0445] Output: For example, you get feedback such as "Try to share more ideas with confidence."

[0446] Step 5: Registering the schedule on the server

[0447] Input: The specific feedback generated.

[0448] How it works: The server determines the best time to send feedback (e.g., when a subordinate arrives at work).

[0449] Queue feedback and when to send it.

[0450] Output: Feedback stored along with the timing of sending.

[0451] Step 6: Receive and display feedback on subordinate devices

[0452] Input: Feedback information sent by the server.

[0453] Operation: The subordinate device receives the feedback information and stores it in its internal memory.

[0454] Providing feedback through the user interface at the appropriate time.

[0455] Output: For example, a message is displayed to the subordinate saying, "Try to share more ideas with confidence."

[0456] This enables a series of steps to be taken, in which feedback information entered from the superior's device is analyzed and generated on the server, and then sent to the subordinate's device at the optimal timing.

[0457] (Application example 1)

[0458] 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."

[0459] In modern factories, real-time feedback is necessary to efficiently improve the behavior and performance of robots. However, when supervisors provide feedback directly to factory robots, it is difficult to instruct effective actions at the appropriate time. Furthermore, advanced technology is required to accurately analyze the robot's operating status and provide appropriate improvement instructions. A means to effectively solve these issues is needed.

[0460] 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.

[0461] In this invention, the server includes means for receiving feedback information input from a superior, means for analyzing the received feedback information, means for generating feedback content based on the analysis results, and means for transmitting the generated feedback content to the device at an appropriate time, thereby enabling the superior to provide timely and effective feedback to the factory robot and improving the robot's operation and performance.

[0462] "Superior" refers to the person responsible for providing feedback to the system.

[0463] "Feedback information" refers to the content of evaluations and advice for the subject, such as text or audio entered by superiors.

[0464] "Means for receiving" refers to the function that allows the system to incorporate feedback information provided by superiors.

[0465] "Means for analysis" refers to the function of analyzing received feedback information using a natural language processing engine or the like and extracting meaning.

[0466] The "means for generating feedback content" refers to a function for generating specific and appropriate feedback messages based on the analysis results.

[0467] "Device" refers to a robot or other automated device that receives feedback.

[0468] "Appropriate timing" refers to the time and situation in which feedback should be most effectively reflected in the device.

[0469] "Means for transmitting" refers to the network and communication technologies for transmitting the generated feedback to the device.

[0470] The "means for storing in a queue" refers to a function for temporarily storing the generated feedback content until the appropriate time to send it.

[0471] "Determined timing" refers to the time and conditions for executing feedback based on analysis and external conditions.

[0472] A "natural language processing engine" refers to artificial intelligence technology that analyzes feedback information and extracts important information and key phrases.

[0473] "Generating based on the analysis results" refers to the process of constructing specific feedback content based on the analyzed information.

[0474] This invention is a system that provides timely and effective feedback from a superior to equipment (such as a factory robot). The system consists of three main components: a superior terminal, a server, and an equipment terminal.

[0475] Operation on the host terminal

[0476] The supervisor installs a dedicated application on the terminal and inputs feedback information for the device. For example, if the supervisor inputs feedback such as "Please increase the operating speed," the information is sent to the server.

[0477] Processing on the server

[0478] When the server receives feedback information from the host terminal, the received information is first stored in a database. The feedback content is then analyzed using a natural language processing engine (such as BERT). As a result, key phrases are extracted, and "Please increase the movement speed" is recognized as a specific improvement instruction. Next, the AI ​​model generates the feedback content based on the analysis results. As a specific example, the AI ​​model generates the instruction "Please increase the robot's movement speed by 20%."

[0479] The generated feedback content is stored in a queue along with the optimal transmission timing, for example, the time when the device terminal can optimally receive the feedback is determined, and the feedback is scheduled to be transmitted at that time.

[0480] Operation on the device terminal

[0481] When a device terminal receives feedback from the server, the content is immediately saved in its internal memory. At the appropriate time, the feedback content is reflected in the device's control system. For example, if a device terminal receives an instruction such as "Increase the robot's movement speed by 20%, it will adjust the movement speed accordingly.

[0482] Overall system operation

[0483] The feedback information entered by the supervisor is analyzed on the server, and specific feedback content is generated by an AI model and sent to the equipment terminal at the optimal timing. This system enables the supervisor to provide timely and effective feedback to factory robots. An example of an input prompt sentence is shown below as a concrete example.

[0484] Prompt Sentence Examples

[0485] "I would like to increase the operating speed of Robot X. Its current operating speed is slow, which is reducing the efficiency of the entire production line."

[0486] Based on such prompts, the AI ​​generates specific feedback such as "Please increase Robot X's movement speed by 20%," and the server sends the instructions to the device terminal at the appropriate time.

[0487] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0488] Step 1:

[0489] The superior inputs feedback information from the terminal. As an example, "Please increase the speed of operation" is entered into the text box. The input data is sent to the server by clicking the "Send" button. The input is text data, and the output is feedback information sent to the server.

[0490] Step 2:

[0491] The server stores the feedback information received from the host terminal in a database. Storing the feedback information in a database ensures that the feedback information is managed continuously and safely. The input is the feedback information received from the terminal, and the output is the feedback information stored in the database.

[0492] Step 3:

[0493] The server extracts feedback information from the database and analyzes it using a natural language processing engine (NLP model). Important key phrases are extracted through the analysis. For example, the key phrases "movement speed" and "please increase it" are obtained. The input is the feedback information extracted from the database, and the output is the analysis results in the form of key phrases.

[0494] Step 4:

[0495] Based on the analysis results, the server uses a generative AI model to generate specific feedback. For example, a specific instruction such as "Increase the robot's movement speed by 20%" is generated. The input is the analysis result obtained through natural language processing, and the output is the specific feedback generated.

[0496] Step 5:

[0497] The server stores the generated feedback in a queue along with the appropriate transmission timing, for example, setting it to be sent at the start of the next production shift. The input is the generated feedback, and the output is the feedback stored in the queue and the transmission timing.

[0498] Step 6:

[0499] The server sends the feedback stored in the queue to the equipment terminal based on the timing it determines, for example, when the next shift starts. The input is the feedback stored in the queue and its sending timing, and the output is the feedback sent to the equipment terminal.

[0500] Step 7:

[0501] The device terminal stores the feedback received from the server in its internal memory. The stored content is reflected in the device's control system at the appropriate time. The input is the feedback received from the server, and the output is the feedback stored in the device's internal memory.

[0502] Step 8:

[0503] The device executes operations based on the feedback stored in its internal memory. For example, an instruction to "increase the robot's movement speed by 20%" is reflected in the actual movement control. The input is the feedback stored in the internal memory, and the output is the actual robot movement.

[0504] 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.

[0505] This invention is a system that uses AI and emotion recognition technology to provide effective and safe feedback from superiors to subordinates. This system consists of three main components: a superior terminal, a server, and a subordinate terminal. By combining these with an emotion engine, the system can dynamically adjust the feedback content based on the user's emotions.

[0506] Operations on the boss's terminal

[0507] A supervisor enters feedback information about a subordinate using a device with a dedicated application installed. The supervisor accesses the feedback input screen, selects the subordinate's name, and enters the feedback content in the text box. When the supervisor clicks the "Send" button, the feedback information is sent to the server. Furthermore, during this process, the emotion engine recognizes the emotion the supervisor was feeling when entering the feedback and modifies the tone and expression of the feedback content as appropriate. For example, if a supervisor enters "Your comments in the recent meeting were accurate, but I would like you to say more," and the emotion engine recognizes the supervisor's positive emotion, it will modify the feedback to read, "Your comments in the recent meeting were very accurate. Please try to speak more."

[0508] Processing on the server

[0509] The server receives feedback information from the superior's device. The received information is stored in a database and then passed to a natural language processing engine. The engine analyzes the feedback content and extracts important key phrases such as "You speak little, but accurately." The AI ​​model then generates specific feedback content based on the analysis results. During this process, the emotion engine checks whether the generated feedback content is appropriate for the subordinate and modifies it if necessary. The generated feedback content is "Try to share more ideas with confidence."

[0510] The generated feedback content is stored in a queue along with the appropriate timing. For example, if it is determined that the subordinate would best receive the feedback when they arrive at work in the morning, the server will schedule the feedback to be sent to the subordinate's device at that time.

[0511] Operations on subordinate devices

[0512] When a subordinate's device receives feedback from the server, the content is immediately saved in its internal memory and displayed to the subordinate through the user interface at the appropriate time. During this process, the subordinate's emotions are recognized by the emotion engine, and the follow-up content is modified depending on how the feedback was received. For example, if a subordinate reacts positively to the feedback displayed at the start of work in the morning, "Try to share more ideas with confidence," the follow-up message will be, "We look forward to hearing your opinion."

[0513] Overall system operation

[0514] This system reduces the risk of a supervisor giving direct feedback to a subordinate, and provides a mechanism for subordinates to receive feedback that will lead to their growth at an appropriate and effective time. Feedback information entered from the supervisor's device is sent to a server, where it is analyzed and feedback is generated using an AI model, after which the emotion engine is checked and corrected. It is then sent to the subordinate's device at the optimal time. This results in smoother communication between the supervisor and subordinate, promoting the subordinate's growth.

[0515] This is the overall system configuration for implementing the present invention.

[0516] The processing flow will be explained below.

[0517] Step 1:

[0518] The supervisor launches the dedicated app or web app. The supervisor selects the "Enter Feedback" option from the main menu, and the feedback entry screen appears.

[0519] Step 2:

[0520] The manager selects the subordinate's name from a drop-down menu, then enters feedback in the text box (e.g., "Your comments in recent meetings were accurate, but I'd like to see more of you.").

[0521] Step 3:

[0522] The boss's device uses an emotion engine to recognize the boss's emotions as they are being input. The emotion engine evaluates the boss's emotional state (e.g., positive, negative) and modifies the feedback content as necessary. For example, if the boss is inputting with a positive emotion, the feedback content will be modified to "Your comments in the recent meeting were very accurate. Please try to speak up more."

[0523] Step 4:

[0524] After the supervisor checks the revised feedback content, he / she clicks the "Send" button. The supervisor's device catches the click event of the Send button, converts the feedback content and the subordinate's identification information into JSON format, and sends an HTTP POST request to the server's API endpoint.

[0525] Step 5:

[0526] The server receives an HTTP POST request at the specified API endpoint, parses the received JSON data, and extracts the feedback content and subordinate's identification information.

[0527] Step 6:

[0528] The server passes the extracted feedback to a natural language processing (NLP) engine, which analyzes the meaning of the feedback and extracts key information (e.g., "Small but accurate").

[0529] Step 7:

[0530] The server inputs the analysis results into the AI ​​model, which then generates optimal feedback for the subordinate based on the analysis results (e.g., "Try to share more ideas with confidence").

[0531] Step 8:

[0532] The generated feedback is passed to the emotion engine, which evaluates whether the tone and expression of the feedback are appropriate and makes corrections as necessary. For example, the tone may be changed to a gentler tone to prevent the subordinate from feeling overly stressed.

[0533] Step 9:

[0534] The server stores the generated feedback content in a queue along with the appropriate delivery timing. The queue contains feedback content to be sent and its delivery timing.

[0535] Step 10:

[0536] Based on the determined timing, the server retrieves the feedback content from the queue and sends an HTTP POST request to the subordinate terminal.

[0537] Step 11:

[0538] The subordinate device receives an HTTP POST request from the server, analyzes the received JSON data, and extracts the feedback content.

[0539] Step 12:

[0540] The subordinate's device uses an appropriate user interface to display the feedback content on the screen. The subordinate then checks the displayed feedback.

[0541] Step 13:

[0542] The subordinate's device recognizes the subordinate's reaction to the feedback using an emotion engine. The emotion engine evaluates the subordinate's emotional state and provides follow-up feedback as needed. For example, if the subordinate reacts positively, a further encouraging message is displayed.

[0543] Example 2

[0544] 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."

[0545] When a manager gives feedback to a subordinate, it is often necessary to convey emotion and express it appropriately. However, inconsistencies in emotion or timing can sometimes result in feedback having the opposite effect. Furthermore, if the feedback is too formal and lacks specificity, it is difficult to promote the subordinate's growth. Conventional systems often fail to adequately resolve these issues.

[0546] 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.

[0547] In this invention, the server includes means for receiving feedback information input from a superior, means for analyzing the received feedback information, recognizing emotions, and modifying the tone and expression of the feedback content, means for generating feedback content based on the analysis results, and means for transmitting the generated feedback content to a subordinate at an appropriate timing. This enables appropriate feedback according to the superior's emotions and timing, and promotes the growth of the subordinate.

[0548] "Feedback information" refers to information that includes evaluations, comments, advice, etc., given by superiors to subordinates.

[0549] The "receiving means" is a function that allows the server to receive feedback information sent from the superior terminal.

[0550] "Means for analysis" refers to the function for processing and analyzing received feedback information and extracting necessary key phrases and emotions.

[0551] "Means of recognizing emotions" refers to a technology that analyzes the emotional aspects of the feedback entered by a supervisor and makes adjustments based on that.

