System

Abstract

To provide a system.SOLUTION: The system includes: the means for acquiring an input of a user to a chat bot having a dialogue-type engagement research function and a bi-directional dialogue function to make the nature of employees visible; means for generating a response to the acquired input of the user by using a generation AI model; means for presenting the response to the user through the chat bot; and means for analyzing the input of the user and generating a report.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] With conventional ES surveys, it was difficult to grasp employees' essential opinions and issues, making it difficult to plan appropriate measures based on those opinions. [Means for solving the problem]

[0005] The present invention has an interactive ES survey function that visualizes the true nature of employees, and uses this interactive ES survey function to conduct two-way dialogue. This highlights previously unseen issues and allows for the development of countermeasures. In particular, the interactive ES survey function is a chatbot using artificial intelligence, and the countermeasures contribute to creating a comfortable working environment for employees and improving performance. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] One aspect of the present invention is a system with an interactive ES survey function that visualizes the true nature of employees. This system uses a chatbot with artificial intelligence to engage in two-way dialogue with employees. The chatbot generates appropriate responses to input from employees and understands their opinions and issues.

[0029] "Example 2"

[0030] Furthermore, one aspect of the present invention is a function that proposes countermeasures for issues that have been identified through two-way dialogue. Based on the identified issues, this function proposes countermeasures that contribute to creating a comfortable working environment for employees and improving business performance. For example, based on feedback from employees, it proposes measures such as improving the work environment, reviewing business processes, and providing education and training.

[0031] "Example 3"

[0032] As a concrete example, if feedback from employees indicates that they often find it difficult to communicate, countermeasures such as providing training to improve communication skills or creating open spaces can be proposed. This will create a comfortable working environment for employees and improve business performance.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The system receives input from employees. This input is about their opinions and issues.

[0036] Step 2: The system then uses an artificial intelligence-powered chatbot to generate appropriate responses to the inputs, which are designed to better understand the employee's opinions and challenges.

[0037] Step 3: Finally, the system gathers employee opinions and issues through two-way dialogue and stores them in a database.

[0038] "Example 2"

[0039] Step 1: The system analyzes employee opinions and issues stored in the database.

[0040] Step 2: Next, based on the analysis results, the system will develop measures to create a comfortable working environment for employees and contribute to improving performance.

[0041] Step 3: Finally, the proposed measures are reported to the manager and implemented.

[0042] "Example 3"

[0043] Step 1: If the system detects a lot of "difficulty in communication" in employee feedback, it will identify this as an issue.

[0044] Step 2: Next, the system will develop countermeasures to address this issue, such as "providing training to improve communication skills" and "establishing open spaces."

[0045] Step 3: Finally, the proposed measures are reported to management and implemented, resulting in the creation of a comfortable working environment for employees and improved performance.

[0046] Example 1

[0047] Next, a description will be given of Example 1 of Form 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."

[0048] Traditional engagement surveys have made it difficult to accurately grasp employee opinions and issues, and lacked effective methods for visualizing the true nature of employees. As a result, it has been difficult to create a comfortable working environment for employees and to devise appropriate measures to contribute to improving performance. Furthermore, because real-time two-way dialogue is not possible, it has been impossible to quickly reflect employee opinions and issues.

[0049] 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.

[0050] In this invention, the server includes a means for a user to access the chatbot using a terminal, a means for the terminal to receive user input and send it to the server, a means for the server to generate a response to the user input using a generative AI model, a means for the server to send the generated response to the terminal, a means for the terminal to display the response from the server to the user, and a means for the server to analyze the user's input data and generate a report. This makes it possible to grasp employee opinions and issues in real time and quickly develop appropriate measures.

[0051] The "interactive engagement survey function" is a function that allows for two-way dialogue to understand employees' opinions and issues and visualize their true nature.

[0052] "Two-way dialogue" is a form of dialogue in which the user and the system exchange opinions and information in real time.

[0053] "Measures to address issues" refers to developing appropriate solutions to employee issues that have been highlighted through two-way dialogue.

[0054] A "terminal" is a device used by a user to access the system, including a PC, smartphone, etc.

[0055] The "server" is a central processing unit that receives user input data, generates responses using generative AI models, and analyzes the data.

[0056] A "generative AI model" is an artificial intelligence model that generates appropriate responses based on user input.

[0057] A "chatbot" is a program that interacts with users and generates responses using generative AI models.

[0058] A "report" is a report in which the server analyzes the data entered by the user and summarizes the opinions and issues of employees.

[0059] This invention is a system with an interactive engagement survey function to visualize the true nature of employees. This system is built around a chatbot using artificial intelligence, and grasps employees' opinions and issues through two-way dialogue with users (employees).

[0060] System configuration

[0061] Hardware

[0062] Terminal: A device used by a user to access the system, including a PC or smartphone.

[0063] Server: A central processing unit that receives user input data, generates responses using generative AI models, and analyzes the data.

[0064] software

[0065] Generative AI model: An artificial intelligence model that generates appropriate responses based on user input. Specifically, OpenAI's GPT-4 (registered trademark) is used.

[0066] Chatbot: A program that interacts with users and generates responses using generative AI models.

[0067] System Operation

[0068] 1. A user accesses a chatbot using a device

[0069] Users can access the system's chatbot using devices such as PCs or smartphones, for example, through a dedicated web application or mobile application.

[0070] 2. The device receives the user's input and sends it to the server

[0071] When a user inputs text into the chatbot, the device sends the input data to the server. For example, a user might input, "I'm feeling stressed about a recent project."

[0072] 3. The server uses the generative AI model to generate a response to the user's input.

[0073] The server passes the received user input data to a generative AI model (e.g., OpenAI's GPT-4) and generates an appropriate response. Based on the user's input, the generative AI model generates a response such as, "Which specifically are you feeling stressed about?"

[0074] 4. The server generates a response and sends it to the device.

[0075] The server sends the responses generated by the generative AI model to the device, providing an appropriate response to the user's input in real time.

[0076] 5. The device displays the response from the server to the user.

[0077] The terminal displays the response received from the server to the user, who can then confirm the response from the chatbot and enter further details.

[0078] 6. The server analyzes the user's input data and generates a report

[0079] The server analyzes the input data collected from users and generates reports to understand employee opinions and issues, which managers can use to evaluate employee engagement and satisfaction.

[0080] Specific examples

[0081] For example, if a user types "I'm feeling stressed about a recent project," the following specific actions will occur:

[0082] 1. A user uses a device to type into the chatbot, "I'm feeling stressed about a recent project."

[0083] 2. The device sends this input to the server.

[0084] 3. The server uses a generative AI model (GPT-4) to generate a response: "What specifically are you feeling stressed about?"

[0085] 4. The server generates a response and sends it to the terminal.

[0086] 5. The device displays the response to the user: "Where specifically are you feeling stressed?"

[0087] 6. The server analyzes the user's input data and generates a report that includes the causes and frequency of employee stress.

[0088] Prompt Sentence Examples

[0089] Examples of prompts to input to a generative AI model include:

[0090] Prompt: "If an employee types in that they are feeling stressed about a recent project, how would you respond?"

[0091] In response to this prompt, the generative AI model generates the following response:

[0092] Sample response: "What specifically are you stressed about? How is the project progressing? How is your team communicating?"

[0093] In this way, the system visualizes the true nature of employees through dialogue with users and provides useful information to managers.

[0094] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0095] Step 1:

[0096] A user accesses the chatbot using a device

[0097] Users can access the system's chatbot using devices such as PCs or smartphones, for example, through a dedicated web application or mobile application.

[0098] Input: User's access request

[0099] Output: The chatbot interface is displayed.

[0100] Step 2:

[0101] The terminal receives the user's input and sends it to the server

[0102] When a user inputs text into the chatbot, the device sends the input data to the server. For example, a user might input, "I'm feeling stressed about a recent project."

[0103] Input: User text input

[0104] Output: The input data is sent to the server

[0105] Step 3:

[0106] The server uses the generative AI model to generate responses to user input.

[0107] The server passes the received user input data to a generative AI model (e.g., OpenAI's GPT-4) and generates an appropriate response. Based on the user's input, the generative AI model generates a response such as, "Which specifically are you feeling stressed about?"

[0108] Input: User-entered data

[0109] Output: Response data from the generative AI model

[0110] Step 4:

[0111] Sends the server-generated response to the terminal

[0112] The server sends the responses generated by the generative AI model to the device, providing an appropriate response to the user's input in real time.

[0113] Input: Response data from a generative AI model

[0114] Output: Response data is sent to the terminal

[0115] Step 5:

[0116] The terminal displays the response from the server to the user

[0117] The terminal displays the response received from the server to the user, who can then confirm the response from the chatbot and enter further details.

[0118] Input: Response data from the server

[0119] Output: The response data is displayed to the user

[0120] Step 6:

[0121] The server analyzes the user's input data and generates a report

[0122] The server analyzes the input data collected from users and generates reports to understand employee opinions and issues, which managers can use to evaluate employee engagement and satisfaction.

[0123] Input: User-entered data

[0124] Output: Report based on the analysis results

[0125] In this way, the system visualizes the true nature of employees through dialogue with users and provides useful information to managers.

[0126] (Application example 1)

[0127] Next, a description will be given of Application Example 1 of Embodiment 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."

[0128] Conventional interactive ES survey systems focus on collecting employee opinions and issues, but lack the means to collect the opinions and issues of workers working in factories and to improve the work environment and increase efficiency. In addition, there is a need for a system that can devise specific measures based on the information obtained through dialogue with workers.

[0129] 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.

[0130] In this invention, the server includes means having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating measures for issues highlighted by the two-way dialogue, means having an application installed on a robot for collecting opinions and issues of workers working in a factory, means for generating appropriate responses to inputs from workers using a generative AI model, and means for improving the work environment and streamlining the work environment based on the responses. This makes it possible to efficiently collect opinions and issues of workers working in a factory and to improve the work environment and streamline the work environment.

[0131] The "interactive ES survey function" is a function that collects opinions and issues through two-way dialogue in order to visualize the true nature of employees.

[0132] "Two-way dialogue" refers to interactive communication that uses artificial intelligence such as chatbots to exchange opinions with employees and workers in real time.

[0133] "Means for planning countermeasures to issues" refers to the function of planning and proposing specific improvement measures and countermeasures for issues that have been highlighted through two-way dialogue.

[0134] "Factory workers" are employees who perform manufacturing, assembly, and other tasks within a factory.

[0135] The "application installed on the robot" is software that is installed on the robots used in the factory and is used to collect opinions and issues through dialogue with workers.

[0136] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate appropriate responses or results based on input data.

[0137] "Means to improve the work environment and increase efficiency" is a function that implements specific measures to improve the work environment and increase work efficiency based on collected opinions and issues.

[0138] A system for implementing this invention includes means having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for planning countermeasures for issues highlighted by the two-way dialogue, means having an application installed on a robot for collecting the opinions and issues of workers working in a factory, means for generating appropriate responses to inputs from workers using a generative AI model, and means for improving the work environment and increasing efficiency based on the responses.

[0139] Program processing explanation

[0140] The server uses a Python program and the OpenAI API to utilize a generative AI model (e.g., GPT-3 (registered trademark)). Robots in the factory collect input from workers and send it to the server. The server uses the generative AI model to generate an appropriate response to the worker's input and sends the response back to the robot. The robot communicates the generated response to the worker.

[0141] Hardware and software used

[0142] Hardware: Robots in factories (e.g. collaborative robots)

[0143] Software: Python, OpenAI API

[0144] Data processing and calculation

[0145] Data processing: Input from the human is sent as prompts to the generative AI model.

[0146] Data computation: Generative AI models generate appropriate responses based on worker input.

[0147] Specific examples

[0148] For example, if a worker types, "I feel like the work environment is a little cold lately. Could you please turn up the heating?", the server will use the generative AI model to generate a response that reads, "Thank you for your feedback on the temperature of the work environment. I will report to the relevant department about adjusting the heating."

[0149] Prompt Sentence Examples

[0150] Dialogue with Workers: The working environment has been a little cold lately. Could you please turn up the heating?

[0151] Generate an appropriate response.

[0152] In this way, it is possible to efficiently collect the opinions and issues of workers working in the factory and improve the work environment and increase efficiency.

[0153] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0154] Step 1:

[0155] The user (worker) inputs opinions and issues to the robot. The input data is collected through the robot's sensors and interface. An example of input data is, "I feel like the working environment is a little cold lately. Could you please turn up the heating?"

[0156] Step 2:

[0157] The robot sends the collected input data to a server, which then analyzes the data and converts it into a format suitable for the generative AI model. During this conversion process, the input data is formatted as a prompt sentence.

[0158] Step 3:

[0159] The server sends a prompt to the generative AI model (e.g., GPT-3). The generative AI model generates an appropriate response based on the prompt. For example, if the prompt is "Dialogue with worker: I feel like the work environment is a little cold recently. Could you please turn up the heating?", the generative AI model will generate the response "Thank you for your feedback on the temperature of the work environment. I will report to the relevant department about adjusting the heating."

[0160] Step 4:

[0161] The server receives the response from the generative AI model and sends it to the robot, where it converts the response data into a format that the robot can understand.

[0162] Step 5:

[0163] The robot communicates the response received from the server to the worker. The robot presents the generated response to the worker using audio output and a display. For example, the robot may respond by voice, "Thank you for your feedback on the temperature of the work environment. We will report to the relevant department about adjusting the heating."

[0164] Step 6:

[0165] The server stores the collected opinions, challenges, and generated responses in a database, which is later used for analysis to improve the work environment and streamline it.

[0166] Step 7:

[0167] Based on the stored data, the server will propose specific measures to improve the work environment and increase efficiency, for example, by reporting proposals for adjusting the temperature of the work environment to the relevant department.

[0168] By following the steps above, it is possible to efficiently collect the opinions and issues of workers working in the factory, thereby improving the work environment and increasing efficiency.

[0169] Example 2

[0170] Next, a description will be given of Example 2 of Form 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."

[0171] With conventional interactive survey systems, it was difficult to effectively analyze employee feedback and develop specific countermeasures. Furthermore, there was a lack of means to quickly notify the results of the feedback analysis and implement countermeasures that would contribute to creating a comfortable working environment for employees and improving business performance.

[0172] 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.

[0173] In this invention, the server includes means for having an interactive survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for collecting feedback from users and analyzing the feedback using a generative AI model, and means for formulating specific countermeasures based on the analysis results and notifying the users. This makes it possible to effectively analyze feedback from employees and quickly formulate and notify specific countermeasures.

[0174] The "interactive survey function" is a function that collects and analyzes information through dialogue with the user.

[0175] "Two-way interaction" refers to an interaction in which the user and the system exchange information with each other.

[0176] "Issues" are problems or areas for improvement identified based on feedback from users.

[0177] "Countermeasures" are specific actions or measures implemented to address identified issues.

[0178] A "generative AI model" is a model that uses artificial intelligence to analyze data and generate results.

[0179] A "prompt" is a textual instruction that is input to a generative AI model.

[0180] "Feedback" refers to information such as opinions, impressions, and reports provided by users.

[0181] "Analysis" is the process of finding meaning and patterns based on collected data.

[0182] "Notification" refers to the act of informing the user of the analysis results and countermeasures.

[0183] MODE FOR CARRYING OUT THE INVENTION

[0184] The present invention is a system that visualizes the true nature of employees, identifies issues through two-way dialogue, and proposes measures to address those issues. A specific embodiment of this system will be described below.

[0185] System configuration

[0186] 1. Interactive Survey Feature

[0187] The server has an interactive survey function, which collects and analyzes information through dialogue with users. Specifically, this function is realized by a chatbot using artificial intelligence.