[0552] The "means for generating feedback content" is a function that creates specific feedback appropriate for subordinates based on the analyzed data.

[0553] The "means for transmitting the generated feedback content" is a function for transmitting the feedback content to the subordinate terminal at an appropriate timing.

[0554] The "means for storing in a queue" is a technique for temporarily storing the generated feedback content and managing it so that it can be sent at a specified timing.

[0555] A "key phrase" is a set of short sentences or words that indicate particularly important parts of the feedback information.

[0556] A "generative AI model" is an artificial intelligence algorithm used to automatically generate feedback content.

[0557] A "natural language processing engine" is a technology for analyzing text data and extracting meaning and key phrases.

[0558] An "emotion engine" is a technology that analyzes emotions from text and voice and adjusts the feedback content based on that information.

[0559] The "user interface" is the part of the system that provides the screen and operation methods for subordinates to view the feedback content.

[0560] This invention is a system that uses AI and emotion recognition technology to provide effective and safe feedback from superiors to subordinates. This system consists of three main components: a superior terminal, a server, and a subordinate terminal. By combining these components with an emotion engine, the system can dynamically adjust the feedback content based on the user's emotions.

[0561] Operations on the boss's terminal

[0562] A supervisor uses a device with dedicated software installed to enter feedback information about a subordinate. The supervisor accesses the feedback entry screen, selects the subordinate's name, and enters the feedback content in the text box. For example, the supervisor can enter, "Your comments in the recent meeting were accurate, but I would like you to speak up more." When the supervisor clicks the "Send" button, the feedback information is sent from the terminal to the server. During this process, the emotion engine recognizes the emotion the supervisor was feeling when entering the feedback and modifies the tone and expression of the feedback content accordingly. For example, if the emotion engine recognizes the supervisor's positive emotion, it will modify the feedback to, "Your comments in the recent meeting were very accurate. Please speak up more."

[0563] Processing on the server

[0564] The server receives feedback information from the supervisor's device. The received information is stored in a database such as MySQL. It is then passed to a natural language processing engine (e.g., SpaCy). The natural language processing engine analyzes the feedback content and extracts important key phrases such as "quiet but accurate."

[0565] Next, an AI model (e.g., GPT-4) generates specific feedback content based on the analysis results. During this process, an emotion engine (e.g., Affectiva) checks whether the generated feedback content is appropriate for the subordinate and modifies it if necessary. For example, the generated feedback content could be, "Try to share more ideas with confidence."

[0566] The generated feedback content is stored in a queue along with the appropriate timing. For example, if it is determined that the subordinate would best receive the feedback when they arrive at work in the morning, the server will schedule the feedback to be sent to the subordinate's device at that time.

[0567] Operations on subordinate devices

[0568] When a subordinate's device receives feedback from the server, the content is immediately saved in internal memory (for example, an SQLite database). At the appropriate time, the feedback content is displayed to the subordinate through the user interface. During this process, the emotion engine recognizes the subordinate's emotions and modifies the follow-up content depending on how the feedback was received. For example, if a subordinate reacts positively to the feedback displayed at the start of work in the morning, "Try to share more ideas with confidence," the follow-up message will be "We look forward to your opinion."

[0569] Examples of prompts for generative AI models

[0570] "Use this feedback, 'You don't say much, but you get it. I wish you'd be more confident and share your ideas,' to generate more positive feedback that's appropriate for your employee."

[0571] This system reduces the risk of a supervisor giving direct feedback to a subordinate and provides a mechanism for subordinates to receive feedback that leads to growth at an appropriate and effective time. Feedback information entered from the supervisor's device is sent to a server, where it is analyzed and feedback is generated using an AI model, after which the emotion engine is checked and corrected. This information is then sent to the subordinate's device at the optimal time, facilitating smooth communication between the supervisor and subordinate and promoting the subordinate's growth. This system contributes to improving the quality of feedback in companies and organizations.

[0572] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0573] Step 1:

[0574] The user launches the dedicated application and accesses the feedback input screen. After selecting the subordinate's name, they enter their feedback in the text box. Once they've finished entering their feedback, they click the "Send" button. The supervisor's device passes this input to an emotion engine, which analyzes the content while recognizing the supervisor's emotions. As a result, the tone and expression of the feedback are adjusted.

[0575] Input: Feedback entered by the manager (e.g., "Your comments in recent meetings were accurate, but I'd like you to say more.")

[0576] Output: Corrected feedback (e.g., "You were very accurate in your recent meeting. Please try speaking up more.")

[0577] Step 2:

[0578] The device sends the corrected feedback to the server, which receives the data and stores it in a database. A relational database such as MySQL is used to store the feedback data.

[0579] Input: Corrected feedback

[0580] Output: Feedback information stored in a database

[0581] Step 3:

[0582] The server retrieves the feedback information from the database and passes it to a natural language processing engine (e.g., SpaCy) for analysis. The engine analyzes the feedback content and extracts important key phrases. For example, the key phrase extracted is "quiet but accurate."

[0583] Input: Feedback information stored in the database

[0584] Output: Extracted key phrases (e.g., "Small but precise")

[0585] Step 4:

[0586] The server then passes the extracted key phrases to a generative AI model (e.g., GPT-4) as prompts to generate specific feedback. The generated feedback is then checked by an emotion engine and corrected if necessary.

[0587] Input: Extracted key phrases

[0588] Output: Generated and revised feedback (e.g., "Try to be more confident and share more ideas")

[0589] Step 5:

[0590] The server stores the generated and modified feedback in a queue and schedules appropriate times for sending it, for example, when subordinates arrive at work in the morning.

[0591] Input: Generated and revised feedback

[0592] Output: Queued feedback

[0593] Step 6:

[0594] The subordinate's device receives the feedback content at the specified time. The received content is immediately saved in the internal memory (SQLite database) and displayed on the user interface at the appropriate time. When the subordinate confirms the feedback, the emotion engine analyzes the subordinate's emotions and performs adaptive follow-up.

[0595] Input: Feedback sent from the queue

[0596] Output: Feedback displayed on the subordinate's device, along with any necessary follow-up (e.g., "I look forward to hearing your opinion.")

[0597] The above is the specific processing flow of this system. This system effectively supports communication between superiors and subordinates and promotes the growth of subordinates.

[0598] (Application example 2)

[0599] 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."

[0600] When using robots in factories, it is important for managers to provide appropriate feedback to robots. However, conventional systems do not accurately reflect the manager's emotions and intentions, making it difficult to appropriately improve the robot's work efficiency and performance. Furthermore, there is a lack of mechanisms for the robot to respond appropriately to the feedback it receives, making it difficult to optimize work efficiency. Furthermore, continuous improvement is hindered by insufficient follow-up based on how the feedback is received.

[0601] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving feedback information input from a superior, means for analyzing the received feedback information, and means for generating feedback content based on the analysis results. This makes it possible to modify the tone and expression of the feedback using an emotion recognition engine. In addition, by including means for sending the feedback content stored in the queue to a subordinate terminal at a determined timing, analyzing the subordinate's emotions in response to the feedback received by the subordinate terminal, and modifying the follow-up content, it becomes possible for the robot to adjust its work efficiency and performance based on the feedback content received. This provides a system in which the manager's intentions are accurately reflected, the robot's work efficiency is improved, and continuous improvement is achieved.

[0602] "Feedback information entered by a superior" refers to evaluations, comments, and advice entered by a manager in the factory based on the robot's work status.

[0603] An "emotion recognition engine" is a technology that analyzes emotions from input text or voice and modifies the tone and expression of information based on those emotions.

[0604] "Feedback content generated based on the analysis results" refers to information that has been reconstructed as appropriate feedback content based on the results of analysis using a natural language processing engine.

[0605] A "subordinate terminal" is a device for receiving and displaying feedback content, and in this case refers to a robot that performs work in a factory.

[0606] A "natural language processing engine" is an algorithm or process that analyzes input text data and understands its content and meaning.

[0607] A "queue" is a data structure for temporarily storing information such as feedback content and transmission timing.

[0608] "Follow-up" refers to ongoing confirmation and advice after the initial feedback, adjusted based on the subordinate's response.

[0609] "Means for adjusting work efficiency and performance" refers to methods and mechanisms by which a robot receives feedback and improves and optimizes its own movements and the way it carries out its work.

[0610] This invention is specifically implemented as a feedback system for robot work in a factory. The system mainly consists of a supervisor terminal, a server, and subordinate terminals (factory work robots).

[0611] Overall system configuration

[0612] Supervisor's terminal: A supervisor uses a smartphone or other device to input feedback information based on the robot's work status. The supervisor's terminal is equipped with an emotion recognition engine that analyzes the emotions expressed during input and includes a function to modify the tone and expression of the feedback.

[0613] Server: Receives feedback information and stores it in a database. Furthermore, it analyzes the data using a natural language processing engine and generates feedback content based on the analysis results. The generated feedback content is corrected to an appropriate tone using an emotion recognition engine and stored in a queue based on the appropriate sending timing. The server uses software such as Flask (web framework), TextBlob (natural language processing), and emotion_recognition (emotion recognition).

[0614] Subordinate terminal (factory robot): This terminal receives feedback from the server, and is played by the factory robot. The robot adjusts its work efficiency and performance based on the received feedback. The robot's reaction to the feedback (if it analyzes emotions) is also sent to the server, and appropriate follow-up is carried out.

[0615] Specific examples

[0616] Example of administrator input: An administrator enters feedback such as "Your work speed is a little slow."

[0617] Emotion recognition and correction: The emotion recognition engine analyzes the input feedback as having a "neutral" emotion and corrects it to "Please be careful to speed up your work."

[0618] Server processing: The feedback information sent to the server is analyzed by a natural language processing engine, which identifies the key phrase "speed" and generates and modifies appropriate improvement suggestions.

[0619] Robot response: The robot receives feedback and makes adjustments to improve its speed of work.

[0620] Prompt Sentence Examples

[0621] Example of feedback provided by the administrator:

[0622] Admin Feedback: I feel like I'm repeating myself

[0623] Expected output:

[0624] Think about your work efficiency and look for areas for improvement.

[0625] Hardware and software used

[0626] Hardware: Smartphone (supervisor's device), server (database and analysis processing), robots that work in the factory (subordinate devices).

[0627] Software: Flask (web framework for server), TextBlob (natural language processing), emotion_recognition (emotion recognition engine).

[0628] This system allows the manager's intentions to be accurately reflected in the robot, improving the robot's work efficiency and enabling continuous adaptation and improvement.

[0629] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0630] Step 1:

[0631] Feedback input on the boss's terminal:

[0632] A user (manager) uses a supervisor's device such as a smartphone to input textual feedback on the performance of a factory robot. This textual input is passed to an emotion recognition engine, which analyzes the tone and expression of the feedback and corrects it as necessary. The feedback text is given as input, and tone-corrected feedback text is generated as output.

[0633] Example: If a manager types "I'm a little slow at work," it will be corrected to "Please pay attention to speeding up your work."

[0634] Step 2:

[0635] Send feedback information:

[0636] The feedback text corrected on the supervisor's terminal is sent to the server. The corrected feedback text is used as input, and the text is transferred to the server as output.

[0637] Example: "Pay attention to speeding up your work" feedback is sent to the server.

[0638] Step 3:

[0639] Feedback analysis on the server:

[0640] The server passes the received feedback text to a natural language processing engine, which analyzes the text, extracts important key phrases, and reconstructs the feedback content. The received feedback text is used as input, and the analyzed feedback content is generated as output.

[0641] Example: Identifying "speed" as a key phrase and generating an appropriate improvement suggestion such as "Try to improve your work speed."

[0642] Step 4:

[0643] Sentiment check and correction of generated feedback:

[0644] The server-generated feedback content is checked by an emotion recognition engine and the expressions are corrected if necessary. The reconstructed feedback content is used as input and the final feedback text is generated as output.

[0645] Example: "Please try to improve your work speed" is corrected to "Please try."

[0646] Step 5:

[0647] Queued feedback:

[0648] The server stores the final feedback text and send timing in a queue. The revised feedback text and send timing are used as input to generate a data entry that is stored in the queue as output.

[0649] Example: The feedback "Please try harder" is queued to be sent at 9am the next morning.

[0650] Step 6:

[0651] Send feedback from a queue:

[0652] Based on the determined timing, the feedback content is sent from the queue to the subordinate device (robot). The data entries stored in the queue are used as input, and the feedback that is sent to the robot as output is generated.

[0653] Example: The robot receives feedback saying "Please try harder" at 9am the next morning.

[0654] Step 7:

[0655] Receiving and acting on feedback in the robot:

[0656] The subordinate device (robot) stores the received feedback in its internal memory and adjusts its work efficiency and performance based on the feedback. The received feedback is used as input, and the robot's behavior is adjusted as output.

[0657] Example: A robot receives feedback saying "try harder" and adjusts its speed.

[0658] Step 8:

[0659] Analysis of the robot's response to feedback:

[0660] The robot responds to the feedback and its reaction (e.g., improved work speed) is sent to the server. The server analyzes this reaction and generates or modifies follow-up feedback as needed. The robot's response data is used as input, and the next feedback content is generated as output.