[0188] 2. Two-way dialogue function

[0189] The server uses an interactive survey function to engage in a two-way dialogue with the user, through which feedback is collected from the user.

[0190] 3. Generative AI Models

[0191] The server inputs the collected feedback into a generative AI model (e.g., OpenAI's GPT-4), which analyzes the feedback and identifies challenges.

[0192] 4. Countermeasure planning function

[0193] The server then proposes countermeasures based on the issues identified by the generative AI model, which contribute to creating a comfortable working environment for employees and improving business performance.

[0194] 5. Notification function

[0195] The server notifies the user of the proposed measures, which are sent via the terminal, allowing the user to check the proposed measures.

[0196] Specific examples

[0197] For example, if a user enters feedback such as "Recently, my workload has increased and I've been working a lot of overtime," the device will send this feedback to the server. The server inputs the received feedback into a generative AI model, which then analyzes it to determine that "a review of the business process is necessary." Based on the results of this analysis, the server will propose specific measures, such as reviewing the business process and allocating additional personnel, and notify the user. The user can then check these measures through their device and take the necessary action.

[0198] Prompt Sentence Examples

[0199] "Recently, my workload has increased and I've been working a lot of overtime. Please suggest some solutions to this."

[0200] In this way, the server can effectively analyze feedback from users and quickly plan and notify specific countermeasures.

[0201] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0202] Program processing flow

[0203] Step 1: User Enters Feedback

[0204] Users input feedback about their work environment and work processes into the terminal. For example, they can input specific details such as, "Recently, the workload has increased and I've been working a lot of overtime."

[0205] Input: User feedback text

[0206] Output: Feedback data entered into the terminal

[0207] Step 2: The device sends feedback to the server

[0208] The terminal transmits the feedback input by the user to the server, where the feedback is converted into an appropriate format and then transmitted to the server.

[0209] Input: Feedback data entered into the terminal

[0210] Output: Feedback data sent to the server

[0211] Step 3: The server receives the feedback and inputs it as a prompt to the generative AI model.

[0212] The server receives feedback sent from the device and inputs it as a prompt to a generative AI model (e.g., OpenAI's GPT-4).

[0213] Input: Feedback data sent to the server

[0214] Output: The prompt sentence that is fed into the generative AI model

[0215] Step 4: Generative AI model analyzes feedback and identifies issues

[0216] The generative AI model analyzes the input prompt and identifies issues based on the feedback. For example, based on the feedback that "the workload has increased and overtime is becoming more frequent," it determines that a review of work processes and the allocation of additional personnel are necessary.

[0217] Input: The prompt given to the generative AI model

[0218] Output: Identified issues

[0219] Step 5: The server develops a plan of action based on the identified issues

[0220] The server then proposes countermeasures based on the issues identified by the generative AI model, such as reviewing business processes, allocating additional personnel, and providing education and training.

[0221] Input: Identified issues

[0222] Output: Planned countermeasures

[0223] Step 6: The server notifies the user of the proposed measures

[0224] The server notifies the user of the proposed measures, which are sent via the terminal, allowing the user to check the proposed measures.

[0225] Input: Proposed measures

[0226] Output: The action notified to the user

[0227] Specific examples of operation

[0228] For example, if a user enters feedback such as "Recently, my workload has increased and I've been working a lot of overtime," the device will send this feedback to the server. The server inputs the received feedback into a generative AI model, which then analyzes it to determine that "a review of the business process is necessary." Based on the results of this analysis, the server will propose specific measures, such as reviewing the business process and allocating additional personnel, and notify the user. The user can then check these measures through their device and take the necessary action.

[0229] (Application example 2)

[0230] Next, a description will be given of Application Example 2 of Form 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."

[0231] In conventional factory environments, it was difficult to effectively collect feedback from workers and to develop prompt and appropriate improvement measures based on that feedback. Furthermore, delays in improving the work environment and reviewing business processes led to problems such as a decline in work efficiency and a worsening workplace environment. This could lead to a decline in worker motivation and productivity, ultimately negatively impacting business performance.

[0232] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0233] In this invention, the server includes a means for having an interactive ES survey function for visualizing the true nature of employees, a means for conducting two-way dialogue using the interactive ES survey function, a means for formulating countermeasures for issues revealed by the two-way dialogue, a means for collecting feedback from workers in the factory, a means for generating improvement measures using a generative AI model based on the collected feedback, and a means for presenting the generated improvement measures to the workers. This makes it possible to effectively collect feedback from workers and quickly formulate appropriate improvement measures. This allows for the work environment to be improved and business processes to be reviewed quickly, thereby improving work efficiency and the workplace environment.

[0234] The "interactive ES survey function" is a function that collects and analyzes information through two-way dialogue in order to visualize the true nature of employees.

[0235] "Two-way dialogue" is a form of communication in which the system and the user exchange information with each other.

[0236] "Means for planning countermeasures to issues" is a function for devising specific improvement measures and solutions based on issues that have been highlighted through two-way dialogue.

[0237] "Means for collecting feedback" is a function for collecting information such as opinions, impressions, and problems from workers.

[0238] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate new information or suggestions from input data.

[0239] "Means for generating improvement measures" is a function that uses a generative AI model to devise specific improvement measures based on collected feedback.

[0240] "Means for presenting improvement measures" is a function that communicates the generated improvement measures to workers in an easy-to-understand manner.

[0241] The system for implementing this invention includes a series of processes that collect feedback from workers in a factory, generate improvement measures using a generative AI model based on the feedback, and present the measures to the workers. A specific embodiment of this system will be described below.

[0242] Hardware and Software Configuration

[0243] 1. Hardware:

[0244] Robot: A robot that interacts with workers in a factory.

[0245] Server: A server for running generative AI models and processing data.

[0246] 2. Software:

[0247] Interactive ES survey function: An interactive survey function that visualizes the true nature of employees. Implemented as a chatbot using artificial intelligence.

[0248] Generative AI models: Use generative AI models such as OpenAI's GPT-3 to generate improvements based on feedback.

[0249] Data collection and presentation capabilities: Software for collecting feedback from workers and presenting generated improvement recommendations.

[0250] Data processing and calculation flow

[0251] 1. Gathering Feedback:

[0252] The robot interacts with workers and collects feedback about the work environment and work processes.

[0253] The collected feedback is sent to a server.

[0254] 2. Generating improvement measures using generative AI models:

[0255] The server inputs the collected feedback into a generative AI model.

[0256] The generative AI model generates specific improvement measures based on the input feedback.

[0257] The generated remediation measures are stored on the server.

[0258] 3. Proposal of improvement measures:

[0259] The server sends the generated remedial measures to the robot.

[0260] The robot will suggest improvements to the worker and engage in additional dialogue as needed.

[0261] Specific examples

[0262] For example, if a worker gives feedback that "the workspace is too small and inefficient," the generative AI model will generate the following improvement measures:

[0263] We will review the layout of your workspace and propose new arrangements to ensure efficient movement.

[0264] These improvement measures are presented to workers through the robot and can be used to improve the working environment.

[0265] Prompt Sentence Examples

[0266] Below is an example of a prompt that can be fed into a generative AI model:

[0267] Based on the feedback below, please suggest ways to improve the factory environment.

[0268] Feedback: The workspace is small and inefficient

[0269] In this way, the system can effectively collect feedback from workers, develop quick and appropriate improvement measures, and improve the working environment and review business processes.

[0270] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0271] Step 1:

[0272] The robot interacts with workers and collects feedback about the work environment and work processes.

[0273] Input: Verbal or textual feedback from the worker.

[0274] Output: Collected feedback data.

[0275] How it works: The robot uses a built-in microphone and text input interface to collect feedback from workers in real time, which is then sent to a server as text data.

[0276] Step 2:

[0277] The server generates prompt sentences to input the collected feedback into the generative AI model.

[0278] Input: Collected feedback data.

[0279] Output: The prompt sentence to be input to the generative AI model.

[0280] Specific operation: The server analyzes the feedback data and generates an appropriate prompt. For example, in response to the feedback "The work space is small and inefficient," the server generates the prompt "Please suggest improvements to the factory environment based on the following feedback. Feedback: The work space is small and inefficient."

[0281] Step 3:

[0282] The server inputs a prompt sentence into the generative AI model and generates an improvement plan.

[0283] Input: The generated prompt statement.

[0284] Output: The improvements generated by the generative AI model.

[0285] Specific operation: The server inputs the generated prompt sentence into a generative AI model such as OpenAI's GPT-3. The generative AI model generates specific improvement measures based on the prompt sentence and returns them to the server.

[0286] Step 4:

[0287] The server sends the generated remedial measures to the robot.

[0288] Input: The improvements generated by the generative AI model.

[0289] Output: Remediation data sent to the robot.

[0290] Specific operation: The server sends the generated improvement measures to the robot as text data. The robot receives this data and prepares to present it to the worker.

[0291] Step 5:

[0292] The robot will suggest improvements to the worker and engage in additional dialogue as needed.

[0293] Input: Remediation data sent from the server.

[0294] Output: Suggested improvements and additional feedback to the worker.

[0295] Specific operation: The robot presents the received improvement measures to the worker via voice or text. If the worker provides additional feedback, the robot collects the feedback again and sends it to the server, thereby further improving the accuracy of the improvement measures.

[0296] Example 3

[0297] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0298] With conventional employee feedback systems, it was difficult to effectively identify employees' fundamental issues and develop appropriate countermeasures. Furthermore, feedback data was often collected and analyzed manually, making it difficult to develop efficient countermeasures. This resulted in issues such as the inability to create a comfortable working environment for employees or to fully improve business performance.

[0299] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0300] In this invention, the server includes means for having an interactive survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for collecting feedback data from employees, means for pre-processing the collected feedback data, means for extracting and analyzing keywords from the pre-processed data, means for generating countermeasures based on the analysis results, and means for presenting and implementing the generated countermeasures. This makes it possible to efficiently collect and analyze employee feedback and quickly formulate and implement appropriate countermeasures.

[0301] The "interactive survey function" is a function for collecting employee feedback and clarifying issues through two-way communication.

[0302] "Two-way dialogue" is a form of communication in which employees and systems exchange information with each other.

[0303] "Issue solutions" are specific action plans or measures to solve specific problems based on employee feedback.

[0304] "Feedback data" refers to information such as opinions, impressions, and evaluations provided by employees.

[0305] "Preprocessing" refers to processes such as cleaning, tokenizing, and removing stop words from collected feedback data to make it easier to analyze.

[0306] "Keyword extraction" is the process of identifying important words and phrases from feedback data.

[0307] "Analysis" is the process of understanding the content of the feedback and finding patterns and trends based on extracted keywords and data.

[0308] "Generating countermeasures" is the process of proposing specific solutions and improvements based on the analysis results.

[0309] "Presenting" is the act of showing the generated countermeasure plan to the user.

[0310] "Implementation" is the process of actually putting the proposed countermeasures into action.

[0311] This invention is a system that efficiently collects and analyzes feedback from employees and promptly plans and implements appropriate measures. A specific embodiment of this system will be described below.

[0312] The server has an interactive survey function that visualizes the true nature of employees. This interactive survey function uses a chatbot with artificial intelligence to collect feedback from employees. For example, feedback can be collected through an internal survey system, email, or chat tool.

[0313] The collected feedback data is pre-processed by the server, which includes data cleaning (removing unnecessary characters and symbols), tokenization (dividing sentences into words), and stop-word removal (removing frequent but meaningless words). This process is performed using Python libraries such as NLTK and spaCy.

[0314] The server extracts and analyzes keywords from the preprocessed data. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) and word clouds to identify frequently occurring keywords in the feedback. It checks whether there are many keywords related to "difficulty in communication," in particular.

[0315] Based on the analysis results, the server generates countermeasures. It uses a generative AI model to propose appropriate countermeasures. For example, the following prompt sentence is input into the generative AI model:

[0316] "Analyze employee feedback and generate countermeasures, especially when there is a lot of feedback about 'difficulty in communication.' Specific countermeasures include 'offering training to improve communication skills' and 'establishing open spaces.'"

[0317] The generated countermeasures are presented to the user via the terminal. The user can review the countermeasures and implement them as necessary. For example, they can arrange a training program to implement "training to improve communication skills." This will help create a comfortable working environment for employees and improve business performance.

[0318] For example, consider the following feedback from an employee:

[0319] "I feel like communication within the team hasn't been going well recently."

[0320] "There are few opportunities to share project progress."

[0321] "Communication is difficult when working remotely."

[0322] The server collects this feedback and analyzes it using NLP technology. As a result of the analysis, it is found that there is a lot of feedback about "difficulty in communication." Therefore, the server generates the following countermeasures:

[0323] "Provide training to improve communication skills."

[0324] "We will set up an open space and create a place where employees can communicate freely with each other."

[0325] The user can check these measures and put them into practice to create a comfortable working environment for employees and improve business performance. The flow of the specific process in the third embodiment will be described with reference to FIG.

[0326] Step 1:

[0327] The server collects feedback data from employees. The input includes feedback from the company's internal survey system, email, and chat tools. This data is collected centrally and stored in a database. The output is the collected feedback data.

[0328] Step 2:

[0329] The server preprocesses the collected feedback data. The input is the collected feedback data. Specific operations include cleaning the data (removing unnecessary characters and symbols), tokenizing (dividing sentences into words), and removing stop words (removing frequent but meaningless words). The output is the preprocessed data.

[0330] Step 3:

[0331] The server extracts and analyzes keywords from the preprocessed data. The input is the preprocessed data. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) and word clouds to identify frequently occurring keywords in the feedback. The output is the extracted keywords and their frequency information.

[0332] Step 4:

[0333] The server generates countermeasures based on the analysis results. The inputs are the extracted keywords and their frequency information. Specifically, it uses a generative AI model to suggest appropriate countermeasures. For example, the following prompt is input into the generative AI model: "Analyze feedback from employees and generate countermeasures in cases where there is a lot of feedback, especially regarding 'difficulty in communication.' Specific countermeasures include 'providing training to improve communication skills' and 'establishing open spaces.'" The generated countermeasures are obtained as output.

[0334] Step 5:

[0335] The terminal presents the generated countermeasure plan to the user. The input is the generated countermeasure plan. The specific operation is to display the countermeasure plan on the user's screen. The output is a state in which the user can check the countermeasure plan.

[0336] Step 6:

[0337] The user checks the proposed countermeasures and implements them as necessary. The input is the proposed countermeasures. A specific action, for example, arranging a training program to implement "training to improve communication skills," is the output: the countermeasures are implemented, creating a comfortable working environment for employees and improving performance.

[0338] (Application example 3)

[0339] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0340] Conventional employee feedback systems lack specific measures to address communication difficulties, making it difficult to create a comfortable working environment for employees and contribute to improving business performance. In addition, feedback collection and analysis are often done manually, making it difficult to develop efficient measures.

[0341] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0342] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for collecting feedback and proposing countermeasures based on the analysis results, means for providing training content for improving communication skills based on the proposed countermeasures, and means for proposing the establishment of open spaces and layout changes. This makes it possible to efficiently collect and analyze employee feedback and quickly formulate and implement specific countermeasures.

[0343] The "Interactive ES Survey Function" is a function that conducts an engagement survey in an interactive format in order to visualize the true nature of employees.

[0344] "Two-way dialogue" is a process in which employees and the system exchange information with each other using the interactive ES survey function.

[0345] "Means for formulating countermeasures for issues" is a function for devising specific solutions to issues that have been highlighted through two-way dialogue.

[0346] "Means for collecting feedback" is a function for efficiently gathering opinions and feedback from employees.

[0347] "Means for proposing measures based on analysis results" is a function for analyzing collected feedback and proposing appropriate measures based on the results.

[0348] "Means of providing training content to improve communication skills" is a function that provides educational materials and programs to improve employees' communication abilities.

[0349] "Means to propose the creation of open spaces and layout changes" is a function that makes suggestions to improve the design and layout of workspaces in order to create an environment where employees can work comfortably.

[0350] A system for implementing this invention includes a server having an interactive ES survey function for visualizing the true nature of employees, a terminal for conducting two-way dialogue using the interactive ES survey function, and a program for planning countermeasures for issues that are highlighted by the two-way dialogue.

[0351] The server is equipped with a chatbot that uses artificial intelligence to collect feedback from employees. The collected feedback is analyzed within the server, and issues such as difficulty in communication are identified. Based on this, the server proposes specific measures.

[0352] The terminal is a device such as a smartphone or PC that provides an interface for employees to enter feedback. The feedback entered from the terminal is sent to a server and analyzed.

[0353] Based on the analysis results, the server provides training content to improve communication skills. It also proposes the creation of open spaces and layout changes, thereby creating a comfortable working environment for employees and improving business performance.

[0354] As a concrete example, the following feedback may be collected:

[0355] "It's difficult to communicate with robots."

[0356] "It's hard to communicate instructions while working"

[0357] "There are a lot of mistakes due to lack of communication."

[0358] Based on this feedback, the following prompt sentences are input into the generative AI model:

[0359] Example prompt sentence:

[0360] Feedback content:

[0361] 1. It's difficult to communicate with robots

[0362] 2. It's difficult to communicate instructions while working

[0363] 3. Lack of communication leads to many mistakes

[0364] Based on this feedback, suggest appropriate measures.

[0365] By inputting this prompt into a generative AI model, the server can obtain more specific countermeasures, such as providing training programs to improve communication skills or changing the layout of the workspace.

[0366] In this way, employee feedback can be collected and analyzed efficiently, and specific measures can be quickly developed and implemented.

[0367] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0368] Step 1:

[0369] The user uses the terminal to enter feedback.

[0370] Input: Feedback entered by the user into the device (e.g., "It's difficult to communicate with the robot").

[0371] Output: Feedback data sent from the device to the server.

[0372] Specific actions: The user enters feedback through the interface of a smartphone or computer and presses the send button.

[0373] Step 2:

[0374] The server collects the feedback.

[0375] Input: Feedback data sent from the device.

[0376] Output: Feedback data stored on the server.

[0377] Specific operation: The server receives the feedback data sent from the terminal and stores it in a database.

[0378] Step 3:

[0379] The server analyzes the feedback.

[0380] Input: Feedback data stored on the server.

[0381] Output: Analysis results (e.g., issues related to communication difficulties).

[0382] What it does: The server uses natural language processing (NLP) algorithms to analyze the feedback data and extract specific keywords and phrases.

[0383] Step 4:

[0384] The server generates a prompt based on the parsing results.

[0385] Input: Analysis results.

[0386] Output: The generated prompt statement.

[0387] Specific operation: Based on the analysis results, the server automatically generates prompt sentences to input into the generative AI model.

[0388] Example prompt sentence:

[0389] Feedback content:

[0390] 1. It's difficult to communicate with robots

[0391] 2. It's difficult to communicate instructions while working

[0392] 3. Lack of communication leads to many mistakes

[0393] Based on this feedback, suggest appropriate measures.

[0394] Step 5:

[0395] The server inputs a prompt sentence into the generative AI model and obtains countermeasure proposals.

[0396] Input: The generated prompt statement.

[0397] Output: Countermeasure proposals from the generative AI model.

[0398] Specific operation: The server inputs a prompt sentence into the generative AI model and obtains the countermeasures returned by the model.

[0399] Step 6:

[0400] The server proposes specific countermeasures based on the proposed countermeasures.

[0401] Input: Countermeasure proposals from a generative AI model.

[0402] Output: Specific countermeasure proposals (e.g., training content to improve communication skills, proposals for establishing open spaces).

[0403] Specific operation: The server proposes specific countermeasures to employees based on the countermeasures obtained from the generative AI model.

[0404] Step 7:

[0405] The user checks and implements the proposed measures.

[0406] Input: Specific measures proposed by the server.

[0407] Output: The results of the measures taken (e.g., attending training, creating open spaces).

[0408] Specific actions: The user checks the measures proposed by the server and takes action as necessary, for example, participating in training or setting up an open space.

[0409] 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.

[0410] "Example 1"

[0411] One embodiment of the present invention is a system that incorporates an emotion engine. This system has an interactive ES survey function that visualizes the true nature of employees, and uses the interactive ES survey function to conduct two-way dialogue. Furthermore, the emotion engine is used to analyze emotions from text input by employees, and the results are used as part of the dialogue. Specifically, if an employee inputs the text "Work didn't go well today," the emotion engine analyzes the text for emotions such as "disappointment" or "disappointment." Then, based on the analysis results, the interactive ES survey function provides an appropriate response to the employee.

[0412] "Example 2"

[0413] Another embodiment of the present invention is a system that proposes countermeasures based on the results of emotion analysis by an emotion engine. This system grasps changes in employees' emotions in real time and proposes countermeasures in response to those changes. Specifically, if the system senses that an employee's emotions are leaning toward "stress" or "anxiety," it proposes countermeasures such as "providing stress management training" or "strengthening the mental health support system."

[0414] "Example 3"

[0415] Another embodiment of the present invention is a system that combines an emotion engine with an interactive employee satisfaction survey function. This system simultaneously grasps employees' emotions and opinions and combines them to gain a deeper understanding. Specifically, it simultaneously grasps an employee's opinion that "I'm stressed because I have too much work" and their feelings of "stress," and based on the results, it proposes measures such as "adjusting the amount of work" or "introducing tools to improve work efficiency."

[0416] The processing flow of each embodiment will be described below.

[0417] "Example 1"

[0418] Step 1: Employees enter text through the interactive ES survey function.

[0419] Step 2: The emotion engine analyzes the emotions from the employee's text input.

[0420] Step 3: The interactive ES survey function uses the analysis results of the emotion engine to respond to employees.

[0421] "Example 2"

[0422] Step 1: The emotion engine identifies changes in employee emotions in real time.

[0423] Step 2: The emotion engine develops measures that correspond to changes in emotions.

[0424] Step 3: The planned measures are implemented to improve employee sentiment.

[0425] "Example 3"

[0426] Step 1: Employees enter their feelings and opinions through the interactive ES survey function.

[0427] Step 2: The emotion engine analyzes the emotions from the employee's text input.

[0428] Step 3: The interactive ES survey function combines the analysis results of the emotion engine with the opinions of employees to develop countermeasures.

[0429] Step 4: The proposed measures are implemented to improve employee sentiment and reflect their opinions.

[0430] Example 1

[0431] Next, a description will be given of Example 1 of Form 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."

[0432] With conventional interactive ES survey systems, it was difficult to accurately grasp employees' opinions and feelings, making it difficult to formulate appropriate measures. Furthermore, the system lacked the functionality to analyze employees' feelings and adjust responses based on them, making it difficult to fully visualize the true nature of employees. This made it difficult to effectively implement measures that would contribute to creating a comfortable working environment for employees and improving business performance.

[0433] 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.

[0434] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating measures for issues highlighted by the two-way dialogue, means for receiving user input, means for analyzing the received input, means for generating an appropriate response based on the analysis results, means for performing emotion analysis, means for adjusting the response based on the emotion analysis results, and means for displaying the adjusted response to the user. This makes it possible to accurately grasp the opinions and emotions of employees and to formulate appropriate measures.

[0435] The "interactive ES survey function" is a function that collects employees' opinions and feelings and makes the true nature of employees visible through two-way dialogue.

[0436] "Two-way interaction" is a form of interaction in which a user and a system exchange information with each other, and is a process in which the system returns a response to a user's input.

[0437] "Means of planning countermeasures to issues" is the function of coming up with appropriate solutions to the issues employees face that have been highlighted through two-way dialogue.

[0438] "Means for receiving user input" refers to a function that receives text or data sent by a user to the system through a terminal.

[0439] The "means for analyzing received input" is a function for analyzing text or data received from a user and understanding its content.

[0440] The "means for generating an appropriate response" is a function for generating an appropriate reply to the user based on the analysis results.

[0441] The "means for performing emotion analysis" is a function for analyzing emotions from the user's text input and identifying those emotions.

[0442] The "means for adjusting the response based on the emotion analysis result" is a function that takes into account the emotion analysis result and appropriately changes the response to the user.

[0443] The "means for displaying the adjusted response to the user" is a function for transmitting the adjusted response to the user's terminal and displaying it on the screen.

[0444] This invention is an interactive ES survey system that visualizes the true nature of employees. This system combines an AI-based chatbot with an emotion analysis engine to collect opinions and emotions through two-way dialogue with employees and then formulates appropriate measures.

[0445] Hardware and software used

[0446] Hardware: Servers, terminals (PCs, smartphones)

[0447] Software: Chatbots (e.g., Dialogflow), sentiment analysis engines (e.g., IBM Watson® Tone Analyzer)

[0448] System Overview

[0449] 1. User input:

[0450] The user uses a device to input text into the chatbot, for example, "Work didn't go well today."

[0451] 2. Server receives input:

[0452] The server receives input from the user and passes it to the chatbot, which then converts the input into JSON format and sends it to the chatbot's API.

[0453] 3. Chatbot response generation:

[0454] The chatbot generates an initial response to the user's input. For example, if the user inputs "Work didn't go well today," the chatbot generates a response such as "That must have been tough."

[0455] 4. Emotion analysis:

[0456] The server sends the chatbot's initial response and the user's input to the emotion analysis engine, which analyzes the user's emotions from the text. Specifically, it extracts emotions such as "disappointment" or "disappointment" from the text "Work didn't go well today."

[0457] 5. Adjusting the response:

[0458] The chatbot receives the results of the sentiment analysis and adjusts its response accordingly. For example, if the sentiment analysis results in "disappointment" or "disappointment," the chatbot might change its response to something like, "You've had a tough day. Is there anything I can help you with?"

[0459] 6. Displaying the response to the user:

[0460] The server sends the chatbot's final response to the user's device and displays it to the user, such as a message like, "You've had a rough day. Is there anything I can help you with?"

[0461] Examples and prompts

[0462] Examples:

[0463] User input: "Work didn't go well today."

[0464] Sentiment analysis engine analysis results: "Disappointed", "Disappointed"

[0465] The chatbot responds: "You've had a tough day. Is there anything I can help you with?"

[0466] Example prompt for a generative AI model:

[0467] If a user types "Work didn't go well today," use a sentiment analysis engine to analyze the sentiment and generate an appropriate response based on that.

[0468] This system makes it possible to accurately grasp the opinions and feelings of employees and devise appropriate measures, thereby contributing to creating a comfortable working environment for employees and improving business performance.

[0469] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0470] Step 1:

[0471] A user inputs text into the chatbot using a terminal, for example, "Work didn't go well today." The input text is sent from the terminal to the server.

[0472] Step 2:

[0473] The server receives input from the user. It converts the received text data into JSON format and sends it to the chatbot's API. The input is the user's text, and the output is JSON format data.

[0474] Step 3:

[0475] The chatbot generates an initial response to the user input received from the server. For example, it generates a response such as "That must have been difficult." The input is the user's text data in JSON format, and the output is the initial response text.

[0476] Step 4:

[0477] The server sends the chatbot's initial response and the user's input to the sentiment analysis engine. The sentiment analysis engine analyzes emotions from the user's text. Specifically, it extracts emotions such as "disappointment" or "disappointment" from the text "Work didn't go well today." The input is the user's text and the chatbot's initial response, and the output is the sentiment analysis result.

[0478] Step 5:

[0479] The chatbot receives the results of the sentiment analysis and adjusts the response. For example, if the result of the sentiment analysis is "disappointed" or "disappointed," the chatbot changes the response to something like, "You've had a tough day. Is there anything I can help you with?" The input is the sentiment analysis result, and the output is the adjusted response text.

[0480] Step 6:

[0481] The server sends the chatbot's final response to the user's device, which receives the response and displays it on its screen. For example, the message might read, "You've had a rough day. Is there anything I can help you with?" The input is the tailored response text, and the output is the message displayed on the user's device.

[0482] (Application example 1)

[0483] Next, a description will be given of Application Example 1 of Embodiment 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."

[0484] While conventional interactive ES survey systems can grasp employee opinions and issues, it is difficult to analyze emotions and take appropriate action. Furthermore, while there is a need to understand the emotions and opinions of factory workers in real time and take appropriate action, there was no effective way to achieve this. This could lead to a decline in worker satisfaction and work efficiency.

[0485] 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.

[0486] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for planning measures for issues highlighted by the two-way dialogue, means for analyzing the emotions and opinions of workers and taking appropriate measures, means for generating responses to inputs by workers using a generative AI model, and means for responding to encouragement to workers based on the results of the emotion analysis. This makes it possible to grasp the emotions and opinions of workers in real time and take appropriate measures.

[0487] The "interactive ES survey function" is a function that allows two-way dialogue with employees in order to visualize their true nature.

[0488] "Two-way dialogue" refers to a form of dialogue in which the system and employees exchange information with each other.

[0489] "Measures to address issues" means formulating solutions to issues that employees face that have been highlighted through two-way dialogue.

[0490] "Means for analyzing emotions and opinions" refers to technology for analyzing emotions and opinions from text input by workers.

[0491] A "generative AI model" is a model that uses artificial intelligence to generate appropriate responses to worker input.

[0492] The "emotion analysis result" is the result of the emotion analyzed from the text input of the worker.

[0493] An "encouraging response" is a response to encourage a worker based on the emotion analysis results.

[0494] A system for implementing this invention includes means having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for planning countermeasures for issues highlighted by the two-way dialogue, means for analyzing the emotions and opinions of workers and taking appropriate action, means for generating responses to inputs by workers using a generative AI model, and means for making responses that encourage workers based on the results of the emotion analysis.

[0495] The server first provides an interactive employee satisfaction survey function to visualize the true nature of employees. This function uses a chatbot that uses artificial intelligence to hold two-way conversations with employees. For example, if an employee types, "Work didn't go well today," the chatbot receives the text and uses an emotion engine to analyze emotions such as "disappointment" or "disappointment."

[0496] The server then uses a generative AI model to generate an appropriate response to the employee's input. This model uses advanced natural language processing techniques, such as OpenAI's GPT-3. For example, the server can respond to an employee's input with a response like, "You've had a tough day. Let me know if there's anything I can help you with."

[0497] Furthermore, the server responds to encourage the worker based on the results of emotion analysis. This makes it possible to grasp the worker's emotions and opinions in real time and respond appropriately. For example, if a worker inputs "Today's work isn't going well," the system will generate a response such as "Today was tough. Please let me know if there's anything I can do to help."

[0498] The hardware used is a robot working in a factory, and the software uses Python, the TextBlob library, and OpenAI's GPT-3 API, which allows for real-time analysis of worker sentiment and opinions and appropriate responses.

[0499] An example of a prompt is as follows:

[0500] "A worker said: 'Work is not going well today.

[0501] Please generate an appropriate response."

[0502] By feeding this prompt to GPT-3, it can generate an appropriate response, such as, "You've had a tough day. Let me know if there's anything I can help you with."

[0503] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0504] Step 1:

[0505] The server receives the employee's input. The user (employee) inputs text, for example, "Work didn't go well today." This input is sent to the server.