[0661] Example: A robot increases its work speed and sends the results to a server, which generates follow-up feedback such as "keep up the good work."

[0662] 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.

[0663] 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.

[0664] 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.

[0665] [Third embodiment]

[0666] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0667] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0668] 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).

[0669] 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.

[0670] 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.

[0671] 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).

[0672] 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.

[0673] 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.

[0674] 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.

[0675] 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.

[0676] 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.

[0677] 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."

[0678] This invention is a system that uses AI technology to provide effective and safe feedback from superiors to subordinates. This system consists of three main components: the superior's terminal, the server, and the subordinate's terminal. Below, we will explain the specific operating procedures for each component and the operation of the entire system.

[0679] Operations on the boss's terminal

[0680] A supervisor enters feedback information about a subordinate using a terminal with a dedicated application installed. The supervisor accesses the feedback input screen, selects the subordinate's name, and enters the feedback content in the text box. When the supervisor clicks the "Send" button, the feedback information is sent to the server. As a concrete example, let's say the supervisor enters, "Your comments in the recent meeting were accurate, but I would like you to say more."

[0681] Processing on the server

[0682] The server receives feedback information from the manager's device. The received information is stored in a database and then passed to a natural language processing engine. The engine analyzes the feedback content and extracts important key phrases such as "quiet but accurate." The AI ​​model then generates specific feedback content based on the analysis results. An example of feedback in this case would be "Try to share more ideas with confidence."

[0683] The generated feedback content is stored in a queue along with the appropriate timing. For example, if it is determined that the subordinate would best receive the feedback when they arrive at work in the morning, the server will schedule the feedback to be sent to the subordinate's device at that time.

[0684] Operations on subordinate devices

[0685] When a subordinate's device receives feedback from the server, the content is immediately saved in its internal memory. At the appropriate time, the feedback content is displayed to the subordinate through the user interface. For example, when a subordinate starts work in the morning, they will see the feedback displayed as "Try to share more ideas with confidence."

[0686] Overall system operation

[0687] This system reduces the risk of a supervisor giving direct feedback to a subordinate and provides a mechanism for subordinates to receive feedback that will lead to their growth at an appropriate and effective time. Feedback information entered from the supervisor's device is sent to a server, where it is analyzed and feedback generated by an AI model is sent to the subordinate's device at the optimal time. As a result, communication between the supervisor and subordinate becomes smoother, promoting the subordinate's growth.

[0688] This is the overall system configuration for implementing the present invention.

[0689] The processing flow will be explained below.

[0690] Step 1:

[0691] The supervisor launches the dedicated app or web app. The supervisor selects the "Enter Feedback" option from the main menu, and the feedback entry screen appears.

[0692] Step 2:

[0693] The manager selects the subordinate's name from the drop-down menu, then enters the feedback in the text box (e.g., "Your comments in recent meetings were accurate, but I'd like to see more of you."), and clicks the "Send" button.

[0694] Step 3:

[0695] The boss's device catches the click event of the send button, converts the feedback content and the subordinate's identification information into JSON format, and sends an HTTP POST request to the server's API endpoint.

[0696] Step 4:

[0697] The server receives an HTTP POST request at the specified API endpoint, parses the received JSON data, and extracts the feedback content and subordinate's identification information.

[0698] Step 5:

[0699] The server passes the extracted feedback to a natural language processing (NLP) engine, which analyzes the meaning of the feedback and extracts key information (e.g., "Small but accurate").

[0700] Step 6:

[0701] The server inputs the analysis results into the AI ​​model, which then generates optimal feedback for the subordinate based on the analysis results (e.g., "Try to share more ideas with confidence").

[0702] Step 7:

[0703] The server compares the generated feedback content with the subordinate's timetable database to determine the optimal transmission timing, and stores the determined feedback content and transmission timing in a queue.

[0704] Step 8:

[0705] Based on the determined timing, the server retrieves the feedback content from the queue and sends an HTTP POST request to the subordinate terminal.

[0706] Step 9:

[0707] The subordinate device receives an HTTP POST request from the server, analyzes the received JSON data, and extracts the feedback content.

[0708] Step 10:

[0709] The subordinate's device uses an appropriate user interface to display the feedback content on the screen. The subordinate checks the displayed feedback and considers possible actions.

[0710] Example 1

[0711] 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."

[0712] Typically, when a manager provides direct feedback to a subordinate, the timing and content are often inappropriate, which results in the subordinate's growth being unsatisfactory. There is also a risk that the manager's feedback may be inappropriate or the subordinate may feel uncomfortable due to poor choice of words. There is a need for a system that can solve these issues and provide feedback to subordinates more effectively and safely.

[0713] 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.

[0714] In this invention, the server includes means for receiving feedback information input from a superior, means for saving the received feedback information in a storage device, means for analyzing the saved feedback information using natural language processing technology, means for generating feedback content based on the analysis result using a generative AI model, and means for sending the generated feedback content to a subordinate at an appropriate time. This makes it possible to analyze feedback from a superior in an appropriate manner, generate optimal feedback content, and provide it to a subordinate at an appropriate time.

[0715] A "supervisor" is an individual in an organization who is in a position to give direct instructions and manage subordinates.

[0716] A "subordinate" is an individual in an organization who is in a position to receive instructions and management from a superior.

[0717] "Feedback information" refers to the content of evaluations, comments, advice, etc. that a superior provides to a subordinate.

[0718] The "receiving means" is a function for taking the feedback information sent from the superior terminal into the server.

[0719] The "storing means" is a function for storing received feedback information in a database or storage device.

[0720] "Natural language processing technology" is a technology for analyzing text data in natural language and converting it into a form that humans can understand.

[0721] "Means of analysis" refers to the function of understanding and analyzing feedback information using natural language processing technology.

[0722] A "generative AI model" is an artificial intelligence model that has been trained in advance using large amounts of data and generates feedback content based on input information.

[0723] "Means for generation" refers to a function for creating feedback content using a generative AI model based on the analysis results.

[0724] The "transmitting means" is a function for sending the generated feedback content to the subordinate terminal.

[0725] The "means for storing in a queue" is a function for temporarily storing the generated feedback content so that it can be sent at an appropriate time.

[0726] "Transmission timing" refers to the optimal time and conditions for transmitting the feedback content to the subordinate terminal.

[0727] "Subordinate terminal" refers to a terminal device used by a subordinate to receive and display feedback.

[0728] MODE FOR CARRYING OUT THE INVENTION

[0729] This invention is a system that uses AI technology to provide feedback from superiors to subordinates effectively and safely. This system consists of three main components: a superior terminal, a server, and a subordinate terminal. The specific operating procedures and the operation of the entire system are explained in detail below.

[0730] Operations on the boss's terminal

[0731] The supervisor uses a device with a dedicated application installed. This device can be a PC or smartphone. To enter feedback information, the supervisor accesses the feedback input screen of the dedicated application, selects the subordinate's name, and enters the feedback content in the text box. For example, the supervisor might enter, "Your comments in the recent meeting were accurate, but I would like you to say more." Once this input is complete, the supervisor clicks the "Send" button to transfer the feedback information to the server.

[0732] Processing on the server

[0733] The server receives the feedback information sent from the supervisor's device. The received feedback information is first stored in a database (e.g., MySQL). The feedback content is then analyzed using a natural language processing engine (e.g., spaCy, NLTK). Through the analysis, important key phrases such as "You speak little, but accurately" are extracted. The server then passes the extracted key phrases to a generative AI model (e.g., GPT-3, BERT) to generate specific feedback content. For example, feedback such as "Try to share more ideas with confidence" is generated.

[0734] The generated feedback is scheduled with the appropriate timing for the subordinate to receive it. The server determines the optimal timing for sending the feedback (e.g., when the subordinate arrives at work in the morning) based on the subordinate's behavioral patterns and preferences, and stores the feedback in a queue.

[0735] Operations on subordinate devices

[0736] The subordinate's device receives the feedback sent from the server. The received feedback is stored in the internal memory and displayed to the subordinate through the user interface at the appropriate time. For example, when the subordinate starts work in the morning, the feedback "Try to share more ideas with confidence" is displayed.

[0737] Examples and prompts

[0738] For example, let's say your boss writes, "Your contributions to the recent project have been great, but you could do better if you paid more attention to the details." This feedback information is parsed and generated as follows:

[0739] Analysis results of the natural language processing engine:

[0740] "Great contributions but attention to detail"

[0741] Feedback generated by the generative AI model:

[0742] "The results are excellent, but with more attention to detail the results would be even better."

[0743] Example prompt for a generative AI model:

[0744] Prompt: Your contribution to your recent project has been great, but it could be even better with a little more attention to detail.

[0745] Output: Good results, but more attention to detail would produce even better results.

[0746] This system reduces the risk involved when a manager gives direct feedback to a subordinate and enables effective feedback to be given at the right time, resulting in smoother communication between managers and subordinates and promoting the growth of subordinates.

[0747] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0748] Step 1: Enter and send feedback on the supervisor's device

[0749] Input: Launch the dedicated application installed on the supervisor's device and access the feedback input screen.

[0750] How it works: A manager selects a subordinate's name and enters specific feedback in the text box.

[0751] Output: When the manager clicks the "Send" button, the feedback information is converted into a data packet and sent to the server.

[0752] Step 2: Receiving and storing feedback information on the server

[0753] Input: Receives data packets sent from the boss's terminal.

[0754] Operation: The server parses the received data packets and extracts the feedback information.

[0755] Output: Save the feedback information to a database (e.g. MySQL).

[0756] Step 3: Analysis using natural language processing on the server

[0757] Input: Feedback information stored in the database.

[0758] How it works: The server passes the feedback information to a natural language processing engine (e.g. spaCy, NLTK) for content analysis.

[0759] A natural language processing engine extracts important key phrases from the feedback.

[0760] Output: As a result of the analysis, we obtain key phrases such as "few comments but accurate."

[0761] Step 4: Feedback generation by the AI ​​model on the server

[0762] Input: Analysis results (important key phrases) obtained from the natural language processing engine.

[0763] How it works: The server inputs the analysis results into a generative AI model (e.g., GPT-3, BERT).

[0764] A generative AI model generates specific feedback content based on key phrases.

[0765] Output: For example, you get feedback such as "Try to share more ideas with confidence."

[0766] Step 5: Registering the schedule on the server

[0767] Input: The specific feedback generated.

[0768] How it works: The server determines the best time to send feedback (e.g., when a subordinate arrives at work).

[0769] Queue feedback and when to send it.

[0770] Output: Feedback stored along with the timing of sending.

[0771] Step 6: Receive and display feedback on subordinate devices

[0772] Input: Feedback information sent by the server.

[0773] Operation: The subordinate device receives the feedback information and stores it in its internal memory.

[0774] Providing feedback through the user interface at the appropriate time.

[0775] Output: For example, a message is displayed to the subordinate saying, "Try to share more ideas with confidence."

[0776] This enables a series of steps to be taken, in which feedback information entered from the superior's device is analyzed and generated on the server, and then sent to the subordinate's device at the optimal timing.

[0777] (Application example 1)

[0778] 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."

[0779] In modern factories, real-time feedback is necessary to efficiently improve the behavior and performance of robots. However, when supervisors provide feedback directly to factory robots, it is difficult to instruct effective actions at the appropriate time. Furthermore, advanced technology is required to accurately analyze the robot's operating status and provide appropriate improvement instructions. A means to effectively solve these issues is needed.

[0780] 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.

[0781] In this invention, the server includes means for receiving feedback information input from a superior, means for analyzing the received feedback information, means for generating feedback content based on the analysis results, and means for transmitting the generated feedback content to the device at an appropriate time, thereby enabling the superior to provide timely and effective feedback to the factory robot and improving the robot's operation and performance.

[0782] "Superior" refers to the person responsible for providing feedback to the system.

[0783] "Feedback information" refers to the content of evaluations and advice for the subject, such as text or audio entered by superiors.

[0784] "Means for receiving" refers to the function that allows the system to incorporate feedback information provided by superiors.

[0785] "Means for analysis" refers to the function of analyzing received feedback information using a natural language processing engine or the like and extracting meaning.

[0786] The "means for generating feedback content" refers to a function for generating specific and appropriate feedback messages based on the analysis results.

[0787] "Device" refers to a robot or other automated device that receives feedback.

[0788] "Appropriate timing" refers to the time and situation in which feedback should be most effectively reflected in the device.

[0789] "Means for transmitting" refers to the network and communication technologies for transmitting the generated feedback to the device.

[0790] The "means for storing in a queue" refers to a function for temporarily storing the generated feedback content until the appropriate time to send it.

[0791] "Determined timing" refers to the time and conditions for executing feedback based on analysis and external conditions.

[0792] A "natural language processing engine" refers to artificial intelligence technology that analyzes feedback information and extracts important information and key phrases.

[0793] "Generating based on the analysis results" refers to the process of constructing specific feedback content based on the analyzed information.

[0794] This invention is a system that provides timely and effective feedback from a superior to equipment (such as a factory robot). The system consists of three main components: a superior terminal, a server, and an equipment terminal.