[0506] Step 2:

[0507] The server passes the received text input to the emotion engine for sentiment analysis. Specifically, it uses the TextBlob library to calculate the polarity and subjectivity of the input text. The input is the employee's text, and the output is the sentiment analysis results (polarity and subjectivity).

[0508] Step 3:

[0509] The server creates a prompt sentence based on the sentiment analysis results and passes it to the generative AI model. Specifically, it generates a prompt sentence like the following: "The worker said: Work isn't going well today. Please generate an appropriate response." The input is the sentiment analysis result and the employee's text, and the output is the generated prompt sentence.

[0510] Step 4:

[0511] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate an appropriate response based on the prompt sentence. The generative AI model receives the prompt sentence as input and outputs an appropriate response in text format. The input is the prompt sentence, and the output is the generated response text.

[0512] Step 5:

[0513] The server returns the generated response text to the user (employee). Specifically, it sends the generated response text to the employee's terminal and displays it. The input is the generated response text, and the output is the response displayed on the employee's terminal.

[0514] Step 6:

[0515] The server stores the sentiment analysis results and generated responses in a database, making them available for later analysis and improvement. The input is the sentiment analysis results and generated responses, and the output is the data stored in the database.

[0516] Example 2

[0517] Next, a description will be given of Example 2 of Form 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."

[0518] With conventional employee feedback collection systems, it was difficult to fully grasp employees' emotions and specific issues, making it difficult to plan appropriate measures. Furthermore, it was not possible to respond to changes in employees' emotions in real time, making it difficult to take prompt measures to reduce stress and anxiety. This resulted in insufficient measures to create a comfortable working environment for employees and improve business performance.

[0519] 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.

[0520] In this invention, the server includes means for having an interactive survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for analyzing employees' emotions using an emotion analysis engine, means for sending prompt messages to the generative AI model based on the analysis results, and means for receiving countermeasures from the generative AI model and presenting them to employees. This makes it possible to analyze emotions based on employee feedback and quickly formulate and present appropriate countermeasures.

[0521] The "interactive survey function" is a function that collects employee feedback and clarifies employees' true nature and challenges through two-way communication.

[0522] "Two-way dialogue" is a form of communication in which the system and employees exchange information with each other.

[0523] "Means for planning countermeasures to issues" is the function of coming up with appropriate solutions to issues that have been identified through two-way dialogue.

[0524] An "emotion analysis engine" is software that analyzes employee feedback and dialogue data to identify employee emotions.

[0525] A "generative AI model" is an artificial intelligence model that generates appropriate countermeasures or solutions based on a given prompt.

[0526] A "prompt" is an instruction given to a generative AI model to generate a solution for a specific problem or situation.

[0527] "Means of receiving countermeasures and presenting them to employees" is a function for communicating the countermeasures obtained from the generative AI model to employees.

[0528] This invention is a system that analyzes emotions based on employee feedback and quickly proposes and presents appropriate measures. This system works in cooperation with three parties: a server, a terminal, and a user.

[0529] Hardware and software used

[0530] Hardware: Servers, terminals (PCs, smartphones)

[0531] Software: Generative AI model, sentiment analysis engine, database management system (DBMS)

[0532] System Overview

[0533] 1. A user accesses the system using a terminal.

[0534] 2. The device sends the user feedback to the server.

[0535] 3. The server stores the feedback in a database and analyzes the feedback using a sentiment analysis engine.

[0536] 4. Based on the analysis results, the server sends a prompt to the generative AI model and develops countermeasures.

[0537] 5. The server receives the countermeasures from the generative AI model and presents them to the user.

[0538] Specific examples

[0539] For example, if employee A sends feedback saying, "My work has been very stressful lately," the system will operate as follows:

[0540] 1. The user (Employee A) sends feedback from the terminal saying, "My work has been very stressful recently."

[0541] 2. The device sends this feedback to the server.

[0542] 3. The server stores the received feedback in a database.

[0543] 4. The server uses an emotion analysis engine to analyze the emotion "stress" from this feedback.

[0544] 5. Based on the analysis results, the server sends the following prompt to the generative AI model:

[0545] "Employee feedback: 'Work has been very stressful lately.' Based on this feedback, please develop strategies to reduce employee stress."

[0546] 6. The server receives the measures returned by the generative AI model. For example, specific measures such as "provide stress management training" or "strengthen mental health support systems" are returned.

[0547] 7. The server sends the details of these measures to the terminal to present them to the user.

[0548] 8. The user can check the proposed measures through the terminal.

[0549] In this way, the system can analyze emotions based on user feedback and quickly plan and present appropriate countermeasures.

[0550] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0551] Step 1:

[0552] A user accesses the system using a terminal.

[0553] Specifically, users access the system's feedback form using a PC or smartphone, and enter specific feedback such as "My work has been very stressful recently."

[0554] Input: User feedback text

[0555] Output: Feedback text is saved to the device

[0556] Step 2:

[0557] The device sends the feedback to the server.

[0558] The device sends the user-entered feedback to the server as an HTTP request, with the data being in a standard data format such as JSON.

[0559] Input: Feedback text

[0560] Output: The feedback text is sent to the server

[0561] Step 3:

[0562] The server stores the feedback in a database.

[0563] The server stores the received feedback in a database management system (DBMS), specifically by storing information such as the feedback content, user ID, and timestamp in an appropriate table in the database.

[0564] Input: Feedback text, User ID, Timestamp

[0565] Output: Feedback is saved in a database

[0566] Step 4:

[0567] The server analyzes the feedback using a sentiment analysis engine.

[0568] The server passes the stored feedback to a sentiment analysis engine, which analyzes the text of the feedback and identifies emotions such as "stress" or "anxiety."

[0569] Input: Feedback text

[0570] Output: Sentiment analysis result (e.g., stress)

[0571] Step 5:

[0572] The server sends a prompt to the generative AI model based on the analysis results.

[0573] The server creates a prompt to be sent to the generative AI model based on the analysis results obtained from the emotion analysis engine. For example, it generates a prompt such as, "Feedback from employees: 'Work has been very stressful recently.' Based on this feedback, please devise measures to reduce employees' stress." The server then sends this prompt to the generative AI model.

[0574] Input: Sentiment analysis results, feedback text

[0575] Output: The prompt is sent to the generative AI model.

[0576] Step 6:

[0577] The server receives the countermeasures from the generative AI model and presents them to the user.

[0578] The server receives the measures returned by the generative AI model. For example, specific measures such as "providing stress management training" or "strengthening mental health support systems" are returned. The server then sends the measures to the device to present to the user. The user can check the presented measures through the device.

[0579] Input: Countermeasures from a generative AI model

[0580] Output: The countermeasures are presented to the user.

[0581] (Application example 2)

[0582] Next, a description will be given of Application Example 2 of Form 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."

[0583] Previous systems for visualizing employees' true nature made it difficult to grasp employee feedback and emotional changes in real time and quickly plan appropriate measures based on that information. Furthermore, there was a lack of means for planning specific measures such as improving the work environment, reviewing work processes, and providing education and training. This meant that the systems were unable to fully contribute to creating a comfortable working environment for employees or improving business performance.

[0584] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0585] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating countermeasures for issues revealed by the two-way dialogue, means for collecting feedback from workers, means for analyzing emotions in the collected feedback, means for formulating countermeasures based on the analysis results, and means for notifying the formulated countermeasures. This makes it possible to grasp changes in employee feedback and emotions in real time and to formulate prompt and appropriate countermeasures based on them.

[0586] The "interactive ES survey function" is a function that collects and analyzes information through two-way dialogue in order to visualize the true nature of employees.

[0587] "Two-way interaction" is a form of communication in which the system and the user exchange information with each other.

[0588] "Means for planning countermeasures to issues" is a function that comes up with specific improvement measures and countermeasures based on information obtained from two-way dialogue and feedback.

[0589] "Means for collecting feedback" refers to a function that collects opinions and impressions from workers and employees via voice or text.

[0590] "Means for analyzing emotions" is a function that analyzes emotions from the content of collected feedback and plans countermeasures based on the results.

[0591] "Means for notifying measures" is a function for informing managers and workers of the planned measures.

[0592] "Improving the working environment" refers to improving the physical or psychological environment to provide workers with an environment in which they can work comfortably.

[0593] "Reviewing business processes" refers to reevaluating business flows and procedures in order to improve and streamline them.

[0594] "Providing education and training" refers to providing education and training programs to employees and workers to enable them to acquire the necessary knowledge and skills.

[0595] The following describes an embodiment of the present invention. The system shown below visualizes the true nature of employees, collects and analyzes feedback and emotional data, and plans and notifies appropriate measures.

[0596] System Configuration

[0597] The system consists of the following major components:

[0598] 1. Interactive ES survey function: This function visualizes the true nature of employees and uses a chatbot with artificial intelligence.

[0599] 2. Two-way dialogue function: Using the interactive ES survey function, employees and the system exchange information in both directions.

[0600] 3. Feedback collection function: Collect feedback from workers via voice and text.

[0601] 4. Sentiment analysis function: Analyzes the sentiment of collected feedback. Specifically, it uses a sentiment analysis engine such as Google® Cloud Natural Language API.

[0602] 5. Countermeasures planning function: Based on the analysis results, measures such as improving the work environment, reviewing business processes, and providing education and training are planned.

[0603] 6. Notification function: Notify managers and workers of the planned measures. For example, send notifications using the Slack API.

[0604] Program processing explanation

[0605] The server first collects feedback from employees using an interactive ES survey function. This feedback is collected through voice input and text input. Next, the collected feedback is analyzed using a sentiment analysis function to understand the employee's emotional state. Sentiment analysis is performed using the Google Cloud Natural Language API.

[0606] Based on the analysis results, the countermeasure planning function will propose appropriate countermeasures. For example, if the emotion analysis result indicates "stress," it will suggest providing stress management training. Finally, the notification function will notify managers and workers of the proposed countermeasures. Notifications are sent in real time using the Slack API.

[0607] Specific examples

[0608] For example, if a worker provides feedback such as, "My work these days has been very stressful," the emotion analysis engine will determine this as "stress." Based on this result, the countermeasure planning function will suggest providing stress management training, and the notification function will notify the manager of the countermeasure.

[0609] Prompt Sentence Examples

[0610] Collect feedback from workers, analyze their emotions, and develop appropriate measures. For example, if the feedback is "My recent work has been very stressful," the emotion analysis engine will determine this as "stress" and suggest providing stress management training.

[0611] In this way, it becomes possible to grasp employee feedback and changes in emotions in real time and to plan prompt and appropriate measures based on that information, which contributes to creating a comfortable working environment for employees and improving business performance.

[0612] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0613] Step 1:

[0614] The server collects feedback from employees using an interactive ES survey function.

[0615] Input: Employee voice or text feedback.

[0616] Data processing: The voice data is converted into text using voice recognition software (e.g., Google Speech-to-Text API).

[0617] Output: Feedback data in text format.

[0618] Step 2:

[0619] The server sends the collected feedback data to the sentiment analysis function.

[0620] Input: Feedback data in text format.

[0621] Data Computation: Analyze the sentiment of the feedback using a sentiment analysis engine (e.g., Google Cloud Natural Language API).

[0622] Output: Sentiment analysis results (e.g., "stressed," "anxious," "satisfied," etc.).

[0623] Step 3:

[0624] The server plans countermeasures based on the results of emotion analysis.

[0625] Input: Sentiment analysis results.

[0626] Data calculation: Using a generative AI model, countermeasures corresponding to the analysis results are proposed. For example, if the condition is judged to be "stress," the system will suggest providing stress management training.

[0627] Output: Planned measures (e.g., "Provide stress management training").

[0628] Step 4:

[0629] The server notifies administrators and workers of the proposed countermeasures using a notification function.

[0630] Input: proposed measures.

[0631] Data processing: Generate notification messages and send them using a notification system (e.g., Slack API).

[0632] Output: Notification messages sent to managers and workers.

[0633] Step 5:

[0634] The user (administrator or worker) checks the notified countermeasures and takes the necessary action.

[0635] Input: Notification message.

[0636] Specific action: The administrator takes action based on the notified measures, such as scheduling stress management training.

[0637] Output: Measure implementation status.

[0638] In this way, the server can grasp employee feedback and changes in emotions in real time, and based on that, can plan and notify prompt and appropriate measures, which will contribute to creating a comfortable working environment for employees and improving business performance.

[0639] Example 3

[0640] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0641] Conventional employee feedback systems make it difficult to fully grasp employee opinions and feelings, making it difficult to formulate appropriate measures. Furthermore, analyzing feedback and formulating improvement measures takes a great deal of time and effort, making them insufficient in today's business environment, where rapid response is required. Furthermore, there was a lack of systems for effectively implementing specific measures that contribute to creating a comfortable working environment for employees and improving business performance.

[0642] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0643] In this invention, the server includes means for having an interactive survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for collecting feedback from employees, means for analyzing the collected feedback using a natural language processing tool, means for extracting frequently occurring keywords and emotions from the analysis results, means for generating improvement measures using a generative AI model based on the extracted data, and means for notifying a manager of the generated improvement measures. This makes it possible to quickly and accurately grasp the opinions and emotions of employees and to plan and implement appropriate countermeasures.

[0644] The "interactive survey function" is a function that collects employee opinions and feelings and highlights issues through two-way communication.

[0645] "Two-way dialogue" is a communication process in which employees and systems exchange information with each other.

[0646] "Means of planning countermeasures to issues" is the process of generating specific improvement measures based on collected data that will contribute to creating a comfortable working environment for employees and improving business performance.

[0647] "Feedback collection methods" are the processes of collecting employee opinions and feelings through digital forms and survey systems.

[0648] A "natural language processing tool" is a software tool for analyzing text data and extracting meaning and emotion.

[0649] "Means for extracting frequently occurring keywords and emotions" refers to the process of identifying and extracting specific keywords and emotions from the analyzed feedback data.

[0650] A "generative AI model" is an artificial intelligence model that automatically generates appropriate improvement measures based on collected data.

[0651] "Means for notifying administrators" refers to the process of communicating generated improvements to administrators via email or messaging tools.

[0652] MODE FOR CARRYING OUT THE INVENTION

[0653] The present invention is a system for collecting and analyzing feedback from employees and formulating appropriate improvement measures. A specific embodiment of this system is described below.

[0654] 1. Gathering feedback

[0655] The server provides a form where employees can enter their feedback. This form is implemented as a web application and can be accessed through a browser. For example, an employee can enter, "Recently, communication within my team has been poor, and I'm feeling stressed," and click the submit button.

[0656] 2. Receiving and storing feedback

[0657] The server receives the feedback and stores it in a database, which uses a relational database (e.g., MySQL (registered trademark) or PostgreSQL).

[0658] 3. Feedback Analysis

[0659] The server passes the saved feedback data to a natural language processing (NLP) tool, specifically using Google Cloud Natural Language API or IBM Watson Natural Language Understanding. The server receives the analysis results returned from the NLP tool and extracts frequently occurring keywords and phrases from the feedback. For example, if the keyword "difficulty in communication" appears frequently, it passes that information on to the next step.

[0660] 4. Emotion analysis

[0661] The server uses an emotion engine (e.g., Affectiva or IBM Watson Tone Analyzer) to analyze the emotions contained in the feedback, identifying emotions such as "stress" or "frustration."

[0662] 5. Integrating data and generating remediation measures

[0663] The server integrates data obtained from the NLP tool and the emotion engine. For example, if the keyword "difficulty in communication" and the emotion "stress" appear simultaneously, the server uses this information to proceed to the next step. Based on the integrated data, the server uses a generative AI model to generate improvement measures. For example, it suggests "providing training to improve communication skills" or "creating an open space."