[0795] Operation on the host terminal

[0796] The supervisor installs a dedicated application on the terminal and inputs feedback information for the device. For example, if the supervisor inputs feedback such as "Please increase the operating speed," the information is sent to the server.

[0797] Processing on the server

[0798] When the server receives feedback information from the host terminal, the received information is first stored in a database. The feedback content is then analyzed using a natural language processing engine (such as BERT). As a result, key phrases are extracted, and "Please increase the movement speed" is recognized as a specific improvement instruction. Next, the AI ​​model generates the feedback content based on the analysis results. As a specific example, the AI ​​model generates the instruction "Please increase the robot's movement speed by 20%."

[0799] The generated feedback content is stored in a queue along with the optimal transmission timing, for example, the time when the device terminal can optimally receive the feedback is determined, and the feedback is scheduled to be transmitted at that time.

[0800] Operation on the device terminal

[0801] When a device terminal receives feedback from the server, the content is immediately saved in its internal memory. At the appropriate time, the feedback content is reflected in the device's control system. For example, if a device terminal receives an instruction such as "Increase the robot's movement speed by 20%, it will adjust the movement speed accordingly.

[0802] Overall system operation

[0803] The feedback information entered by the supervisor is analyzed on the server, and specific feedback content is generated by an AI model and sent to the equipment terminal at the optimal timing. This system enables the supervisor to provide timely and effective feedback to factory robots. An example of an input prompt sentence is shown below as a concrete example.

[0804] Prompt Sentence Examples

[0805] "I would like to increase the operating speed of Robot X. Its current operating speed is slow, which is reducing the efficiency of the entire production line."

[0806] Based on such prompts, the AI ​​generates specific feedback such as "Please increase Robot X's movement speed by 20%," and the server sends the instructions to the device terminal at the appropriate time.

[0807] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0808] Step 1:

[0809] The superior inputs feedback information from the terminal. As an example, "Please increase the speed of operation" is entered into the text box. The input data is sent to the server by clicking the "Send" button. The input is text data, and the output is feedback information sent to the server.

[0810] Step 2:

[0811] The server stores the feedback information received from the host terminal in a database. Storing the feedback information in a database ensures that the feedback information is managed continuously and safely. The input is the feedback information received from the terminal, and the output is the feedback information stored in the database.

[0812] Step 3:

[0813] The server extracts feedback information from the database and analyzes it using a natural language processing engine (NLP model). Important key phrases are extracted through the analysis. For example, the key phrases "movement speed" and "please increase it" are obtained. The input is the feedback information extracted from the database, and the output is the analysis results in the form of key phrases.

[0814] Step 4:

[0815] Based on the analysis results, the server uses a generative AI model to generate specific feedback. For example, a specific instruction such as "Increase the robot's movement speed by 20%" is generated. The input is the analysis result obtained through natural language processing, and the output is the specific feedback generated.

[0816] Step 5:

[0817] The server stores the generated feedback in a queue along with the appropriate transmission timing, for example, setting it to be sent at the start of the next production shift. The input is the generated feedback, and the output is the feedback stored in the queue and the transmission timing.

[0818] Step 6:

[0819] The server sends the feedback stored in the queue to the equipment terminal based on the timing it determines, for example, when the next shift starts. The input is the feedback stored in the queue and its sending timing, and the output is the feedback sent to the equipment terminal.

[0820] Step 7:

[0821] The device terminal stores the feedback received from the server in its internal memory. The stored content is reflected in the device's control system at the appropriate time. The input is the feedback received from the server, and the output is the feedback stored in the device's internal memory.

[0822] Step 8:

[0823] The device executes operations based on the feedback stored in its internal memory. For example, an instruction to "increase the robot's movement speed by 20%" is reflected in the actual movement control. The input is the feedback stored in the internal memory, and the output is the actual robot movement.

[0824] 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.

[0825] This invention is a system that uses AI and emotion recognition technology to provide effective and safe feedback from superiors to subordinates. This system consists of three main components: a superior terminal, a server, and a subordinate terminal. By combining these with an emotion engine, the system can dynamically adjust the feedback content based on the user's emotions.

[0826] Operations on the boss's terminal

[0827] A supervisor enters feedback information about a subordinate using a device with a dedicated application installed. The supervisor accesses the feedback input screen, selects the subordinate's name, and enters the feedback content in the text box. When the supervisor clicks the "Send" button, the feedback information is sent to the server. Furthermore, during this process, the emotion engine recognizes the emotion the supervisor was feeling when entering the feedback and modifies the tone and expression of the feedback content as appropriate. For example, if a supervisor enters "Your comments in the recent meeting were accurate, but I would like you to say more," and the emotion engine recognizes the supervisor's positive emotion, it will modify the feedback to read, "Your comments in the recent meeting were very accurate. Please try to speak more."

[0828] Processing on the server

[0829] The server receives feedback information from the superior's device. The received information is stored in a database and then passed to a natural language processing engine. The engine analyzes the feedback content and extracts important key phrases such as "You speak little, but accurately." The AI ​​model then generates specific feedback content based on the analysis results. During this process, the emotion engine checks whether the generated feedback content is appropriate for the subordinate and modifies it if necessary. The generated feedback content is "Try to share more ideas with confidence."

[0830] The generated feedback content is stored in a queue along with the appropriate timing. For example, if it is determined that the subordinate would best receive the feedback when they arrive at work in the morning, the server will schedule the feedback to be sent to the subordinate's device at that time.

[0831] Operations on subordinate devices

[0832] When a subordinate's device receives feedback from the server, the content is immediately saved in its internal memory and displayed to the subordinate through the user interface at the appropriate time. During this process, the subordinate's emotions are recognized by the emotion engine, and the follow-up content is modified depending on how the feedback was received. For example, if a subordinate reacts positively to the feedback displayed at the start of work in the morning, "Try to share more ideas with confidence," the follow-up message will be, "We look forward to hearing your opinion."

[0833] Overall system operation

[0834] This system reduces the risk of a supervisor giving direct feedback to a subordinate, and provides a mechanism for subordinates to receive feedback that will lead to their growth at an appropriate and effective time. Feedback information entered from the supervisor's device is sent to a server, where it is analyzed and feedback is generated using an AI model, after which the emotion engine is checked and corrected. It is then sent to the subordinate's device at the optimal time. This results in smoother communication between the supervisor and subordinate, promoting the subordinate's growth.

[0835] This is the overall system configuration for implementing the present invention.

[0836] The processing flow will be explained below.

[0837] Step 1:

[0838] The supervisor launches the dedicated app or web app. The supervisor selects the "Enter Feedback" option from the main menu, and the feedback entry screen appears.

[0839] Step 2:

[0840] The manager selects the subordinate's name from a drop-down menu, then enters feedback in the text box (e.g., "Your comments in recent meetings were accurate, but I'd like to see more of you.").

[0841] Step 3:

[0842] The boss's device uses an emotion engine to recognize the boss's emotions as they are being input. The emotion engine evaluates the boss's emotional state (e.g., positive, negative) and modifies the feedback content as necessary. For example, if the boss is inputting with a positive emotion, the feedback content will be modified to "Your comments in the recent meeting were very accurate. Please try to speak up more."

[0843] Step 4:

[0844] After the supervisor checks the revised feedback content, he / she clicks the "Send" button. The supervisor's device catches the click event of the Send button, converts the feedback content and the subordinate's identification information into JSON format, and sends an HTTP POST request to the server's API endpoint.

[0845] Step 5:

[0846] The server receives an HTTP POST request at the specified API endpoint, parses the received JSON data, and extracts the feedback content and subordinate's identification information.

[0847] Step 6:

[0848] The server passes the extracted feedback to a natural language processing (NLP) engine, which analyzes the meaning of the feedback and extracts key information (e.g., "Small but accurate").

[0849] Step 7:

[0850] The server inputs the analysis results into the AI ​​model, which then generates optimal feedback for the subordinate based on the analysis results (e.g., "Try to share more ideas with confidence").

[0851] Step 8:

[0852] The generated feedback is passed to the emotion engine, which evaluates whether the tone and expression of the feedback are appropriate and makes corrections as necessary. For example, the tone may be changed to a gentler tone to prevent the subordinate from feeling overly stressed.

[0853] Step 9:

[0854] The server stores the generated feedback content in a queue along with the appropriate delivery timing. The queue contains feedback content to be sent and its delivery timing.

[0855] Step 10:

[0856] Based on the determined timing, the server retrieves the feedback content from the queue and sends an HTTP POST request to the subordinate terminal.

[0857] Step 11:

[0858] The subordinate device receives an HTTP POST request from the server, analyzes the received JSON data, and extracts the feedback content.

[0859] Step 12:

[0860] The subordinate's device uses an appropriate user interface to display the feedback content on the screen. The subordinate then checks the displayed feedback.

[0861] Step 13:

[0862] The subordinate's device recognizes the subordinate's reaction to the feedback using an emotion engine. The emotion engine evaluates the subordinate's emotional state and provides follow-up feedback as needed. For example, if the subordinate reacts positively, a further encouraging message is displayed.

[0863] Example 2

[0864] 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."

[0865] When a manager gives feedback to a subordinate, it is often necessary to convey emotion and express it appropriately. However, inconsistencies in emotion or timing can sometimes result in feedback having the opposite effect. Furthermore, if the feedback is too formal and lacks specificity, it is difficult to promote the subordinate's growth. Conventional systems often fail to adequately resolve these issues.

[0866] 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.

[0867] In this invention, the server includes means for receiving feedback information input from a superior, means for analyzing the received feedback information, recognizing emotions, and modifying the tone and expression of the feedback content, means for generating feedback content based on the analysis results, and means for transmitting the generated feedback content to a subordinate at an appropriate timing. This enables appropriate feedback according to the superior's emotions and timing, and promotes the growth of the subordinate.

[0868] "Feedback information" refers to information that includes evaluations, comments, advice, etc., given by superiors to subordinates.

[0869] The "receiving means" is a function that allows the server to receive feedback information sent from the superior terminal.

[0870] "Means for analysis" refers to the function for processing and analyzing received feedback information and extracting necessary key phrases and emotions.

[0871] "Means of recognizing emotions" refers to a technology that analyzes the emotional aspects of the feedback entered by a supervisor and makes adjustments based on that.

[0872] The "means for generating feedback content" is a function that creates specific feedback appropriate for subordinates based on the analyzed data.

[0873] The "means for transmitting the generated feedback content" is a function for transmitting the feedback content to the subordinate terminal at an appropriate timing.

[0874] The "means for storing in a queue" is a technique for temporarily storing the generated feedback content and managing it so that it can be sent at a specified timing.

[0875] A "key phrase" is a set of short sentences or words that indicate particularly important parts of the feedback information.

[0876] A "generative AI model" is an artificial intelligence algorithm used to automatically generate feedback content.

[0877] A "natural language processing engine" is a technology for analyzing text data and extracting meaning and key phrases.

[0878] An "emotion engine" is a technology that analyzes emotions from text and voice and adjusts the feedback content based on that information.

[0879] The "user interface" is the part of the system that provides the screen and operation methods for subordinates to view the feedback content.

[0880] This invention is a system that uses AI and emotion recognition technology to provide effective and safe feedback from superiors to subordinates. This system consists of three main components: a superior terminal, a server, and a subordinate terminal. By combining these components with an emotion engine, the system can dynamically adjust the feedback content based on the user's emotions.

[0881] Operations on the boss's terminal

[0882] A supervisor uses a device with dedicated software installed to enter feedback information about a subordinate. The supervisor accesses the feedback entry screen, selects the subordinate's name, and enters the feedback content in the text box. For example, the supervisor can enter, "Your comments in the recent meeting were accurate, but I would like you to speak up more." When the supervisor clicks the "Send" button, the feedback information is sent from the terminal to the server. During this process, the emotion engine recognizes the emotion the supervisor was feeling when entering the feedback and modifies the tone and expression of the feedback content accordingly. For example, if the emotion engine recognizes the supervisor's positive emotion, it will modify the feedback to, "Your comments in the recent meeting were very accurate. Please speak up more."

[0883] Processing on the server

[0884] The server receives feedback information from the supervisor's device. The received information is stored in a database such as MySQL. It is then passed to a natural language processing engine (e.g., SpaCy). The natural language processing engine analyzes the feedback content and extracts important key phrases such as "quiet but accurate."

[0885] Next, an AI model (e.g., GPT-4) generates specific feedback content based on the analysis results. During this process, an emotion engine (e.g., Affectiva) checks whether the generated feedback content is appropriate for the subordinate and modifies it if necessary. For example, the generated feedback content could be, "Try to share more ideas with confidence."

[0886] The generated feedback content is stored in a queue along with the appropriate timing. For example, if it is determined that the subordinate would best receive the feedback when they arrive at work in the morning, the server will schedule the feedback to be sent to the subordinate's device at that time.

[0887] Operations on subordinate devices

[0888] When a subordinate's device receives feedback from the server, the content is immediately saved in internal memory (for example, an SQLite database). At the appropriate time, the feedback content is displayed to the subordinate through the user interface. During this process, the emotion engine recognizes the subordinate's emotions and modifies the follow-up content depending on how the feedback was received. For example, if a subordinate reacts positively to the feedback displayed at the start of work in the morning, "Try to share more ideas with confidence," the follow-up message will be "We look forward to your opinion."

[0889] Examples of prompts for generative AI models

[0890] "Use this feedback, 'You don't say much, but you get it. I wish you'd be more confident and share your ideas,' to generate more positive feedback that's appropriate for your employee."

[0891] This system reduces the risk of a supervisor giving direct feedback to a subordinate and provides a mechanism for subordinates to receive feedback that leads to growth at an appropriate and effective time. Feedback information entered from the supervisor's device is sent to a server, where it is analyzed and feedback is generated using an AI model, after which the emotion engine is checked and corrected. This information is then sent to the subordinate's device at the optimal time, facilitating smooth communication between the supervisor and subordinate and promoting the subordinate's growth. This system contributes to improving the quality of feedback in companies and organizations.

[0892] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0893] Step 1:

[0894] The user launches the dedicated application and accesses the feedback input screen. After selecting the subordinate's name, they enter their feedback in the text box. Once they've finished entering their feedback, they click the "Send" button. The supervisor's device passes this input to an emotion engine, which analyzes the content while recognizing the supervisor's emotions. As a result, the tone and expression of the feedback are adjusted.

[0895] Input: Feedback entered by the manager (e.g., "Your comments in recent meetings were accurate, but I'd like you to say more.")

[0896] Output: Corrected feedback (e.g., "You were very accurate in your recent meeting. Please try speaking up more.")

[0897] Step 2:

[0898] The device sends the corrected feedback to the server, which receives the data and stores it in a database. A relational database such as MySQL is used to store the feedback data.

[0899] Input: Corrected feedback

[0900] Output: Feedback information stored in a database

[0901] Step 3:

[0902] The server retrieves the feedback information from the database and passes it to a natural language processing engine (e.g., SpaCy) for analysis. The engine analyzes the feedback content and extracts important key phrases. For example, the key phrase extracted is "quiet but accurate."

[0903] Input: Feedback information stored in the database

[0904] Output: Extracted key phrases (e.g., "Small but precise")

[0905] Step 4:

[0906] The server then passes the extracted key phrases to a generative AI model (e.g., GPT-4) as prompts to generate specific feedback. The generated feedback is then checked by an emotion engine and corrected if necessary.

[0907] Input: Extracted key phrases

[0908] Output: Generated and revised feedback (e.g., "Try to be more confident and share more ideas")

[0909] Step 5:

[0910] The server stores the generated and modified feedback in a queue and schedules appropriate times for sending it, for example, when subordinates arrive at work in the morning.

[0911] Input: Generated and revised feedback

[0912] Output: Queued feedback

[0913] Step 6:

[0914] The subordinate's device receives the feedback content at the specified time. The received content is immediately saved in the internal memory (SQLite database) and displayed on the user interface at the appropriate time. When the subordinate confirms the feedback, the emotion engine analyzes the subordinate's emotions and performs adaptive follow-up.

[0915] Input: Feedback sent from the queue

[0916] Output: Feedback displayed on the subordinate's device, along with any necessary follow-up (e.g., "I look forward to hearing your opinion.")

[0917] The above is the specific processing flow of this system. This system effectively supports communication between superiors and subordinates and promotes the growth of subordinates.

[0918] (Application example 2)

[0919] 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."

[0920] When using robots in factories, it is important for managers to provide appropriate feedback to robots. However, conventional systems do not accurately reflect the manager's emotions and intentions, making it difficult to appropriately improve the robot's work efficiency and performance. Furthermore, there is a lack of mechanisms for the robot to respond appropriately to the feedback it receives, making it difficult to optimize work efficiency. Furthermore, continuous improvement is hindered by insufficient follow-up based on how the feedback is received.

[0921] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving feedback information input from a superior, means for analyzing the received feedback information, and means for generating feedback content based on the analysis results. This makes it possible to modify the tone and expression of the feedback using an emotion recognition engine. In addition, by including means for sending the feedback content stored in the queue to a subordinate terminal at a determined timing, analyzing the subordinate's emotions in response to the feedback received by the subordinate terminal, and modifying the follow-up content, it becomes possible for the robot to adjust its work efficiency and performance based on the feedback content received. This provides a system in which the manager's intentions are accurately reflected, the robot's work efficiency is improved, and continuous improvement is achieved.

[0922] "Feedback information entered by a superior" refers to evaluations, comments, and advice entered by a manager in the factory based on the robot's work status.

[0923] An "emotion recognition engine" is a technology that analyzes emotions from input text or voice and modifies the tone and expression of information based on those emotions.

[0924] "Feedback content generated based on the analysis results" refers to information that has been reconstructed as appropriate feedback content based on the results of analysis using a natural language processing engine.

[0925] A "subordinate terminal" is a device for receiving and displaying feedback content, and in this case refers to a robot that performs work in a factory.

[0926] A "natural language processing engine" is an algorithm or process that analyzes input text data and understands its content and meaning.

[0927] A "queue" is a data structure for temporarily storing information such as feedback content and transmission timing.

[0928] "Follow-up" refers to ongoing confirmation and advice after the initial feedback, adjusted based on the subordinate's response.

[0929] "Means for adjusting work efficiency and performance" refers to methods and mechanisms by which a robot receives feedback and improves and optimizes its own movements and the way it carries out its work.

[0930] This invention is specifically implemented as a feedback system for robot work in a factory. The system mainly consists of a supervisor terminal, a server, and subordinate terminals (factory work robots).

[0931] Overall system configuration

[0932] Supervisor's terminal: A supervisor uses a smartphone or other device to input feedback information based on the robot's work status. The supervisor's terminal is equipped with an emotion recognition engine that analyzes the emotions expressed during input and includes a function to modify the tone and expression of the feedback.

[0933] Server: Receives feedback information and stores it in a database. Furthermore, it analyzes the data using a natural language processing engine and generates feedback content based on the analysis results. The generated feedback content is corrected to an appropriate tone using an emotion recognition engine and stored in a queue based on the appropriate sending timing. The server uses software such as Flask (web framework), TextBlob (natural language processing), and emotion_recognition (emotion recognition).

[0934] Subordinate terminal (factory robot): This terminal receives feedback from the server, and is played by the factory robot. The robot adjusts its work efficiency and performance based on the received feedback. The robot's reaction to the feedback (if it analyzes emotions) is also sent to the server, and appropriate follow-up is carried out.

[0935] Specific examples

[0936] Example of administrator input: An administrator enters feedback such as "Your work speed is a little slow."

[0937] Emotion recognition and correction: The emotion recognition engine analyzes the input feedback as having a "neutral" emotion and corrects it to "Please be careful to speed up your work."

[0938] Server processing: The feedback information sent to the server is analyzed by a natural language processing engine, which identifies the key phrase "speed" and generates and modifies appropriate improvement suggestions.

[0939] Robot response: The robot receives feedback and makes adjustments to improve its speed of work.

[0940] Prompt Sentence Examples

[0941] Example of feedback provided by the administrator:

[0942] Admin Feedback: I feel like I'm repeating myself

[0943] Expected output:

[0944] Think about your work efficiency and look for areas for improvement.

[0945] Hardware and software used

[0946] Hardware: Smartphone (supervisor's device), server (database and analysis processing), robots that work in the factory (subordinate devices).

[0947] Software: Flask (web framework for server), TextBlob (natural language processing), emotion_recognition (emotion recognition engine).

[0948] This system allows the manager's intentions to be accurately reflected in the robot, improving the robot's work efficiency and enabling continuous adaptation and improvement.

[0949] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0950] Step 1:

[0951] Feedback input on the boss's terminal:

[0952] A user (manager) uses a supervisor's device such as a smartphone to input textual feedback on the performance of a factory robot. This textual input is passed to an emotion recognition engine, which analyzes the tone and expression of the feedback and corrects it as necessary. The feedback text is given as input, and tone-corrected feedback text is generated as output.

[0953] Example: If a manager types "I'm a little slow at work," it will be corrected to "Please pay attention to speeding up your work."

[0954] Step 2:

[0955] Send feedback information:

[0956] The feedback text corrected on the supervisor's terminal is sent to the server. The corrected feedback text is used as input, and the text is transferred to the server as output.

[0957] Example: "Pay attention to speeding up your work" feedback is sent to the server.

[0958] Step 3:

[0959] Feedback analysis on the server:

[0960] The server passes the received feedback text to a natural language processing engine, which analyzes the text, extracts important key phrases, and reconstructs the feedback content. The received feedback text is used as input, and the analyzed feedback content is generated as output.

[0961] Example: Identifying "speed" as a key phrase and generating an appropriate improvement suggestion such as "Try to improve your work speed."

[0962] Step 4:

[0963] Sentiment check and correction of generated feedback:

[0964] The server-generated feedback content is checked by an emotion recognition engine and the expressions are corrected if necessary. The reconstructed feedback content is used as input and the final feedback text is generated as output.

[0965] Example: "Please try to improve your work speed" is corrected to "Please try."

[0966] Step 5:

[0967] Queued feedback:

[0968] The server stores the final feedback text and send timing in a queue. The revised feedback text and send timing are used as input to generate a data entry that is stored in the queue as output.

[0969] Example: The feedback "Please try harder" is queued to be sent at 9am the next morning.

[0970] Step 6:

[0971] Send feedback from a queue:

[0972] Based on the determined timing, the feedback content is sent from the queue to the subordinate device (robot). The data entries stored in the queue are used as input, and the feedback that is sent to the robot as output is generated.

[0973] Example: The robot receives feedback saying "Please try harder" at 9am the next morning.

[0974] Step 7:

[0975] Receiving and acting on feedback in the robot:

[0976] The subordinate device (robot) stores the received feedback in its internal memory and adjusts its work efficiency and performance based on the feedback. The received feedback is used as input, and the robot's behavior is adjusted as output.

[0977] Example: A robot receives feedback saying "try harder" and adjusts its speed.

[0978] Step 8:

[0979] Analysis of the robot's response to feedback:

[0980] The robot responds to the feedback and its reaction (e.g., improved work speed) is sent to the server. The server analyzes this reaction and generates or modifies follow-up feedback as needed. The robot's response data is used as input, and the next feedback content is generated as output.

[0981] Example: A robot increases its work speed and sends the results to a server, which generates follow-up feedback such as "keep up the good work."

[0982] 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.

[0983] 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.

[0984] 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.

[0985] [Fourth embodiment]

[0986] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0987] 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.

[0988] 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).

[0989] 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.

[0990] 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.

[0991] 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).

[0992] 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.

[0993] 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.

[0994] 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.

[0995] 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.

[0996] 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.

[0997] 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.

[0998] 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."

[0999] This invention is a system that uses AI technology to provide effective and safe feedback from superiors to subordinates. This system consists of three main components: the superior's terminal, the server, and the subordinate's terminal. Below, we will explain the specific operating procedures for each component and the operation of the entire system.

[1000] Operations on the boss's terminal

[1001] A supervisor enters feedback information about a subordinate using a terminal with a dedicated application installed. The supervisor accesses the feedback input screen, selects the subordinate's name, and enters the feedback content in the text box. When the supervisor clicks the "Send" button, the feedback information is sent to the server. As a concrete example, let's say the supervisor enters, "Your comments in the recent meeting were accurate, but I would like you to say more."

[1002] Processing on the server

[1003] The server receives feedback information from the manager's device. The received information is stored in a database and then passed to a natural language processing engine. The engine analyzes the feedback content and extracts important key phrases such as "quiet but accurate." The AI ​​model then generates specific feedback content based on the analysis results. An example of feedback in this case would be "Try to share more ideas with confidence."

[1004] The generated feedback content is stored in a queue along with the appropriate timing. For example, if it is determined that the subordinate would best receive the feedback when they arrive at work in the morning, the server will schedule the feedback to be sent to the subordinate's device at that time.

[1005] Operations on subordinate devices

[1006] When a subordinate's device receives feedback from the server, the content is immediately saved in its internal memory. At the appropriate time, the feedback content is displayed to the subordinate through the user interface. For example, when a subordinate starts work in the morning, they will see the feedback displayed as "Try to share more ideas with confidence."

[1007] Overall system operation

[1008] This system reduces the risk of a supervisor giving direct feedback to a subordinate and provides a mechanism for subordinates to receive feedback that will lead to their growth at an appropriate and effective time. Feedback information entered from the supervisor's device is sent to a server, where it is analyzed and feedback generated by an AI model is sent to the subordinate's device at the optimal time. As a result, communication between the supervisor and subordinate becomes smoother, promoting the subordinate's growth.

[1009] This is the overall system configuration for implementing the present invention.

[1010] The processing flow will be explained below.

[1011] Step 1:

[1012] The supervisor launches the dedicated app or web app. The supervisor selects the "Enter Feedback" option from the main menu, and the feedback entry screen appears.

[1013] Step 2:

[1014] The manager selects the subordinate's name from the drop-down menu, then enters the feedback in the text box (e.g., "Your comments in recent meetings were accurate, but I'd like to see more of you."), and clicks the "Send" button.