[0664] 6. Notification of remedial measures

[0665] The server notifies the administrator of the generated remediation action via email (e.g., Gmail API) or internal messaging tools (e.g., Slack or MICROSOFT® TEAMS®).

[0666] Examples of specific examples and prompts

[0667] A user enters "Recently, communication within the team has been going poorly, and I'm feeling stressed" into the feedback form and clicks the submit button. The server analyzes this feedback and extracts the keywords and emotions of "difficulty in communication" and "stress." Based on this, the server suggests "Providing training to improve communication skills."

[0668] Example prompt sentence:

[0669] "Analyze employee feedback and extract frequently occurring keywords and emotions, such as 'difficulty in communication' or 'stress.'"

[0670] "Based on the extracted keywords and sentiment, propose appropriate improvement measures. For example, 'Provide training to improve communication skills' or 'Establish an open space.'"

[0671] The above is a specific embodiment for carrying out the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0672] Step 1:

[0673] The user enters their opinions and feelings into the feedback form and clicks the submit button. The input data is, for example, text such as "Recently, communication within my team has not been going well, and I am feeling stressed." The server receives this input data and stores it in a database. The output is the feedback data stored in the database.

[0674] Step 2:

[0675] The server passes the saved feedback data to a natural language processing (NLP) tool. Specifically, it uses Google Cloud Natural Language API or IBM Watson Natural Language Understanding. The input is the feedback data retrieved from the database. The server receives the analysis results returned from the NLP tool and extracts frequently occurring keywords and phrases from the feedback. The output is the extracted keywords and phrases.

[0676] Step 3:

[0677] The server uses an emotion engine (e.g., Affectiva or IBM Watson Tone Analyzer) to analyze the emotions contained in the feedback. The input is the feedback data retrieved from the database. The server receives the analysis results returned by the emotion engine and identifies the emotions contained in the feedback. The output is the identified emotion data.

[0678] Step 4:

[0679] The server integrates data from the NLP tool and the emotion engine. The inputs are extracted keywords and phrases and identified emotion data. The server uses a generative AI model to generate remediation recommendations based on this data. The output is the generated remediation recommendations.

[0680] Step 5:

[0681] The server notifies the administrator of the generated remediation. The input is the generated remediation. The notification is via email (e.g., Gmail API) or internal messaging tools (e.g., Slack or Microsoft Teams). The output is the notification sent to the administrator.

[0682] The above is the specific processing flow of the program of this system.

[0683] (Application example 3)

[0684] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0685] The problems are that communication within traditional factories is difficult and the working environment has not been sufficiently improved. In particular, it is difficult to properly understand workers' emotions and feedback and to plan specific measures based on that. This can increase worker stress and reduce work efficiency.

[0686] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0687] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating measures for issues highlighted by the two-way dialogue, means for analyzing employees' emotions using an emotion engine, means for formulating measures for improving the work environment and communication skills based on the analysis results, and means for generating prompt sentences using a generative AI model. This makes it possible to simultaneously grasp the feedback and emotions of workers and quickly formulate specific measures.

[0688] The "interactive ES survey function" is a function that collects information through two-way dialogue in order to visualize the true nature of employees.

[0689] "Two-way interaction" is a form of communication in which the system and the user exchange information with each other.

[0690] "Means for formulating countermeasures" is a function that plans specific improvement measures and countermeasures based on collected information and analysis results.

[0691] An "emotion engine" is a technology that analyzes a user's emotions and identifies their emotional state.

[0692] A "generative AI model" is a model that uses artificial intelligence to generate prompts and other output for a specific task.

[0693] A "prompt" is an instruction that can be input into a generative AI model to obtain a specific output.

[0694] "Improving the working environment" refers to creating a physical and psychological environment that allows workers to work more efficiently and comfortably.

[0695] "Improving communication skills" refers to efforts to improve the ability of employees and workers to effectively communicate information and understand each other.

[0696] The system for implementing this invention includes an interactive ES survey function for visualizing the true nature of employees, an emotion engine, and a prompt sentence generation function using a generative AI model. Specific embodiments are described below.

[0697] System Configuration

[0698] The system consists of three main components: a server, a terminal, and a user.

[0699] server

[0700] The server has the following functions:

[0701] 1. Interactive ES survey function: Provides a chatbot function to collect employee feedback. The chatbot uses artificial intelligence to conduct conversations in natural language.

[0702] 2. Emotion Engine: Analyzes collected feedback data and identifies employee emotions. Natural Language Processing (NLP) technology is used to analyze text data.

[0703] 3. Countermeasure planning function: Based on feedback data and emotion analysis results, measures are planned to improve the work environment and communication skills.

[0704] 4. Generative AI model: Generates prompts and creates instructions to obtain output for a specific task.

[0705] Terminal

[0706] A terminal is a device through which a user inputs feedback, and includes smartphones, tablets, and PCs.

[0707] User

[0708] Users are employees and workers who use the system, input feedback, and receive suggestions for countermeasures from the system.

[0709] Processing flow

[0710] 1. Feedback collection: Users use their devices to enter feedback through an interactive ES survey function, for example, by entering specific opinions such as "I feel stressed because there is too much work."

[0711] 2. Emotion Analysis: The server uses an emotion engine to analyze the feedback data and identify the user's emotion, for example, "stress."

[0712] 3. Countermeasures Planning: Based on the analysis results, the server will propose measures to improve the work environment and communication skills, such as "adjusting the workload" or "introducing tools to improve work efficiency."

[0713] 4. Prompt generation: A generative AI model is used to generate prompts, such as "Collect feedback from workers in the factory and analyze their emotions using an emotion engine. Based on the analysis results, please devise measures to improve the work environment and communication skills."

[0714] Specific examples

[0715] For example, if there is a lot of feedback in a factory that "the workload is too heavy and it's stressful," the emotion engine will identify the emotion as "stress" and suggest countermeasures such as "adjusting the workload" or "introducing tools to improve work efficiency." In this way, it is possible to simultaneously grasp the feedback and emotions of workers and quickly devise specific countermeasures.

[0716] Prompt Sentence Examples

[0717] "Collect feedback from workers in your factory and analyze their emotions using the emotion engine. Based on the analysis results, plan measures to improve the working environment and communication skills."

[0718] In this way, the system can create a comfortable working environment for workers and improve work efficiency.

[0719] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0720] Step 1:

[0721] Users use their devices to input feedback through the interactive ES survey function. Specifically, users provide feedback interactively to the chatbot using devices such as smartphones or PCs. For example, they can input specific opinions such as "I feel stressed because I have too much work to do." The input data is sent to the server in text format.

[0722] Step 2:

[0723] The server passes the received feedback data to the emotion engine. The emotion engine analyzes the text data using natural language processing (NLP) techniques and identifies the user's emotion. For example, it identifies the emotion "stress." The input is the feedback text data, and the output is the identified emotion data.

[0724] Step 3:

[0725] The server uses its countermeasure planning function to propose specific countermeasures based on the emotion data and feedback data obtained from the emotion engine. For example, it may propose "adjusting the workload" or "introducing tools to improve work efficiency." The input is emotion data and feedback data, and the output is the proposed countermeasures.

[0726] Step 4:

[0727] The server generates prompts using a generative AI model. The generative AI model creates instructions for specific tasks based on proposed countermeasures. For example, it generates a prompt such as, "Collect feedback from workers in the factory and analyze their emotions using an emotion engine. Based on the analysis results, devise countermeasures to improve the work environment and communication skills." The input is the proposed countermeasures, and the output is the prompt.

[0728] Step 5:

[0729] The server provides the generated prompt sentence to the user, who can then review it through a terminal and add feedback as needed. This allows the system to continually improve. The input is the prompt sentence, and the output is the user's additional feedback.

[0730] In this way, the system can simultaneously grasp the feedback and emotions of workers and quickly devise specific countermeasures.

[0731] 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.

[0732] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0733] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0734] 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.

[0735] [Second embodiment]

[0736] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0737] 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.

[0738] 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).

[0739] 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.

[0740] 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.

[0741] 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).

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0748] "Example 1"

[0749] One aspect of the present invention is a system with an interactive ES survey function that visualizes the true nature of employees. This system uses a chatbot with artificial intelligence to engage in two-way dialogue with employees. The chatbot generates appropriate responses to input from employees and understands their opinions and issues.

[0750] "Example 2"

[0751] Furthermore, one aspect of the present invention is a function that proposes countermeasures for issues that have been identified through two-way dialogue. Based on the identified issues, this function proposes countermeasures that contribute to creating a comfortable working environment for employees and improving business performance. For example, based on feedback from employees, it proposes measures such as improving the work environment, reviewing business processes, and providing education and training.

[0752] "Example 3"

[0753] As a concrete example, if feedback from employees indicates that they often find it difficult to communicate, countermeasures such as providing training to improve communication skills or creating open spaces can be proposed. This will create a comfortable working environment for employees and improve business performance.

[0754] The processing flow of each embodiment will be described below.

[0755] "Example 1"

[0756] Step 1: The system receives input from employees. This input is about their opinions and issues.

[0757] Step 2: The system then uses an artificial intelligence-powered chatbot to generate appropriate responses to the inputs, which are designed to better understand the employee's opinions and challenges.

[0758] Step 3: Finally, the system gathers employee opinions and issues through two-way dialogue and stores them in a database.

[0759] "Example 2"

[0760] Step 1: The system analyzes employee opinions and issues stored in the database.

[0761] Step 2: Next, based on the analysis results, the system will develop measures to create a comfortable working environment for employees and contribute to improving performance.

[0762] Step 3: Finally, the proposed measures are reported to the manager and implemented.

[0763] "Example 3"

[0764] Step 1: If the system detects a lot of "difficulty in communication" in employee feedback, it will identify this as an issue.

[0765] Step 2: Next, the system will develop countermeasures to address this issue, such as "providing training to improve communication skills" and "establishing open spaces."

[0766] Step 3: Finally, the proposed measures are reported to management and implemented, resulting in the creation of a comfortable working environment for employees and improved performance.

[0767] Example 1

[0768] Next, a description will be given of Example 1 of Form 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."

[0769] Traditional engagement surveys have made it difficult to accurately grasp employee opinions and issues, and lacked effective methods for visualizing the true nature of employees. As a result, it has been difficult to create a comfortable working environment for employees and to devise appropriate measures to contribute to improving performance. Furthermore, because real-time two-way dialogue is not possible, it has been impossible to quickly reflect employee opinions and issues.

[0770] 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.

[0771] In this invention, the server includes a means for a user to access the chatbot using a terminal, a means for the terminal to receive user input and send it to the server, a means for the server to generate a response to the user input using a generative AI model, a means for the server to send the generated response to the terminal, a means for the terminal to display the response from the server to the user, and a means for the server to analyze the user's input data and generate a report. This makes it possible to grasp employee opinions and issues in real time and quickly develop appropriate measures.

[0772] The "interactive engagement survey function" is a function that allows for two-way dialogue to understand employees' opinions and issues and visualize their true nature.

[0773] "Two-way dialogue" is a form of dialogue in which the user and the system exchange opinions and information in real time.

[0774] "Measures to address issues" refers to developing appropriate solutions to employee issues that have been highlighted through two-way dialogue.

[0775] A "terminal" is a device used by a user to access the system, including a PC, smartphone, etc.

[0776] The "server" is a central processing unit that receives user input data, generates responses using generative AI models, and analyzes the data.

[0777] A "generative AI model" is an artificial intelligence model that generates appropriate responses based on user input.

[0778] A "chatbot" is a program that interacts with users and generates responses using generative AI models.

[0779] A "report" is a report in which the server analyzes the data entered by the user and summarizes the opinions and issues of employees.

[0780] This invention is a system with an interactive engagement survey function to visualize the true nature of employees. This system is built around a chatbot using artificial intelligence, and grasps employees' opinions and issues through two-way dialogue with users (employees).

[0781] System configuration

[0782] Hardware

[0783] Terminal: A device used by a user to access the system, including a PC or smartphone.

[0784] Server: A central processing unit that receives user input data, generates responses using generative AI models, and analyzes the data.

[0785] software

[0786] Generative AI model: An artificial intelligence model that generates appropriate responses based on user input. Specifically, OpenAI's GPT-4 is used.

[0787] Chatbot: A program that interacts with users and generates responses using generative AI models.

[0788] System Operation

[0789] 1. A user accesses a chatbot using a device

[0790] Users can access the system's chatbot using devices such as PCs or smartphones, for example, through a dedicated web application or mobile application.

[0791] 2. The device receives the user's input and sends it to the server

[0792] When a user inputs text into the chatbot, the device sends the input data to the server. For example, a user might input, "I'm feeling stressed about a recent project."

[0793] 3. The server uses the generative AI model to generate a response to the user's input.

[0794] The server passes the received user input data to a generative AI model (e.g., OpenAI's GPT-4) and generates an appropriate response. Based on the user's input, the generative AI model generates a response such as, "Which specifically are you feeling stressed about?"

[0795] 4. The server generates a response and sends it to the device.

[0796] The server sends the responses generated by the generative AI model to the device, providing an appropriate response to the user's input in real time.

[0797] 5. The device displays the response from the server to the user.

[0798] The terminal displays the response received from the server to the user, who can then confirm the response from the chatbot and enter further details.

[0799] 6. The server analyzes the user's input data and generates a report

[0800] The server analyzes the input data collected from users and generates reports to understand employee opinions and issues, which managers can use to evaluate employee engagement and satisfaction.

[0801] Specific examples

[0802] For example, if a user types "I'm feeling stressed about a recent project," the following specific actions will occur:

[0803] 1. A user uses a device to type into the chatbot, "I'm feeling stressed about a recent project."

[0804] 2. The device sends this input to the server.

[0805] 3. The server uses a generative AI model (GPT-4) to generate a response: "What specifically are you feeling stressed about?"

[0806] 4. The server generates a response and sends it to the terminal.

[0807] 5. The device displays the response to the user: "Where specifically are you feeling stressed?"

[0808] 6. The server analyzes the user's input data and generates a report that includes the causes and frequency of employee stress.

[0809] Prompt Sentence Examples

[0810] Examples of prompts to input to a generative AI model include:

[0811] Prompt: "If an employee types in that they are feeling stressed about a recent project, how would you respond?"

[0812] In response to this prompt, the generative AI model generates the following response:

[0813] Sample response: "What specifically are you stressed about? How is the project progressing? How is your team communicating?"

[0814] In this way, the system visualizes the true nature of employees through dialogue with users and provides useful information to managers.

[0815] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0816] Step 1:

[0817] A user accesses the chatbot using a device

[0818] Users can access the system's chatbot using devices such as PCs or smartphones, for example, through a dedicated web application or mobile application.

[0819] Input: User's access request

[0820] Output: The chatbot interface is displayed.

[0821] Step 2:

[0822] The terminal receives the user's input and sends it to the server

[0823] When a user inputs text into the chatbot, the device sends the input data to the server. For example, a user might input, "I'm feeling stressed about a recent project."

[0824] Input: User text input

[0825] Output: The input data is sent to the server

[0826] Step 3:

[0827] The server uses the generative AI model to generate responses to user input.

[0828] The server passes the received user input data to a generative AI model (e.g., OpenAI's GPT-4) and generates an appropriate response. Based on the user's input, the generative AI model generates a response such as, "Which specifically are you feeling stressed about?"

[0829] Input: User-entered data

[0830] Output: Response data from the generative AI model

[0831] Step 4:

[0832] Sends the server-generated response to the terminal

[0833] The server sends the responses generated by the generative AI model to the device, providing an appropriate response to the user's input in real time.

[0834] Input: Response data from a generative AI model

[0835] Output: Response data is sent to the terminal

[0836] Step 5:

[0837] The terminal displays the response from the server to the user

[0838] The terminal displays the response received from the server to the user, who can then confirm the response from the chatbot and enter further details.

[0839] Input: Response data from the server

[0840] Output: The response data is displayed to the user

[0841] Step 6:

[0842] The server analyzes the user's input data and generates a report

[0843] The server analyzes the input data collected from users and generates reports to understand employee opinions and issues, which managers can use to evaluate employee engagement and satisfaction.

[0844] Input: User-entered data

[0845] Output: Report based on the analysis results

[0846] In this way, the system visualizes the true nature of employees through dialogue with users and provides useful information to managers.

[0847] (Application example 1)

[0848] Next, a description will be given of Application Example 1 of Form 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."

[0849] Conventional interactive ES survey systems focus on collecting employee opinions and issues, but lack the means to collect the opinions and issues of workers working in factories and to improve the work environment and increase efficiency. In addition, there is a need for a system that can devise specific measures based on the information obtained through dialogue with workers.

[0850] 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.

[0851] In this invention, the server includes means having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating measures for issues highlighted by the two-way dialogue, means having an application installed on a robot for collecting opinions and issues of workers working in a factory, means for generating appropriate responses to inputs from workers using a generative AI model, and means for improving the work environment and streamlining the work environment based on the responses. This makes it possible to efficiently collect opinions and issues of workers working in a factory and to improve the work environment and streamline the work environment.

[0852] The "interactive ES survey function" is a function that collects opinions and issues through two-way dialogue in order to visualize the true nature of employees.

[0853] "Two-way dialogue" refers to interactive communication that uses artificial intelligence such as chatbots to exchange opinions with employees and workers in real time.

[0854] "Means for planning countermeasures to issues" refers to the function of planning and proposing specific improvement measures and countermeasures for issues that have been highlighted through two-way dialogue.

[0855] "Factory workers" are employees who perform manufacturing, assembly, and other tasks within a factory.

[0856] The "application installed on the robot" is software that is installed on the robots used in the factory and is used to collect opinions and issues through dialogue with workers.

[0857] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate appropriate responses or results based on input data.

[0858] "Means to improve the work environment and increase efficiency" is a function that implements specific measures to improve the work environment and increase work efficiency based on collected opinions and issues.

[0859] A system for implementing this invention includes means having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for planning countermeasures for issues highlighted by the two-way dialogue, means having an application installed on a robot for collecting the opinions and issues of workers working in a factory, means for generating appropriate responses to inputs from workers using a generative AI model, and means for improving the work environment and increasing efficiency based on the responses.

[0860] Program processing explanation

[0861] The server uses a Python program and the OpenAI API to utilize a generative AI model (e.g., GPT-3). Robots in the factory collect input from workers and send it to the server. The server uses the generative AI model to generate an appropriate response to the worker's input and sends the response back to the robot. The robot communicates the generated response to the worker.

[0862] Hardware and software used

[0863] Hardware: Robots in factories (e.g. collaborative robots)

[0864] Software: Python, OpenAI API

[0865] Data processing and calculation

[0866] Data processing: Input from the human is sent as prompts to the generative AI model.

[0867] Data computation: Generative AI models generate appropriate responses based on worker input.

[0868] Specific examples

[0869] For example, if a worker types, "I feel like the work environment is a little cold lately. Could you please turn up the heating?", the server will use the generative AI model to generate a response that reads, "Thank you for your feedback on the temperature of the work environment. I will report to the relevant department about adjusting the heating."

[0870] Prompt Sentence Examples

[0871] Dialogue with Workers: The working environment has been a little cold lately. Could you please turn up the heating?

[0872] Generate an appropriate response.

[0873] In this way, it is possible to efficiently collect the opinions and issues of workers working in the factory and improve the work environment and increase efficiency.

[0874] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0875] Step 1:

[0876] The user (worker) inputs opinions and issues to the robot. The input data is collected through the robot's sensors and interface. An example of input data is, "I feel like the working environment is a little cold lately. Could you please turn up the heating?"

[0877] Step 2:

[0878] The robot sends the collected input data to a server, which then analyzes the data and converts it into a format suitable for the generative AI model. During this conversion process, the input data is formatted as a prompt sentence.

[0879] Step 3:

[0880] The server sends a prompt to the generative AI model (e.g., GPT-3). The generative AI model generates an appropriate response based on the prompt. For example, if the prompt is "Dialogue with worker: I feel like the work environment is a little cold recently. Could you please turn up the heating?", the generative AI model will generate the response "Thank you for your feedback on the temperature of the work environment. I will report to the relevant department about adjusting the heating."

[0881] Step 4:

[0882] The server receives the response from the generative AI model and sends it to the robot, where it converts the response data into a format that the robot can understand.

[0883] Step 5:

[0884] The robot communicates the response received from the server to the worker. The robot presents the generated response to the worker using audio output and a display. For example, the robot may respond by voice, "Thank you for your feedback on the temperature of the work environment. We will report to the relevant department about adjusting the heating."

[0885] Step 6:

[0886] The server stores the collected opinions, challenges, and generated responses in a database, which is later used for analysis to improve the work environment and streamline it.

[0887] Step 7:

[0888] Based on the stored data, the server will propose specific measures to improve the work environment and increase efficiency, for example, by reporting proposals for adjusting the temperature of the work environment to the relevant department.

[0889] By following the steps above, it is possible to efficiently collect the opinions and issues of workers working in the factory, thereby improving the work environment and increasing efficiency.

[0890] Example 2

[0891] Next, a description will be given of Example 2 of Form 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."

[0892] With conventional interactive survey systems, it was difficult to effectively analyze employee feedback and develop specific countermeasures. Furthermore, there was a lack of means to quickly notify the results of the feedback analysis and implement countermeasures that would contribute to creating a comfortable working environment for employees and improving business performance.

[0893] 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.

[0894] In this invention, the server includes means for having an interactive survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for collecting feedback from users and analyzing the feedback using a generative AI model, and means for formulating specific countermeasures based on the analysis results and notifying the users. This makes it possible to effectively analyze feedback from employees and quickly formulate and notify specific countermeasures.

[0895] The "interactive survey function" is a function that collects and analyzes information through dialogue with the user.

[0896] "Two-way interaction" refers to an interaction in which the user and the system exchange information with each other.

[0897] "Issues" are problems or areas for improvement identified based on feedback from users.

[0898] "Countermeasures" are specific actions or measures implemented to address identified issues.

[0899] A "generative AI model" is a model that uses artificial intelligence to analyze data and generate results.

[0900] A "prompt" is a textual instruction that is input to a generative AI model.

[0901] "Feedback" refers to information such as opinions, impressions, and reports provided by users.

[0902] "Analysis" is the process of finding meaning and patterns based on collected data.

[0903] "Notification" refers to the act of informing the user of the analysis results and countermeasures.

[0904] MODE FOR CARRYING OUT THE INVENTION

[0905] The present invention is a system that visualizes the true nature of employees, identifies issues through two-way dialogue, and proposes measures to address those issues. A specific embodiment of this system will be described below.

[0906] System configuration

[0907] 1. Interactive Survey Feature

[0908] The server has an interactive survey function, which collects and analyzes information through dialogue with users. Specifically, this function is realized by a chatbot using artificial intelligence.

[0909] 2. Two-way dialogue function

[0910] The server uses an interactive survey function to engage in a two-way dialogue with the user, through which feedback is collected from the user.

[0911] 3. Generative AI Models

[0912] The server inputs the collected feedback into a generative AI model (e.g., OpenAI's GPT-4), which analyzes the feedback and identifies challenges.

[0913] 4. Countermeasure planning function

[0914] The server then proposes countermeasures based on the issues identified by the generative AI model, which contribute to creating a comfortable working environment for employees and improving business performance.

[0915] 5. Notification function

[0916] The server notifies the user of the proposed measures, which are sent via the terminal, allowing the user to check the proposed measures.

[0917] Specific examples

[0918] For example, if a user enters feedback such as "Recently, my workload has increased and I've been working a lot of overtime," the device will send this feedback to the server. The server inputs the received feedback into a generative AI model, which then analyzes it to determine that "a review of the business process is necessary." Based on the results of this analysis, the server will propose specific measures, such as reviewing the business process and allocating additional personnel, and notify the user. The user can then check these measures through their device and take the necessary action.

[0919] Prompt Sentence Examples

[0920] "Recently, my workload has increased and I've been working a lot of overtime. Please suggest some solutions to this."

[0921] In this way, the server can effectively analyze feedback from users and quickly plan and notify specific countermeasures.

[0922] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0923] Program processing flow

[0924] Step 1: User Enters Feedback

[0925] Users input feedback about their work environment and work processes into the terminal. For example, they can input specific details such as, "Recently, the workload has increased and I've been working a lot of overtime."

[0926] Input: User feedback text

[0927] Output: Feedback data entered into the terminal

[0928] Step 2: The device sends feedback to the server

[0929] The terminal transmits the feedback input by the user to the server, where the feedback is converted into an appropriate format and then transmitted to the server.

[0930] Input: Feedback data entered into the terminal

[0931] Output: Feedback data sent to the server

[0932] Step 3: The server receives the feedback and inputs it as a prompt to the generative AI model.

[0933] The server receives feedback sent from the device and inputs it as a prompt to a generative AI model (e.g., OpenAI's GPT-4).

[0934] Input: Feedback data sent to the server

[0935] Output: The prompt sentence that is fed into the generative AI model

[0936] Step 4: Generative AI model analyzes feedback and identifies issues

[0937] The generative AI model analyzes the input prompt and identifies issues based on the feedback. For example, based on the feedback that "the workload has increased and overtime is becoming more frequent," it determines that a review of work processes and the allocation of additional personnel are necessary.

[0938] Input: The prompt given to the generative AI model

[0939] Output: Identified issues

[0940] Step 5: The server develops a plan of action based on the identified issues

[0941] The server then proposes countermeasures based on the issues identified by the generative AI model, such as reviewing business processes, allocating additional personnel, and providing education and training.

[0942] Input: Identified issues

[0943] Output: Planned countermeasures

[0944] Step 6: The server notifies the user of the proposed measures

[0945] The server notifies the user of the proposed measures, which are sent via the terminal, allowing the user to check the proposed measures.

[0946] Input: Proposed measures

[0947] Output: The action notified to the user

[0948] Specific examples of operation

[0949] For example, if a user enters feedback such as "Recently, my workload has increased and I've been working a lot of overtime," the device will send this feedback to the server. The server inputs the received feedback into a generative AI model, which then analyzes it to determine that "a review of the business process is necessary." Based on the results of this analysis, the server will propose specific measures, such as reviewing the business process and allocating additional personnel, and notify the user. The user can then check these measures through their device and take the necessary action.

[0950] (Application example 2)

[0951] Next, a description will be given of Application Example 2 of Form 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."

[0952] In conventional factory environments, it was difficult to effectively collect feedback from workers and to develop prompt and appropriate improvement measures based on that feedback. Furthermore, delays in improving the work environment and reviewing business processes led to problems such as a decline in work efficiency and a worsening workplace environment. This could lead to a decline in worker motivation and productivity, ultimately negatively impacting business performance.

[0953] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0954] In this invention, the server includes a means for having an interactive ES survey function for visualizing the true nature of employees, a means for conducting two-way dialogue using the interactive ES survey function, a means for formulating countermeasures for issues revealed by the two-way dialogue, a means for collecting feedback from workers in the factory, a means for generating improvement measures using a generative AI model based on the collected feedback, and a means for presenting the generated improvement measures to the workers. This makes it possible to effectively collect feedback from workers and quickly formulate appropriate improvement measures. This allows for the work environment to be improved and business processes to be reviewed quickly, thereby improving work efficiency and the workplace environment.

[0955] The "interactive ES survey function" is a function that collects and analyzes information through two-way dialogue in order to visualize the true nature of employees.

[0956] "Two-way dialogue" is a form of communication in which the system and the user exchange information with each other.

[0957] "Means for planning countermeasures to issues" is a function for devising specific improvement measures and solutions based on issues that have been highlighted through two-way dialogue.

[0958] "Means for collecting feedback" is a function for collecting information such as opinions, impressions, and problems from workers.

[0959] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate new information or suggestions from input data.

[0960] "Means for generating improvement measures" is a function that uses a generative AI model to devise specific improvement measures based on collected feedback.

[0961] "Means for presenting improvement measures" is a function that communicates the generated improvement measures to workers in an easy-to-understand manner.

[0962] The system for implementing this invention includes a series of processes that collect feedback from workers in a factory, generate improvement measures using a generative AI model based on the feedback, and present the measures to the workers. A specific embodiment of this system will be described below.

[0963] Hardware and Software Configuration

[0964] 1. Hardware:

[0965] Robot: A robot that interacts with workers in a factory.

[0966] Server: A server for running generative AI models and processing data.

[0967] 2. Software:

[0968] Interactive ES survey function: An interactive survey function that visualizes the true nature of employees. Implemented as a chatbot using artificial intelligence.

[0969] Generative AI models: Use generative AI models such as OpenAI's GPT-3 to generate improvements based on feedback.

[0970] Data collection and presentation capabilities: Software for collecting feedback from workers and presenting generated improvement recommendations.

[0971] Data processing and calculation flow

[0972] 1. Gathering Feedback:

[0973] The robot interacts with workers and collects feedback about the work environment and work processes.

[0974] The collected feedback is sent to a server.

[0975] 2. Generating improvement measures using generative AI models:

[0976] The server inputs the collected feedback into a generative AI model.

[0977] The generative AI model generates specific improvement measures based on the input feedback.

[0978] The generated remediation measures are stored on the server.

[0979] 3. Proposal of improvement measures:

[0980] The server sends the generated remedial measures to the robot.

[0981] The robot will suggest improvements to the worker and engage in additional dialogue as needed.

[0982] Specific examples

[0983] For example, if a worker gives feedback that "the workspace is too small and inefficient," the generative AI model will generate the following improvement measures:

[0984] We will review the layout of your workspace and propose new arrangements to ensure efficient movement.

[0985] These improvement measures are presented to workers through the robot and can be used to improve the working environment.

[0986] Prompt Sentence Examples

[0987] Below is an example of a prompt that can be fed into a generative AI model:

[0988] Based on the feedback below, please suggest ways to improve the factory environment.

[0989] Feedback: The workspace is small and inefficient

[0990] In this way, the system can effectively collect feedback from workers, develop quick and appropriate improvement measures, and improve the working environment and review business processes.

[0991] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0992] Step 1:

[0993] The robot interacts with workers and collects feedback about the work environment and work processes.

[0994] Input: Verbal or textual feedback from the worker.

[0995] Output: Collected feedback data.

[0996] How it works: The robot uses a built-in microphone and text input interface to collect feedback from workers in real time, which is then sent to a server as text data.

[0997] Step 2:

[0998] The server generates prompt sentences to input the collected feedback into the generative AI model.

[0999] Input: Collected feedback data.

[1000] Output: The prompt sentence to be input to the generative AI model.

[1001] Specific operation: The server analyzes the feedback data and generates an appropriate prompt. For example, in response to the feedback "The work space is small and inefficient," the server generates the prompt "Please suggest improvements to the factory environment based on the following feedback. Feedback: The work space is small and inefficient."

[1002] Step 3:

[1003] The server inputs a prompt sentence into the generative AI model and generates an improvement plan.

[1004] Input: The generated prompt statement.