[1015] Step 3:

[1016] The boss's device catches the click event of the send button, converts the feedback content and the subordinate's identification information into JSON format, and sends an HTTP POST request to the server's API endpoint.

[1017] Step 4:

[1018] The server receives an HTTP POST request at the specified API endpoint, parses the received JSON data, and extracts the feedback content and subordinate's identification information.

[1019] Step 5:

[1020] The server passes the extracted feedback to a natural language processing (NLP) engine, which analyzes the meaning of the feedback and extracts key information (e.g., "Small but accurate").

[1021] Step 6:

[1022] The server inputs the analysis results into the AI ​​model, which then generates optimal feedback for the subordinate based on the analysis results (e.g., "Try to share more ideas with confidence").

[1023] Step 7:

[1024] The server compares the generated feedback content with the subordinate's timetable database to determine the optimal transmission timing, and stores the determined feedback content and transmission timing in a queue.

[1025] Step 8:

[1026] Based on the determined timing, the server retrieves the feedback content from the queue and sends an HTTP POST request to the subordinate terminal.

[1027] Step 9:

[1028] The subordinate device receives an HTTP POST request from the server, analyzes the received JSON data, and extracts the feedback content.

[1029] Step 10:

[1030] The subordinate's device uses an appropriate user interface to display the feedback content on the screen. The subordinate checks the displayed feedback and considers possible actions.

[1031] Example 1

[1032] 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."

[1033] Typically, when a manager provides direct feedback to a subordinate, the timing and content are often inappropriate, which results in the subordinate's growth being unsatisfactory. There is also a risk that the manager's feedback may be inappropriate or the subordinate may feel uncomfortable due to poor choice of words. There is a need for a system that can solve these issues and provide feedback to subordinates more effectively and safely.

[1034] 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.

[1035] In this invention, the server includes means for receiving feedback information input from a superior, means for saving the received feedback information in a storage device, means for analyzing the saved feedback information using natural language processing technology, means for generating feedback content based on the analysis result using a generative AI model, and means for sending the generated feedback content to a subordinate at an appropriate time. This makes it possible to analyze feedback from a superior in an appropriate manner, generate optimal feedback content, and provide it to a subordinate at an appropriate time.

[1036] A "supervisor" is an individual in an organization who is in a position to give direct instructions and manage subordinates.

[1037] A "subordinate" is an individual in an organization who is in a position to receive instructions and management from a superior.

[1038] "Feedback information" refers to the content of evaluations, comments, advice, etc. that a superior provides to a subordinate.

[1039] The "receiving means" is a function for taking the feedback information sent from the superior terminal into the server.

[1040] The "storing means" is a function for storing received feedback information in a database or storage device.

[1041] "Natural language processing technology" is a technology for analyzing text data in natural language and converting it into a form that humans can understand.

[1042] "Means of analysis" refers to the function of understanding and analyzing feedback information using natural language processing technology.

[1043] A "generative AI model" is an artificial intelligence model that has been trained in advance using large amounts of data and generates feedback content based on input information.

[1044] "Means for generation" refers to a function for creating feedback content using a generative AI model based on the analysis results.

[1045] The "transmitting means" is a function for sending the generated feedback content to the subordinate terminal.

[1046] The "means for storing in a queue" is a function for temporarily storing the generated feedback content so that it can be sent at an appropriate time.

[1047] "Transmission timing" refers to the optimal time and conditions for transmitting the feedback content to the subordinate terminal.

[1048] "Subordinate terminal" refers to a terminal device used by a subordinate to receive and display feedback.

[1049] MODE FOR CARRYING OUT THE INVENTION

[1050] This invention is a system that uses AI technology to provide feedback from superiors to subordinates effectively and safely. This system consists of three main components: a superior terminal, a server, and a subordinate terminal. The specific operating procedures and the operation of the entire system are explained in detail below.

[1051] Operations on the boss's terminal

[1052] The supervisor uses a device with a dedicated application installed. This device can be a PC or smartphone. To enter feedback information, the supervisor accesses the feedback input screen of the dedicated application, selects the subordinate's name, and enters the feedback content in the text box. For example, the supervisor might enter, "Your comments in the recent meeting were accurate, but I would like you to say more." Once this input is complete, the supervisor clicks the "Send" button to transfer the feedback information to the server.

[1053] Processing on the server

[1054] The server receives the feedback information sent from the supervisor's device. The received feedback information is first stored in a database (e.g., MySQL). The feedback content is then analyzed using a natural language processing engine (e.g., spaCy, NLTK). Through the analysis, important key phrases such as "You speak little, but accurately" are extracted. The server then passes the extracted key phrases to a generative AI model (e.g., GPT-3, BERT) to generate specific feedback content. For example, feedback such as "Try to share more ideas with confidence" is generated.

[1055] The generated feedback is scheduled with the appropriate timing for the subordinate to receive it. The server determines the optimal timing for sending the feedback (e.g., when the subordinate arrives at work in the morning) based on the subordinate's behavioral patterns and preferences, and stores the feedback in a queue.

[1056] Operations on subordinate devices

[1057] The subordinate's device receives the feedback sent from the server. The received feedback is stored in the internal memory and displayed to the subordinate through the user interface at the appropriate time. For example, when the subordinate starts work in the morning, the feedback "Try to share more ideas with confidence" is displayed.

[1058] Examples and prompts

[1059] For example, let's say your boss writes, "Your contributions to the recent project have been great, but you could do better if you paid more attention to the details." This feedback information is parsed and generated as follows:

[1060] Analysis results of the natural language processing engine:

[1061] "Great contributions but attention to detail"

[1062] Feedback generated by the generative AI model:

[1063] "The results are excellent, but with more attention to detail the results would be even better."

[1064] Example prompt for a generative AI model:

[1065] Prompt: Your contribution to your recent project has been great, but it could be even better with a little more attention to detail.

[1066] Output: Good results, but more attention to detail would produce even better results.

[1067] This system reduces the risk involved when a manager gives direct feedback to a subordinate and enables effective feedback to be given at the right time, resulting in smoother communication between managers and subordinates and promoting the growth of subordinates.

[1068] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1069] Step 1: Enter and send feedback on the supervisor's device

[1070] Input: Launch the dedicated application installed on the supervisor's device and access the feedback input screen.

[1071] How it works: A manager selects a subordinate's name and enters specific feedback in the text box.

[1072] Output: When the manager clicks the "Send" button, the feedback information is converted into a data packet and sent to the server.

[1073] Step 2: Receiving and storing feedback information on the server

[1074] Input: Receives data packets sent from the boss's terminal.

[1075] Operation: The server parses the received data packets and extracts the feedback information.

[1076] Output: Save the feedback information to a database (e.g. MySQL).

[1077] Step 3: Analysis using natural language processing on the server

[1078] Input: Feedback information stored in the database.

[1079] How it works: The server passes the feedback information to a natural language processing engine (e.g. spaCy, NLTK) for content analysis.

[1080] A natural language processing engine extracts important key phrases from the feedback.

[1081] Output: As a result of the analysis, we obtain key phrases such as "few comments but accurate."

[1082] Step 4: Feedback generation by the AI ​​model on the server

[1083] Input: Analysis results (important key phrases) obtained from the natural language processing engine.

[1084] How it works: The server inputs the analysis results into a generative AI model (e.g., GPT-3, BERT).

[1085] A generative AI model generates specific feedback content based on key phrases.

[1086] Output: For example, you get feedback such as "Try to share more ideas with confidence."

[1087] Step 5: Registering the schedule on the server

[1088] Input: The specific feedback generated.

[1089] How it works: The server determines the best time to send feedback (e.g., when a subordinate arrives at work).

[1090] Queue feedback and when to send it.

[1091] Output: Feedback stored along with the timing of sending.

[1092] Step 6: Receive and display feedback on subordinate devices

[1093] Input: Feedback information sent by the server.

[1094] Operation: The subordinate device receives the feedback information and stores it in its internal memory.

[1095] Providing feedback through the user interface at the appropriate time.

[1096] Output: For example, a message is displayed to the subordinate saying, "Try to share more ideas with confidence."

[1097] This enables a series of steps to be taken, in which feedback information entered from the superior's device is analyzed and generated on the server, and then sent to the subordinate's device at the optimal timing.

[1098] (Application example 1)

[1099] 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."

[1100] In modern factories, real-time feedback is necessary to efficiently improve the behavior and performance of robots. However, when supervisors provide feedback directly to factory robots, it is difficult to instruct effective actions at the appropriate time. Furthermore, advanced technology is required to accurately analyze the robot's operating status and provide appropriate improvement instructions. A means to effectively solve these issues is needed.

[1101] 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.

[1102] In this invention, the server includes means for receiving feedback information input from a superior, means for analyzing the received feedback information, means for generating feedback content based on the analysis results, and means for transmitting the generated feedback content to the device at an appropriate time, thereby enabling the superior to provide timely and effective feedback to the factory robot and improving the robot's operation and performance.

[1103] "Superior" refers to the person responsible for providing feedback to the system.

[1104] "Feedback information" refers to the content of evaluations and advice for the subject, such as text or audio entered by superiors.

[1105] "Means for receiving" refers to the function that allows the system to incorporate feedback information provided by superiors.

[1106] "Means for analysis" refers to the function of analyzing received feedback information using a natural language processing engine or the like and extracting meaning.

[1107] The "means for generating feedback content" refers to a function for generating specific and appropriate feedback messages based on the analysis results.

[1108] "Device" refers to a robot or other automated device that receives feedback.

[1109] "Appropriate timing" refers to the time and situation in which feedback should be most effectively reflected in the device.

[1110] "Means for transmitting" refers to the network and communication technologies for transmitting the generated feedback to the device.

[1111] The "means for storing in a queue" refers to a function for temporarily storing the generated feedback content until the appropriate time to send it.

[1112] "Determined timing" refers to the time and conditions for executing feedback based on analysis and external conditions.

[1113] A "natural language processing engine" refers to artificial intelligence technology that analyzes feedback information and extracts important information and key phrases.

[1114] "Generating based on the analysis results" refers to the process of constructing specific feedback content based on the analyzed information.

[1115] This invention is a system that provides timely and effective feedback from a superior to equipment (such as a factory robot). The system consists of three main components: a superior terminal, a server, and an equipment terminal.

[1116] Operation on the host terminal

[1117] The supervisor installs a dedicated application on the terminal and inputs feedback information for the device. For example, if the supervisor inputs feedback such as "Please increase the operating speed," the information is sent to the server.

[1118] Processing on the server

[1119] When the server receives feedback information from the host terminal, the received information is first stored in a database. The feedback content is then analyzed using a natural language processing engine (such as BERT). As a result, key phrases are extracted, and "Please increase the movement speed" is recognized as a specific improvement instruction. Next, the AI ​​model generates the feedback content based on the analysis results. As a specific example, the AI ​​model generates the instruction "Please increase the robot's movement speed by 20%."

[1120] The generated feedback content is stored in a queue along with the optimal transmission timing, for example, the time when the device terminal can optimally receive the feedback is determined, and the feedback is scheduled to be transmitted at that time.

[1121] Operation on the device terminal

[1122] When a device terminal receives feedback from the server, the content is immediately saved in its internal memory. At the appropriate time, the feedback content is reflected in the device's control system. For example, if a device terminal receives an instruction such as "Increase the robot's movement speed by 20%, it will adjust the movement speed accordingly.

[1123] Overall system operation

[1124] The feedback information entered by the supervisor is analyzed on the server, and specific feedback content is generated by an AI model and sent to the equipment terminal at the optimal timing. This system enables the supervisor to provide timely and effective feedback to factory robots. An example of an input prompt sentence is shown below as a concrete example.

[1125] Prompt Sentence Examples

[1126] "I would like to increase the operating speed of Robot X. Its current operating speed is slow, which is reducing the efficiency of the entire production line."

[1127] Based on such prompts, the AI ​​generates specific feedback such as "Please increase Robot X's movement speed by 20%," and the server sends the instructions to the device terminal at the appropriate time.

[1128] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1129] Step 1:

[1130] The superior inputs feedback information from the terminal. As an example, "Please increase the speed of operation" is entered into the text box. The input data is sent to the server by clicking the "Send" button. The input is text data, and the output is feedback information sent to the server.

[1131] Step 2:

[1132] The server stores the feedback information received from the host terminal in a database. Storing the feedback information in a database ensures that the feedback information is managed continuously and safely. The input is the feedback information received from the terminal, and the output is the feedback information stored in the database.

[1133] Step 3:

[1134] The server extracts feedback information from the database and analyzes it using a natural language processing engine (NLP model). Important key phrases are extracted through the analysis. For example, the key phrases "movement speed" and "please increase it" are obtained. The input is the feedback information extracted from the database, and the output is the analysis results in the form of key phrases.

[1135] Step 4:

[1136] Based on the analysis results, the server uses a generative AI model to generate specific feedback. For example, a specific instruction such as "Increase the robot's movement speed by 20%" is generated. The input is the analysis result obtained through natural language processing, and the output is the specific feedback generated.

[1137] Step 5:

[1138] The server stores the generated feedback in a queue along with the appropriate transmission timing, for example, setting it to be sent at the start of the next production shift. The input is the generated feedback, and the output is the feedback stored in the queue and the transmission timing.

[1139] Step 6:

[1140] The server sends the feedback stored in the queue to the equipment terminal based on the timing it determines, for example, when the next shift starts. The input is the feedback stored in the queue and its sending timing, and the output is the feedback sent to the equipment terminal.

[1141] Step 7:

[1142] The device terminal stores the feedback received from the server in its internal memory. The stored content is reflected in the device's control system at the appropriate time. The input is the feedback received from the server, and the output is the feedback stored in the device's internal memory.

[1143] Step 8:

[1144] The device executes operations based on the feedback stored in its internal memory. For example, an instruction to "increase the robot's movement speed by 20%" is reflected in the actual movement control. The input is the feedback stored in the internal memory, and the output is the actual robot movement.

[1145] 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.

[1146] This invention is a system that uses AI and emotion recognition technology to provide effective and safe feedback from superiors to subordinates. This system consists of three main components: a superior terminal, a server, and a subordinate terminal. By combining these with an emotion engine, the system can dynamically adjust the feedback content based on the user's emotions.

[1147] Operations on the boss's terminal

[1148] A supervisor enters feedback information about a subordinate using a device with a dedicated application installed. The supervisor accesses the feedback input screen, selects the subordinate's name, and enters the feedback content in the text box. When the supervisor clicks the "Send" button, the feedback information is sent to the server. Furthermore, during this process, the emotion engine recognizes the emotion the supervisor was feeling when entering the feedback and modifies the tone and expression of the feedback content as appropriate. For example, if a supervisor enters "Your comments in the recent meeting were accurate, but I would like you to say more," and the emotion engine recognizes the supervisor's positive emotion, it will modify the feedback to read, "Your comments in the recent meeting were very accurate. Please try to speak more."

[1149] Processing on the server

[1150] The server receives feedback information from the superior's device. The received information is stored in a database and then passed to a natural language processing engine. The engine analyzes the feedback content and extracts important key phrases such as "You speak little, but accurately." The AI ​​model then generates specific feedback content based on the analysis results. During this process, the emotion engine checks whether the generated feedback content is appropriate for the subordinate and modifies it if necessary. The generated feedback content is "Try to share more ideas with confidence."

[1151] The generated feedback content is stored in a queue along with the appropriate timing. For example, if it is determined that the subordinate would best receive the feedback when they arrive at work in the morning, the server will schedule the feedback to be sent to the subordinate's device at that time.

[1152] Operations on subordinate devices

[1153] When a subordinate's device receives feedback from the server, the content is immediately saved in its internal memory and displayed to the subordinate through the user interface at the appropriate time. During this process, the subordinate's emotions are recognized by the emotion engine, and the follow-up content is modified depending on how the feedback was received. For example, if a subordinate reacts positively to the feedback displayed at the start of work in the morning, "Try to share more ideas with confidence," the follow-up message will be, "We look forward to hearing your opinion."

[1154] Overall system operation

[1155] This system reduces the risk of a supervisor giving direct feedback to a subordinate, and provides a mechanism for subordinates to receive feedback that will lead to their growth at an appropriate and effective time. Feedback information entered from the supervisor's device is sent to a server, where it is analyzed and feedback is generated using an AI model, after which the emotion engine is checked and corrected. It is then sent to the subordinate's device at the optimal time. This results in smoother communication between the supervisor and subordinate, promoting the subordinate's growth.

[1156] This is the overall system configuration for implementing the present invention.

[1157] The processing flow will be explained below.

[1158] Step 1:

[1159] The supervisor launches the dedicated app or web app. The supervisor selects the "Enter Feedback" option from the main menu, and the feedback entry screen appears.

[1160] Step 2:

[1161] The manager selects the subordinate's name from a drop-down menu, then enters feedback in the text box (e.g., "Your comments in recent meetings were accurate, but I'd like to see more of you.").

[1162] Step 3:

[1163] The boss's device uses an emotion engine to recognize the boss's emotions as they are being input. The emotion engine evaluates the boss's emotional state (e.g., positive, negative) and modifies the feedback content as necessary. For example, if the boss is inputting with a positive emotion, the feedback content will be modified to "Your comments in the recent meeting were very accurate. Please try to speak up more."

[1164] Step 4:

[1165] After the supervisor checks the revised feedback content, he / she clicks the "Send" button. The supervisor's device catches the click event of the Send button, converts the feedback content and the subordinate's identification information into JSON format, and sends an HTTP POST request to the server's API endpoint.

[1166] Step 5:

[1167] The server receives an HTTP POST request at the specified API endpoint, parses the received JSON data, and extracts the feedback content and subordinate's identification information.

[1168] Step 6:

[1169] The server passes the extracted feedback to a natural language processing (NLP) engine, which analyzes the meaning of the feedback and extracts key information (e.g., "Small but accurate").

[1170] Step 7:

[1171] The server inputs the analysis results into the AI ​​model, which then generates optimal feedback for the subordinate based on the analysis results (e.g., "Try to share more ideas with confidence").

[1172] Step 8:

[1173] The generated feedback is passed to the emotion engine, which evaluates whether the tone and expression of the feedback are appropriate and makes corrections as necessary. For example, the tone may be changed to a gentler tone to prevent the subordinate from feeling overly stressed.

[1174] Step 9:

[1175] The server stores the generated feedback content in a queue along with the appropriate delivery timing. The queue contains feedback content to be sent and its delivery timing.

[1176] Step 10:

[1177] Based on the determined timing, the server retrieves the feedback content from the queue and sends an HTTP POST request to the subordinate terminal.

[1178] Step 11:

[1179] The subordinate device receives an HTTP POST request from the server, analyzes the received JSON data, and extracts the feedback content.

[1180] Step 12:

[1181] The subordinate's device uses an appropriate user interface to display the feedback content on the screen. The subordinate then checks the displayed feedback.

[1182] Step 13:

[1183] The subordinate's device recognizes the subordinate's reaction to the feedback using an emotion engine. The emotion engine evaluates the subordinate's emotional state and provides follow-up feedback as needed. For example, if the subordinate reacts positively, a further encouraging message is displayed.

[1184] Example 2

[1185] 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."

[1186] When a manager gives feedback to a subordinate, it is often necessary to convey emotion and express it appropriately. However, inconsistencies in emotion or timing can sometimes result in feedback having the opposite effect. Furthermore, if the feedback is too formal and lacks specificity, it is difficult to promote the subordinate's growth. Conventional systems often fail to adequately resolve these issues.

[1187] 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.

[1188] In this invention, the server includes means for receiving feedback information input from a superior, means for analyzing the received feedback information, recognizing emotions, and modifying the tone and expression of the feedback content, means for generating feedback content based on the analysis results, and means for transmitting the generated feedback content to a subordinate at an appropriate timing. This enables appropriate feedback according to the superior's emotions and timing, and promotes the growth of the subordinate.

[1189] "Feedback information" refers to information that includes evaluations, comments, advice, etc., given by superiors to subordinates.

[1190] The "receiving means" is a function that allows the server to receive feedback information sent from the superior terminal.

[1191] "Means for analysis" refers to the function for processing and analyzing received feedback information and extracting necessary key phrases and emotions.

[1192] "Means of recognizing emotions" refers to a technology that analyzes the emotional aspects of the feedback entered by a supervisor and makes adjustments based on that.

[1193] The "means for generating feedback content" is a function that creates specific feedback appropriate for subordinates based on the analyzed data.

[1194] The "means for transmitting the generated feedback content" is a function for transmitting the feedback content to the subordinate terminal at an appropriate timing.

[1195] The "means for storing in a queue" is a technique for temporarily storing the generated feedback content and managing it so that it can be sent at a specified timing.

[1196] A "key phrase" is a set of short sentences or words that indicate particularly important parts of the feedback information.

[1197] A "generative AI model" is an artificial intelligence algorithm used to automatically generate feedback content.

[1198] A "natural language processing engine" is a technology for analyzing text data and extracting meaning and key phrases.

[1199] An "emotion engine" is a technology that analyzes emotions from text and voice and adjusts the feedback content based on that information.

[1200] The "user interface" is the part of the system that provides the screen and operation methods for subordinates to view the feedback content.

[1201] This invention is a system that uses AI and emotion recognition technology to provide effective and safe feedback from superiors to subordinates. This system consists of three main components: a superior terminal, a server, and a subordinate terminal. By combining these components with an emotion engine, the system can dynamically adjust the feedback content based on the user's emotions.

[1202] Operations on the boss's terminal

[1203] A supervisor uses a device with dedicated software installed to enter feedback information about a subordinate. The supervisor accesses the feedback entry screen, selects the subordinate's name, and enters the feedback content in the text box. For example, the supervisor can enter, "Your comments in the recent meeting were accurate, but I would like you to speak up more." When the supervisor clicks the "Send" button, the feedback information is sent from the terminal to the server. During this process, the emotion engine recognizes the emotion the supervisor was feeling when entering the feedback and modifies the tone and expression of the feedback content accordingly. For example, if the emotion engine recognizes the supervisor's positive emotion, it will modify the feedback to, "Your comments in the recent meeting were very accurate. Please speak up more."

[1204] Processing on the server

[1205] The server receives feedback information from the supervisor's device. The received information is stored in a database such as MySQL. It is then passed to a natural language processing engine (e.g., SpaCy). The natural language processing engine analyzes the feedback content and extracts important key phrases such as "quiet but accurate."

[1206] Next, an AI model (e.g., GPT-4) generates specific feedback content based on the analysis results. During this process, an emotion engine (e.g., Affectiva) checks whether the generated feedback content is appropriate for the subordinate and modifies it if necessary. For example, the generated feedback content could be, "Try to share more ideas with confidence."

[1207] The generated feedback content is stored in a queue along with the appropriate timing. For example, if it is determined that the subordinate would best receive the feedback when they arrive at work in the morning, the server will schedule the feedback to be sent to the subordinate's device at that time.

[1208] Operations on subordinate devices

[1209] When a subordinate's device receives feedback from the server, the content is immediately saved in internal memory (for example, an SQLite database). At the appropriate time, the feedback content is displayed to the subordinate through the user interface. During this process, the emotion engine recognizes the subordinate's emotions and modifies the follow-up content depending on how the feedback was received. For example, if a subordinate reacts positively to the feedback displayed at the start of work in the morning, "Try to share more ideas with confidence," the follow-up message will be "We look forward to your opinion."

[1210] Examples of prompts for generative AI models

[1211] "Use this feedback, 'You don't say much, but you get it. I wish you'd be more confident and share your ideas,' to generate more positive feedback that's appropriate for your employee."

[1212] This system reduces the risk of a supervisor giving direct feedback to a subordinate and provides a mechanism for subordinates to receive feedback that leads to growth at an appropriate and effective time. Feedback information entered from the supervisor's device is sent to a server, where it is analyzed and feedback is generated using an AI model, after which the emotion engine is checked and corrected. This information is then sent to the subordinate's device at the optimal time, facilitating smooth communication between the supervisor and subordinate and promoting the subordinate's growth. This system contributes to improving the quality of feedback in companies and organizations.

[1213] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1214] Step 1:

[1215] The user launches the dedicated application and accesses the feedback input screen. After selecting the subordinate's name, they enter their feedback in the text box. Once they've finished entering their feedback, they click the "Send" button. The supervisor's device passes this input to an emotion engine, which analyzes the content while recognizing the supervisor's emotions. As a result, the tone and expression of the feedback are adjusted.

[1216] Input: Feedback entered by the manager (e.g., "Your comments in recent meetings were accurate, but I'd like you to say more.")

[1217] Output: Corrected feedback (e.g., "You were very accurate in your recent meeting. Please try speaking up more.")

[1218] Step 2:

[1219] The device sends the corrected feedback to the server, which receives the data and stores it in a database. A relational database such as MySQL is used to store the feedback data.

[1220] Input: Corrected feedback

[1221] Output: Feedback information stored in a database

[1222] Step 3:

[1223] The server retrieves the feedback information from the database and passes it to a natural language processing engine (e.g., SpaCy) for analysis. The engine analyzes the feedback content and extracts important key phrases. For example, the key phrase extracted is "quiet but accurate."

[1224] Input: Feedback information stored in the database

[1225] Output: Extracted key phrases (e.g., "Small but precise")

[1226] Step 4:

[1227] The server then passes the extracted key phrases to a generative AI model (e.g., GPT-4) as prompts to generate specific feedback. The generated feedback is then checked by an emotion engine and corrected if necessary.

[1228] Input: Extracted key phrases

[1229] Output: Generated and revised feedback (e.g., "Try to be more confident and share more ideas")

[1230] Step 5:

[1231] The server stores the generated and modified feedback in a queue and schedules appropriate times for sending it, for example, when subordinates arrive at work in the morning.

[1232] Input: Generated and revised feedback

[1233] Output: Queued feedback

[1234] Step 6:

[1235] The subordinate's device receives the feedback content at the specified time. The received content is immediately saved in the internal memory (SQLite database) and displayed on the user interface at the appropriate time. When the subordinate confirms the feedback, the emotion engine analyzes the subordinate's emotions and performs adaptive follow-up.