[1005] Output: The improvements generated by the generative AI model.

[1006] Specific operation: The server inputs the generated prompt sentence into a generative AI model such as OpenAI's GPT-3. The generative AI model generates specific improvement measures based on the prompt sentence and returns them to the server.

[1007] Step 4:

[1008] The server sends the generated remedial measures to the robot.

[1009] Input: The improvements generated by the generative AI model.

[1010] Output: Remediation data sent to the robot.

[1011] Specific operation: The server sends the generated improvement measures to the robot as text data. The robot receives this data and prepares to present it to the worker.

[1012] Step 5:

[1013] The robot will suggest improvements to the worker and engage in additional dialogue as needed.

[1014] Input: Remediation data sent from the server.

[1015] Output: Suggested improvements and additional feedback to the worker.

[1016] Specific operation: The robot presents the received improvement measures to the worker via voice or text. If the worker provides additional feedback, the robot collects the feedback again and sends it to the server, thereby further improving the accuracy of the improvement measures.

[1017] Example 3

[1018] Next, a description will be given of Example 3 of Form Example 3. 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."

[1019] With conventional employee feedback systems, it was difficult to effectively identify employees' fundamental issues and develop appropriate countermeasures. Furthermore, feedback data was often collected and analyzed manually, making it difficult to develop efficient countermeasures. This resulted in issues such as the inability to create a comfortable working environment for employees or to fully improve business performance.

[1020] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1021] In this invention, the server includes means for having an interactive survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for collecting feedback data from employees, means for pre-processing the collected feedback data, means for extracting and analyzing keywords from the pre-processed data, means for generating countermeasures based on the analysis results, and means for presenting and implementing the generated countermeasures. This makes it possible to efficiently collect and analyze employee feedback and quickly formulate and implement appropriate countermeasures.

[1022] The "interactive survey function" is a function for collecting employee feedback and clarifying issues through two-way communication.

[1023] "Two-way dialogue" is a form of communication in which employees and systems exchange information with each other.

[1024] "Issue solutions" are specific action plans or measures to solve specific problems based on employee feedback.

[1025] "Feedback data" refers to information such as opinions, impressions, and evaluations provided by employees.

[1026] "Preprocessing" refers to processes such as cleaning, tokenizing, and removing stop words from collected feedback data to make it easier to analyze.

[1027] "Keyword extraction" is the process of identifying important words and phrases from feedback data.

[1028] "Analysis" is the process of understanding the content of the feedback and finding patterns and trends based on extracted keywords and data.

[1029] "Generating countermeasures" is the process of proposing specific solutions and improvements based on the analysis results.

[1030] "Presenting" is the act of showing the generated countermeasure plan to the user.

[1031] "Implementation" is the process of actually putting the proposed countermeasures into action.

[1032] This invention is a system that efficiently collects and analyzes feedback from employees and promptly plans and implements appropriate measures. A specific embodiment of this system will be described below.

[1033] The server has an interactive survey function that visualizes the true nature of employees. This interactive survey function uses a chatbot with artificial intelligence to collect feedback from employees. For example, feedback can be collected through an internal survey system, email, or chat tool.

[1034] The collected feedback data is pre-processed by the server, which includes data cleaning (removing unnecessary characters and symbols), tokenization (dividing sentences into words), and stop-word removal (removing frequent but meaningless words). This process is performed using Python libraries such as NLTK and spaCy.

[1035] The server extracts and analyzes keywords from the preprocessed data. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) and word clouds to identify frequently occurring keywords in the feedback. It checks whether there are many keywords related to "difficulty in communication," in particular.

[1036] Based on the analysis results, the server generates countermeasures. It uses a generative AI model to propose appropriate countermeasures. For example, the following prompt sentence is input into the generative AI model:

[1037] "Analyze employee feedback and generate countermeasures, especially when there is a lot of feedback about 'difficulty in communication.' Specific countermeasures include 'offering training to improve communication skills' and 'establishing open spaces.'"

[1038] The generated countermeasures are presented to the user via the terminal. The user can review the countermeasures and implement them as necessary. For example, they can arrange a training program to implement "training to improve communication skills." This will help create a comfortable working environment for employees and improve business performance.

[1039] For example, consider the following feedback from an employee:

[1040] "I feel like communication within the team hasn't been going well recently."

[1041] "There are few opportunities to share project progress."

[1042] "Communication is difficult when working remotely."

[1043] The server collects this feedback and analyzes it using NLP technology. As a result of the analysis, it is found that there is a lot of feedback about "difficulty in communication." Therefore, the server generates the following countermeasures:

[1044] "Provide training to improve communication skills."

[1045] "We will set up an open space and create a place where employees can communicate freely with each other."

[1046] The user can check these measures and put them into practice to create a comfortable working environment for employees and improve business performance. The flow of the specific process in the third embodiment will be described with reference to FIG.

[1047] Step 1:

[1048] The server collects feedback data from employees. The input includes feedback from the company's internal survey system, email, and chat tools. This data is collected centrally and stored in a database. The output is the collected feedback data.

[1049] Step 2:

[1050] The server preprocesses the collected feedback data. The input is the collected feedback data. Specific operations include cleaning the data (removing unnecessary characters and symbols), tokenizing (dividing sentences into words), and removing stop words (removing frequent but meaningless words). The output is the preprocessed data.

[1051] Step 3:

[1052] The server extracts and analyzes keywords from the preprocessed data. The input is the preprocessed data. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) and word clouds to identify frequently occurring keywords in the feedback. The output is the extracted keywords and their frequency information.

[1053] Step 4:

[1054] The server generates countermeasures based on the analysis results. The inputs are the extracted keywords and their frequency information. Specifically, it uses a generative AI model to suggest appropriate countermeasures. For example, the following prompt is input into the generative AI model: "Analyze feedback from employees and generate countermeasures in cases where there is a lot of feedback, especially regarding 'difficulty in communication.' Specific countermeasures include 'providing training to improve communication skills' and 'establishing open spaces.'" The generated countermeasures are obtained as output.

[1055] Step 5:

[1056] The terminal presents the generated countermeasure plan to the user. The input is the generated countermeasure plan. The specific operation is to display the countermeasure plan on the user's screen. The output is a state in which the user can check the countermeasure plan.

[1057] Step 6:

[1058] The user checks the proposed countermeasures and implements them as necessary. The input is the proposed countermeasures. A specific action, for example, arranging a training program to implement "training to improve communication skills," is the output: the countermeasures are implemented, creating a comfortable working environment for employees and improving performance.

[1059] (Application example 3)

[1060] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1061] Conventional employee feedback systems lack specific measures to address communication difficulties, making it difficult to create a comfortable working environment for employees and contribute to improving business performance. In addition, feedback collection and analysis are often done manually, making it difficult to develop efficient measures.

[1062] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1063] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for collecting feedback and proposing countermeasures based on the analysis results, means for providing training content for improving communication skills based on the proposed countermeasures, and means for proposing the establishment of open spaces and layout changes. This makes it possible to efficiently collect and analyze employee feedback and quickly formulate and implement specific countermeasures.

[1064] The "Interactive ES Survey Function" is a function that conducts an engagement survey in an interactive format in order to visualize the true nature of employees.

[1065] "Two-way dialogue" is a process in which employees and the system exchange information with each other using the interactive ES survey function.

[1066] "Means for formulating countermeasures for issues" is a function for devising specific solutions to issues that have been highlighted through two-way dialogue.

[1067] "Means for collecting feedback" is a function for efficiently gathering opinions and feedback from employees.

[1068] "Means for proposing measures based on analysis results" is a function for analyzing collected feedback and proposing appropriate measures based on the results.

[1069] "Means of providing training content to improve communication skills" is a function that provides educational materials and programs to improve employees' communication abilities.

[1070] "Means to propose the creation of open spaces and layout changes" is a function that makes suggestions to improve the design and layout of workspaces in order to create an environment where employees can work comfortably.

[1071] A system for implementing this invention includes a server having an interactive ES survey function for visualizing the true nature of employees, a terminal for conducting two-way dialogue using the interactive ES survey function, and a program for planning countermeasures for issues that are highlighted by the two-way dialogue.

[1072] The server is equipped with a chatbot that uses artificial intelligence to collect feedback from employees. The collected feedback is analyzed within the server, and issues such as difficulty in communication are identified. Based on this, the server proposes specific measures.

[1073] The terminal is a device such as a smartphone or PC that provides an interface for employees to enter feedback. The feedback entered from the terminal is sent to a server and analyzed.

[1074] Based on the analysis results, the server provides training content to improve communication skills. It also proposes the creation of open spaces and layout changes, thereby creating a comfortable working environment for employees and improving business performance.

[1075] As a concrete example, the following feedback may be collected:

[1076] "It's difficult to communicate with robots."

[1077] "It's hard to communicate instructions while working"

[1078] "There are a lot of mistakes due to lack of communication."

[1079] Based on this feedback, the following prompt sentences are input into the generative AI model:

[1080] Example prompt sentence:

[1081] Feedback content:

[1082] 1. It's difficult to communicate with robots

[1083] 2. It's difficult to communicate instructions while working

[1084] 3. Lack of communication leads to many mistakes

[1085] Based on this feedback, suggest appropriate measures.

[1086] By inputting this prompt into a generative AI model, the server can obtain more specific countermeasures, such as providing training programs to improve communication skills or changing the layout of the workspace.

[1087] In this way, employee feedback can be collected and analyzed efficiently, and specific measures can be quickly developed and implemented.

[1088] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1089] Step 1:

[1090] The user uses the terminal to enter feedback.

[1091] Input: Feedback entered by the user into the device (e.g., "It's difficult to communicate with the robot").

[1092] Output: Feedback data sent from the device to the server.

[1093] Specific actions: The user enters feedback through the interface of a smartphone or computer and presses the send button.

[1094] Step 2:

[1095] The server collects the feedback.

[1096] Input: Feedback data sent from the device.

[1097] Output: Feedback data stored on the server.

[1098] Specific operation: The server receives the feedback data sent from the terminal and stores it in a database.

[1099] Step 3:

[1100] The server analyzes the feedback.

[1101] Input: Feedback data stored on the server.

[1102] Output: Analysis results (e.g., issues related to communication difficulties).

[1103] What it does: The server uses natural language processing (NLP) algorithms to analyze the feedback data and extract specific keywords and phrases.

[1104] Step 4:

[1105] The server generates a prompt based on the parsing results.

[1106] Input: Analysis results.

[1107] Output: The generated prompt statement.

[1108] Specific operation: Based on the analysis results, the server automatically generates prompt sentences to input into the generative AI model.

[1109] Example prompt sentence:

[1110] Feedback content:

[1111] 1. It's difficult to communicate with robots

[1112] 2. It's difficult to communicate instructions while working

[1113] 3. Lack of communication leads to many mistakes

[1114] Based on this feedback, suggest appropriate measures.

[1115] Step 5:

[1116] The server inputs a prompt sentence into the generative AI model and obtains countermeasure proposals.

[1117] Input: The generated prompt statement.

[1118] Output: Countermeasure proposals from the generative AI model.

[1119] Specific operation: The server inputs a prompt sentence into the generative AI model and obtains the countermeasures returned by the model.

[1120] Step 6:

[1121] The server proposes specific countermeasures based on the proposed countermeasures.

[1122] Input: Countermeasure proposals from a generative AI model.

[1123] Output: Specific countermeasure proposals (e.g., training content to improve communication skills, proposals for establishing open spaces).

[1124] Specific operation: The server proposes specific countermeasures to employees based on the countermeasures obtained from the generative AI model.

[1125] Step 7:

[1126] The user checks and implements the proposed measures.

[1127] Input: Specific measures proposed by the server.

[1128] Output: The results of the measures taken (e.g., attending training, creating open spaces).

[1129] Specific actions: The user checks the measures proposed by the server and takes action as necessary, for example, participating in training or setting up an open space.

[1130] 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.

[1131] "Example 1"

[1132] One embodiment of the present invention is a system that incorporates an emotion engine. This system has an interactive ES survey function that visualizes the true nature of employees, and uses the interactive ES survey function to conduct two-way dialogue. Furthermore, the emotion engine is used to analyze emotions from text input by employees, and the results are used as part of the dialogue. Specifically, if an employee inputs the text "Work didn't go well today," the emotion engine analyzes the text for emotions such as "disappointment" or "disappointment." Then, based on the analysis results, the interactive ES survey function provides an appropriate response to the employee.

[1133] "Example 2"

[1134] Another embodiment of the present invention is a system that proposes countermeasures based on the results of emotion analysis by an emotion engine. This system grasps changes in employees' emotions in real time and proposes countermeasures in response to those changes. Specifically, if the system senses that an employee's emotions are leaning toward "stress" or "anxiety," it proposes countermeasures such as "providing stress management training" or "strengthening the mental health support system."

[1135] "Example 3"

[1136] Another embodiment of the present invention is a system that combines an emotion engine with an interactive employee satisfaction survey function. This system simultaneously grasps employees' emotions and opinions and combines them to gain a deeper understanding. Specifically, it simultaneously grasps an employee's opinion that "I'm stressed because I have too much work" and their feelings of "stress," and based on the results, it proposes measures such as "adjusting the amount of work" or "introducing tools to improve work efficiency."

[1137] The processing flow of each embodiment will be described below.

[1138] "Example 1"

[1139] Step 1: Employees enter text through the interactive ES survey function.

[1140] Step 2: The emotion engine analyzes the emotions from the employee's text input.

[1141] Step 3: The interactive ES survey function uses the analysis results of the emotion engine to respond to employees.

[1142] "Example 2"

[1143] Step 1: The emotion engine identifies changes in employee emotions in real time.

[1144] Step 2: The emotion engine develops measures that correspond to changes in emotions.

[1145] Step 3: The planned measures are implemented to improve employee sentiment.

[1146] "Example 3"

[1147] Step 1: Employees enter their feelings and opinions through the interactive ES survey function.

[1148] Step 2: The emotion engine analyzes the emotions from the employee's text input.

[1149] Step 3: The interactive ES survey function combines the analysis results of the emotion engine with the opinions of employees to develop countermeasures.

[1150] Step 4: The proposed measures are implemented to improve employee sentiment and reflect their opinions.

[1151] Example 1

[1152] Next, a description will be given of Example 1 of Form 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."

[1153] With conventional interactive ES survey systems, it was difficult to accurately grasp employees' opinions and feelings, making it difficult to formulate appropriate measures. Furthermore, the system lacked the functionality to analyze employees' feelings and adjust responses based on them, making it difficult to fully visualize the true nature of employees. This made it difficult to effectively implement measures that would contribute to creating a comfortable working environment for employees and improving business performance.

[1154] 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.

[1155] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating measures for issues highlighted by the two-way dialogue, means for receiving user input, means for analyzing the received input, means for generating an appropriate response based on the analysis results, means for performing emotion analysis, means for adjusting the response based on the emotion analysis results, and means for displaying the adjusted response to the user. This makes it possible to accurately grasp the opinions and emotions of employees and to formulate appropriate measures.

[1156] The "interactive ES survey function" is a function that collects employees' opinions and feelings and makes the true nature of employees visible through two-way dialogue.

[1157] "Two-way interaction" is a form of interaction in which a user and a system exchange information with each other, and is a process in which the system returns a response to a user's input.

[1158] "Means of planning countermeasures to issues" is the function of coming up with appropriate solutions to the issues employees face that have been highlighted through two-way dialogue.

[1159] "Means for receiving user input" refers to a function that receives text or data sent by a user to the system through a terminal.

[1160] The "means for analyzing received input" is a function for analyzing text or data received from a user and understanding its content.