[1236] Input: Feedback sent from the queue

[1237] Output: Feedback displayed on the subordinate's device, along with any necessary follow-up (e.g., "I look forward to hearing your opinion.")

[1238] The above is the specific processing flow of this system. This system effectively supports communication between superiors and subordinates and promotes the growth of subordinates.

[1239] (Application example 2)

[1240] 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."

[1241] When using robots in factories, it is important for managers to provide appropriate feedback to robots. However, conventional systems do not accurately reflect the manager's emotions and intentions, making it difficult to appropriately improve the robot's work efficiency and performance. Furthermore, there is a lack of mechanisms for the robot to respond appropriately to the feedback it receives, making it difficult to optimize work efficiency. Furthermore, continuous improvement is hindered by insufficient follow-up based on how the feedback is received.

[1242] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving feedback information input from a superior, means for analyzing the received feedback information, and means for generating feedback content based on the analysis results. This makes it possible to modify the tone and expression of the feedback using an emotion recognition engine. In addition, by including means for sending the feedback content stored in the queue to a subordinate terminal at a determined timing, analyzing the subordinate's emotions in response to the feedback received by the subordinate terminal, and modifying the follow-up content, it becomes possible for the robot to adjust its work efficiency and performance based on the feedback content received. This provides a system in which the manager's intentions are accurately reflected, the robot's work efficiency is improved, and continuous improvement is achieved.

[1243] "Feedback information entered by a superior" refers to evaluations, comments, and advice entered by a manager in the factory based on the robot's work status.

[1244] An "emotion recognition engine" is a technology that analyzes emotions from input text or voice and modifies the tone and expression of information based on those emotions.

[1245] "Feedback content generated based on the analysis results" refers to information that has been reconstructed as appropriate feedback content based on the results of analysis using a natural language processing engine.

[1246] A "subordinate terminal" is a device for receiving and displaying feedback content, and in this case refers to a robot that performs work in a factory.

[1247] A "natural language processing engine" is an algorithm or process that analyzes input text data and understands its content and meaning.

[1248] A "queue" is a data structure for temporarily storing information such as feedback content and transmission timing.

[1249] "Follow-up" refers to ongoing confirmation and advice after the initial feedback, adjusted based on the subordinate's response.

[1250] "Means for adjusting work efficiency and performance" refers to methods and mechanisms by which a robot receives feedback and improves and optimizes its own movements and the way it carries out its work.

[1251] This invention is specifically implemented as a feedback system for robot work in a factory. The system mainly consists of a supervisor terminal, a server, and subordinate terminals (factory work robots).

[1252] Overall system configuration

[1253] Supervisor's terminal: A supervisor uses a smartphone or other device to input feedback information based on the robot's work status. The supervisor's terminal is equipped with an emotion recognition engine that analyzes the emotions expressed during input and includes a function to modify the tone and expression of the feedback.

[1254] Server: Receives feedback information and stores it in a database. Furthermore, it analyzes the data using a natural language processing engine and generates feedback content based on the analysis results. The generated feedback content is corrected to an appropriate tone using an emotion recognition engine and stored in a queue based on the appropriate sending timing. The server uses software such as Flask (web framework), TextBlob (natural language processing), and emotion_recognition (emotion recognition).

[1255] Subordinate terminal (factory robot): This terminal receives feedback from the server, and is played by the factory robot. The robot adjusts its work efficiency and performance based on the received feedback. The robot's reaction to the feedback (if it analyzes emotions) is also sent to the server, and appropriate follow-up is carried out.

[1256] Specific examples

[1257] Example of administrator input: An administrator enters feedback such as "Your work speed is a little slow."

[1258] Emotion recognition and correction: The emotion recognition engine analyzes the input feedback as having a "neutral" emotion and corrects it to "Please be careful to speed up your work."

[1259] Server processing: The feedback information sent to the server is analyzed by a natural language processing engine, which identifies the key phrase "speed" and generates and modifies appropriate improvement suggestions.

[1260] Robot response: The robot receives feedback and makes adjustments to improve its speed of work.

[1261] Prompt Sentence Examples

[1262] Example of feedback provided by the administrator:

[1263] Admin Feedback: I feel like I'm repeating myself

[1264] Expected output:

[1265] Think about your work efficiency and look for areas for improvement.

[1266] Hardware and software used

[1267] Hardware: Smartphone (supervisor's device), server (database and analysis processing), robots that work in the factory (subordinate devices).

[1268] Software: Flask (web framework for server), TextBlob (natural language processing), emotion_recognition (emotion recognition engine).

[1269] This system allows the manager's intentions to be accurately reflected in the robot, improving the robot's work efficiency and enabling continuous adaptation and improvement.

[1270] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1271] Step 1:

[1272] Feedback input on the boss's terminal:

[1273] A user (manager) uses a supervisor's device such as a smartphone to input textual feedback on the performance of a factory robot. This textual input is passed to an emotion recognition engine, which analyzes the tone and expression of the feedback and corrects it as necessary. The feedback text is given as input, and tone-corrected feedback text is generated as output.

[1274] Example: If a manager types "I'm a little slow at work," it will be corrected to "Please pay attention to speeding up your work."

[1275] Step 2:

[1276] Send feedback information:

[1277] The feedback text corrected on the supervisor's terminal is sent to the server. The corrected feedback text is used as input, and the text is transferred to the server as output.

[1278] Example: "Pay attention to speeding up your work" feedback is sent to the server.

[1279] Step 3:

[1280] Feedback analysis on the server:

[1281] The server passes the received feedback text to a natural language processing engine, which analyzes the text, extracts important key phrases, and reconstructs the feedback content. The received feedback text is used as input, and the analyzed feedback content is generated as output.

[1282] Example: Identifying "speed" as a key phrase and generating an appropriate improvement suggestion such as "Try to improve your work speed."

[1283] Step 4:

[1284] Sentiment check and correction of generated feedback:

[1285] The server-generated feedback content is checked by an emotion recognition engine and the expressions are corrected if necessary. The reconstructed feedback content is used as input and the final feedback text is generated as output.

[1286] Example: "Please try to improve your work speed" is corrected to "Please try."

[1287] Step 5:

[1288] Queued feedback:

[1289] The server stores the final feedback text and send timing in a queue. The revised feedback text and send timing are used as input to generate a data entry that is stored in the queue as output.

[1290] Example: The feedback "Please try harder" is queued to be sent at 9am the next morning.

[1291] Step 6:

[1292] Send feedback from a queue:

[1293] Based on the determined timing, the feedback content is sent from the queue to the subordinate device (robot). The data entries stored in the queue are used as input, and the feedback that is sent to the robot as output is generated.

[1294] Example: The robot receives feedback saying "Please try harder" at 9am the next morning.

[1295] Step 7:

[1296] Receiving and acting on feedback in the robot:

[1297] The subordinate device (robot) stores the received feedback in its internal memory and adjusts its work efficiency and performance based on the feedback. The received feedback is used as input, and the robot's behavior is adjusted as output.

[1298] Example: A robot receives feedback saying "try harder" and adjusts its speed.

[1299] Step 8:

[1300] Analysis of the robot's response to feedback:

[1301] The robot responds to the feedback and its reaction (e.g., improved work speed) is sent to the server. The server analyzes this reaction and generates or modifies follow-up feedback as needed. The robot's response data is used as input, and the next feedback content is generated as output.

[1302] Example: A robot increases its work speed and sends the results to a server, which generates follow-up feedback such as "keep up the good work."

[1303] 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.

[1304] 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.

[1305] 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.

[1306] 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.

[1307] 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.

[1308] 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.

[1309] 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).

[1310] 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.

[1311] 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."

[1312] 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.

[1313] 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).

[1314] 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.

[1315] 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.

[1316] 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.

[1317] 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.

[1318] 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.

[1319] 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.

[1320] 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.

[1321] 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.

[1322] 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.

[1323] 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.

[1324] The following is further disclosed regarding the above embodiment.

[1325] (Claim 1)

[1326] a means for receiving feedback information input from a supervisor;

[1327] means for analyzing received feedback information;

[1328] means for generating feedback content based on the analysis results;

[1329] A means for sending the generated feedback content to subordinates at an appropriate time;

[1330] A system including:

[1331] (Claim 2)

[1332] means for storing the generated feedback content in a queue along with an appropriate transmission timing;

[1333] means for transmitting the feedback content stored in the queue to the subordinate terminal based on the determined timing;

[1334] The system of claim 1 further comprising:

[1335] (Claim 3)

[1336] A means for analyzing feedback information entered by a supervisor using a natural language processing engine;

[1337] A means for generating optimal feedback for subordinates based on the analysis results;

[1338] The system of claim 1 further comprising:

[1339] "Example 1"

[1340] (Claim 1)

[1341] a means for receiving feedback information input from a supervisor;

[1342] means for storing the received feedback information in a storage device;

[1343] means for analyzing the stored feedback information using natural language processing technology;

[1344] A means for generating feedback content based on the analysis results using a generation AI model;

[1345] A means for sending the generated feedback content to subordinates at an appropriate time;

[1346] A system including:

[1347] (Claim 2)

[1348] means for storing the generated feedback content in a queue along with an appropriate transmission timing;

[1349] means for transmitting the feedback content stored in the queue to the subordinate terminal based on the determined timing;

[1350] The system of claim 1 further comprising:

[1351] (Claim 3)

[1352] A natural language processing engine that analyzes the feedback information entered by the supervisor,

[1353] A generative AI model that generates optimal feedback for subordinates based on the analysis results;

[1354] The system of claim 1 further comprising:

[1355] "Application Example 1"

[1356] (Claim 1)

[1357] means for receiving feedback information input from a superior;

[1358] means for analyzing received feedback information;

[1359] means for generating feedback content based on the analysis results;

[1360] means for transmitting the generated feedback content to the device in a timely manner;

[1361] A system including:

[1362] (Claim 2)

[1363] means for storing the generated feedback content in a queue along with an appropriate transmission timing;

[1364] means for transmitting the feedback content stored in the queue to the device terminal based on the determined timing;

[1365] The system of claim 1 further comprising:

[1366] (Claim 3)

[1367] A means for analyzing feedback information input by superiors using a natural language processing engine;

[1368] a means for generating optimal feedback for the device based on the analysis results;

[1369] The system of claim 1 further comprising:

[1370] "Example 2: Combining Emotion Engines"

[1371] (Claim 1)

[1372] a means for receiving feedback information input from a supervisor;

[1373] a means for analyzing the received feedback information, recognizing emotions, and modifying the tone and expression of the feedback content;

[1374] means for generating feedback content based on the analysis results;

[1375] A means for sending the generated feedback content to subordinates at an appropriate time;

[1376] A system including:

[1377] (Claim 2)

[1378] means for storing the generated feedback content in a queue along with an appropriate transmission timing;

[1379] means for transmitting the feedback content stored in the queue to the subordinate terminal based on the determined timing;

[1380] The system of claim 1 further comprising:

[1381] (Claim 3)

[1382] A method for analyzing feedback information entered by superiors using a natural language processing engine and extracting important key phrases;

[1383] a means for using the generative AI model to generate optimal feedback for the subordinate based on the extracted key phrases;

[1384] A means to check the tone of the generated feedback using an emotion engine and correct it if necessary;

[1385] The system of claim 1 further comprising:

[1386] "Application example 2 when combining emotion engines"

[1387] (Claim 1)

[1388] a means for receiving feedback information input from a supervisor;

[1389] means for analyzing received feedback information;

[1390] means for generating feedback content based on the analysis results;

[1391] A means for sending the generated feedback content to subordinates at an appropriate time;

[1392] A means of analyzing emotions at the time of input using an emotion recognition engine and correcting the tone and expression of the feedback content;

[1393] A system including:

[1394] (Claim 2)

[1395] means for storing the generated feedback content in a queue along with an appropriate transmission timing;

[1396] means for transmitting the feedback content stored in the queue to the subordinate terminal based on the determined timing;

[1397] A means for analyzing the subordinate's emotions in response to the feedback received by the subordinate's device and modifying the content of follow-up depending on how the feedback is perceived;

[1398] The system of claim 1 further comprising:

[1399] (Claim 3)

[1400] A means for analyzing feedback information entered by a supervisor using a natural language processing engine;

[1401] A means for generating optimal feedback for subordinates based on the analysis results;

[1402] A means for adjusting work efficiency and performance based on feedback received by robots working in factories, and

[1403] The system of claim 1 further comprising: [Explanation of symbols]

[1404] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for receiving feedback information input from a supervisor; means for analyzing received feedback information; means for generating feedback content based on the analysis results; A means for sending the generated feedback content to subordinates at an appropriate time; A system including:

2. means for storing the generated feedback content in a queue together with an appropriate transmission timing; means for transmitting the feedback content stored in the queue to the subordinate terminal based on the determined timing; The system of claim 1 further comprising:

3. A means for analyzing feedback information entered by a supervisor using a natural language processing engine; A means for generating optimal feedback for subordinates based on the analysis results; The system of claim 1 further comprising:

Images