[1161] The "means for generating an appropriate response" is a function for generating an appropriate reply to the user based on the analysis results.

[1162] The "means for performing emotion analysis" is a function for analyzing emotions from the user's text input and identifying those emotions.

[1163] The "means for adjusting the response based on the emotion analysis result" is a function that takes into account the emotion analysis result and appropriately changes the response to the user.

[1164] The "means for displaying the adjusted response to the user" is a function for transmitting the adjusted response to the user's terminal and displaying it on the screen.

[1165] This invention is an interactive ES survey system that visualizes the true nature of employees. This system combines an AI-based chatbot with an emotion analysis engine to collect opinions and emotions through two-way dialogue with employees and then formulates appropriate measures.

[1166] Hardware and software used

[1167] Hardware: Servers, terminals (PCs, smartphones)

[1168] Software: Chatbots (e.g., Dialogflow), sentiment analysis engines (e.g., IBM Watson Tone Analyzer)

[1169] System Overview

[1170] 1. User input:

[1171] The user uses a device to input text into the chatbot, for example, "Work didn't go well today."

[1172] 2. Server receives input:

[1173] The server receives input from the user and passes it to the chatbot, which then converts the input into JSON format and sends it to the chatbot's API.

[1174] 3. Chatbot response generation:

[1175] The chatbot generates an initial response to the user's input. For example, if the user inputs "Work didn't go well today," the chatbot generates a response such as "That must have been tough."

[1176] 4. Emotion analysis:

[1177] The server sends the chatbot's initial response and the user's input to the emotion analysis engine, which analyzes the user's emotions from the text. Specifically, it extracts emotions such as "disappointment" or "disappointment" from the text "Work didn't go well today."

[1178] 5. Adjusting the response:

[1179] The chatbot receives the results of the sentiment analysis and adjusts its response accordingly. For example, if the sentiment analysis results in "disappointment" or "disappointment," the chatbot might change its response to something like, "You've had a tough day. Is there anything I can help you with?"

[1180] 6. Displaying the response to the user:

[1181] The server sends the chatbot's final response to the user's device and displays it to the user, such as a message like, "You've had a rough day. Is there anything I can help you with?"

[1182] Examples and prompts

[1183] Examples:

[1184] User input: "Work didn't go well today."

[1185] Sentiment analysis engine analysis results: "Disappointed", "Disappointed"

[1186] The chatbot responds: "You've had a tough day. Is there anything I can help you with?"

[1187] Example prompt for a generative AI model:

[1188] If a user types "Work didn't go well today," use a sentiment analysis engine to analyze the sentiment and generate an appropriate response based on that.

[1189] This system makes it possible to accurately grasp the opinions and feelings of employees and devise appropriate measures, thereby contributing to creating a comfortable working environment for employees and improving business performance.

[1190] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1191] Step 1:

[1192] A user inputs text into the chatbot using a terminal, for example, "Work didn't go well today." The input text is sent from the terminal to the server.

[1193] Step 2:

[1194] The server receives input from the user. It converts the received text data into JSON format and sends it to the chatbot's API. The input is the user's text, and the output is JSON format data.

[1195] Step 3:

[1196] The chatbot generates an initial response to the user input received from the server. For example, it generates a response such as "That must have been difficult." The input is the user's text data in JSON format, and the output is the initial response text.

[1197] Step 4:

[1198] The server sends the chatbot's initial response and the user's input to the sentiment analysis engine. The sentiment analysis engine analyzes emotions from the user's text. Specifically, it extracts emotions such as "disappointment" or "disappointment" from the text "Work didn't go well today." The input is the user's text and the chatbot's initial response, and the output is the sentiment analysis result.

[1199] Step 5:

[1200] The chatbot receives the results of the sentiment analysis and adjusts the response. For example, if the result of the sentiment analysis is "disappointed" or "disappointed," the chatbot changes the response to something like, "You've had a tough day. Is there anything I can help you with?" The input is the sentiment analysis result, and the output is the adjusted response text.

[1201] Step 6:

[1202] The server sends the chatbot's final response to the user's device, which receives the response and displays it on its screen. For example, the message might read, "You've had a rough day. Is there anything I can help you with?" The input is the tailored response text, and the output is the message displayed on the user's device.

[1203] (Application example 1)

[1204] Next, a description will be given of Application Example 1 of Form 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."

[1205] While conventional interactive ES survey systems can grasp employee opinions and issues, it is difficult to analyze emotions and take appropriate action. Furthermore, while there is a need to understand the emotions and opinions of factory workers in real time and take appropriate action, there was no effective way to achieve this. This could lead to a decline in worker satisfaction and work efficiency.

[1206] 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.

[1207] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for planning measures for issues highlighted by the two-way dialogue, means for analyzing the emotions and opinions of workers and taking appropriate measures, means for generating responses to inputs by workers using a generative AI model, and means for responding to encouragement to workers based on the results of the emotion analysis. This makes it possible to grasp the emotions and opinions of workers in real time and take appropriate measures.

[1208] The "interactive ES survey function" is a function that allows two-way dialogue with employees in order to visualize their true nature.

[1209] "Two-way dialogue" refers to a form of dialogue in which the system and employees exchange information with each other.

[1210] "Measures to address issues" means formulating solutions to issues that employees face that have been highlighted through two-way dialogue.

[1211] "Means for analyzing emotions and opinions" refers to technology for analyzing emotions and opinions from text input by workers.

[1212] A "generative AI model" is a model that uses artificial intelligence to generate appropriate responses to worker input.

[1213] The "emotion analysis result" is the result of the emotion analyzed from the text input of the worker.

[1214] An "encouraging response" is a response to encourage a worker based on the emotion analysis results.

[1215] A system for implementing this invention includes means having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for planning countermeasures for issues highlighted by the two-way dialogue, means for analyzing the emotions and opinions of workers and taking appropriate action, means for generating responses to inputs by workers using a generative AI model, and means for making responses that encourage workers based on the results of the emotion analysis.

[1216] The server first provides an interactive employee satisfaction survey function to visualize the true nature of employees. This function uses a chatbot that uses artificial intelligence to hold two-way conversations with employees. For example, if an employee types, "Work didn't go well today," the chatbot receives the text and uses an emotion engine to analyze emotions such as "disappointment" or "disappointment."

[1217] The server then uses a generative AI model to generate an appropriate response to the employee's input. This model uses advanced natural language processing techniques, such as OpenAI's GPT-3. For example, the server can respond to an employee's input with a response like, "You've had a tough day. Let me know if there's anything I can help you with."

[1218] Furthermore, the server responds to encourage the worker based on the results of emotion analysis. This makes it possible to grasp the worker's emotions and opinions in real time and respond appropriately. For example, if a worker inputs "Today's work isn't going well," the system will generate a response such as "Today was tough. Please let me know if there's anything I can do to help."

[1219] The hardware used is a robot working in a factory, and the software uses Python, the TextBlob library, and OpenAI's GPT-3 API, which allows for real-time analysis of worker sentiment and opinions and appropriate responses.

[1220] An example of a prompt is as follows:

[1221] "A worker said: 'Work is not going well today.

[1222] Please generate an appropriate response."

[1223] By feeding this prompt to GPT-3, it can generate an appropriate response, such as, "You've had a tough day. Let me know if there's anything I can help you with."

[1224] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1225] Step 1:

[1226] The server receives the employee's input. The user (employee) inputs text, for example, "Work didn't go well today." This input is sent to the server.

[1227] Step 2:

[1228] The server passes the received text input to the emotion engine for sentiment analysis. Specifically, it uses the TextBlob library to calculate the polarity and subjectivity of the input text. The input is the employee's text, and the output is the sentiment analysis results (polarity and subjectivity).

[1229] Step 3:

[1230] The server creates a prompt sentence based on the sentiment analysis results and passes it to the generative AI model. Specifically, it generates a prompt sentence like the following: "The worker said: Work isn't going well today. Please generate an appropriate response." The input is the sentiment analysis result and the employee's text, and the output is the generated prompt sentence.

[1231] Step 4:

[1232] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate an appropriate response based on the prompt sentence. The generative AI model receives the prompt sentence as input and outputs an appropriate response in text format. The input is the prompt sentence, and the output is the generated response text.

[1233] Step 5:

[1234] The server returns the generated response text to the user (employee). Specifically, it sends the generated response text to the employee's terminal and displays it. The input is the generated response text, and the output is the response displayed on the employee's terminal.

[1235] Step 6:

[1236] The server stores the sentiment analysis results and generated responses in a database, making them available for later analysis and improvement. The input is the sentiment analysis results and generated responses, and the output is the data stored in the database.

[1237] Example 2

[1238] Next, a description will be given of Example 2 of Form 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."

[1239] With conventional employee feedback collection systems, it was difficult to fully grasp employees' emotions and specific issues, making it difficult to plan appropriate measures. Furthermore, it was not possible to respond to changes in employees' emotions in real time, making it difficult to take prompt measures to reduce stress and anxiety. This resulted in insufficient measures to create a comfortable working environment for employees and improve business performance.

[1240] 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.

[1241] In this invention, the server includes means for having an interactive survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for analyzing employees' emotions using an emotion analysis engine, means for sending prompt messages to the generative AI model based on the analysis results, and means for receiving countermeasures from the generative AI model and presenting them to employees. This makes it possible to analyze emotions based on employee feedback and quickly formulate and present appropriate countermeasures.

[1242] The "interactive survey function" is a function that collects employee feedback and clarifies employees' true nature and challenges through two-way communication.

[1243] "Two-way dialogue" is a form of communication in which the system and employees exchange information with each other.

[1244] "Means for planning countermeasures to issues" is the function of coming up with appropriate solutions to issues that have been identified through two-way dialogue.

[1245] An "emotion analysis engine" is software that analyzes employee feedback and dialogue data to identify employee emotions.

[1246] A "generative AI model" is an artificial intelligence model that generates appropriate countermeasures or solutions based on a given prompt.

[1247] A "prompt" is an instruction given to a generative AI model to generate a solution for a specific problem or situation.

[1248] "Means of receiving countermeasures and presenting them to employees" is a function for communicating the countermeasures obtained from the generative AI model to employees.

[1249] This invention is a system that analyzes emotions based on employee feedback and quickly proposes and presents appropriate measures. This system works in cooperation with three parties: a server, a terminal, and a user.

[1250] Hardware and software used

[1251] Hardware: Servers, terminals (PCs, smartphones)

[1252] Software: Generative AI model, sentiment analysis engine, database management system (DBMS)

[1253] System Overview

[1254] 1. A user accesses the system using a terminal.

[1255] 2. The device sends the user feedback to the server.

[1256] 3. The server stores the feedback in a database and analyzes the feedback using a sentiment analysis engine.

[1257] 4. Based on the analysis results, the server sends a prompt to the generative AI model and develops countermeasures.

[1258] 5. The server receives the countermeasures from the generative AI model and presents them to the user.

[1259] Specific examples

[1260] For example, if employee A sends feedback saying, "My work has been very stressful lately," the system will operate as follows:

[1261] 1. The user (Employee A) sends feedback from the terminal saying, "My work has been very stressful recently."

[1262] 2. The device sends this feedback to the server.

[1263] 3. The server stores the received feedback in a database.

[1264] 4. The server uses an emotion analysis engine to analyze the emotion "stress" from this feedback.

[1265] 5. Based on the analysis results, the server sends the following prompt to the generative AI model:

[1266] "Employee feedback: 'Work has been very stressful lately.' Based on this feedback, please develop strategies to reduce employee stress."

[1267] 6. The server receives the measures returned by the generative AI model. For example, specific measures such as "provide stress management training" or "strengthen mental health support systems" are returned.

[1268] 7. The server sends the details of these measures to the terminal to present them to the user.

[1269] 8. The user can check the proposed measures through the terminal.

[1270] In this way, the system can analyze emotions based on user feedback and quickly plan and present appropriate countermeasures.

[1271] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1272] Step 1:

[1273] A user accesses the system using a terminal.

[1274] Specifically, users access the system's feedback form using a PC or smartphone, and enter specific feedback such as "My work has been very stressful recently."

[1275] Input: User feedback text

[1276] Output: Feedback text is saved to the device

[1277] Step 2:

[1278] The device sends the feedback to the server.

[1279] The device sends the user-entered feedback to the server as an HTTP request, with the data being in a standard data format such as JSON.

[1280] Input: Feedback text

[1281] Output: The feedback text is sent to the server

[1282] Step 3:

[1283] The server stores the feedback in a database.

[1284] The server stores the received feedback in a database management system (DBMS), specifically by storing information such as the feedback content, user ID, and timestamp in an appropriate table in the database.

[1285] Input: Feedback text, User ID, Timestamp

[1286] Output: Feedback is saved in a database

[1287] Step 4:

[1288] The server analyzes the feedback using a sentiment analysis engine.

[1289] The server passes the stored feedback to a sentiment analysis engine, which analyzes the text of the feedback and identifies emotions such as "stress" or "anxiety."

[1290] Input: Feedback text

[1291] Output: Sentiment analysis result (e.g., stress)

[1292] Step 5:

[1293] The server sends a prompt to the generative AI model based on the analysis results.

[1294] The server creates a prompt to be sent to the generative AI model based on the analysis results obtained from the emotion analysis engine. For example, it generates a prompt such as, "Feedback from employees: 'Work has been very stressful recently.' Based on this feedback, please devise measures to reduce employees' stress." The server then sends this prompt to the generative AI model.

[1295] Input: Sentiment analysis results, feedback text

[1296] Output: The prompt is sent to the generative AI model.

[1297] Step 6:

[1298] The server receives the countermeasures from the generative AI model and presents them to the user.

[1299] The server receives the measures returned by the generative AI model. For example, specific measures such as "providing stress management training" or "strengthening mental health support systems" are returned. The server then sends the measures to the device to present to the user. The user can check the presented measures through the device.

[1300] Input: Countermeasures from a generative AI model

[1301] Output: The countermeasures are presented to the user.

[1302] (Application example 2)

[1303] Next, a description will be given of Application Example 2 of Form 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."

[1304] Previous systems for visualizing employees' true nature made it difficult to grasp employee feedback and emotional changes in real time and quickly plan appropriate measures based on that information. Furthermore, there was a lack of means for planning specific measures such as improving the work environment, reviewing work processes, and providing education and training. This meant that the systems were unable to fully contribute to creating a comfortable working environment for employees or improving business performance.

[1305] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1306] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating countermeasures for issues revealed by the two-way dialogue, means for collecting feedback from workers, means for analyzing emotions in the collected feedback, means for formulating countermeasures based on the analysis results, and means for notifying the formulated countermeasures. This makes it possible to grasp changes in employee feedback and emotions in real time and to formulate prompt and appropriate countermeasures based on them.

[1307] The "interactive ES survey function" is a function that collects and analyzes information through two-way dialogue in order to visualize the true nature of employees.

[1308] "Two-way interaction" is a form of communication in which the system and the user exchange information with each other.

[1309] "Means for planning countermeasures to issues" is a function that comes up with specific improvement measures and countermeasures based on information obtained from two-way dialogue and feedback.

[1310] "Means for collecting feedback" refers to a function that collects opinions and impressions from workers and employees via voice or text.

[1311] "Means for analyzing emotions" is a function that analyzes emotions from the content of collected feedback and plans countermeasures based on the results.

[1312] "Means for notifying measures" is a function for informing managers and workers of the planned measures.

[1313] "Improving the working environment" refers to improving the physical or psychological environment to provide workers with an environment in which they can work comfortably.

[1314] "Reviewing business processes" refers to reevaluating business flows and procedures in order to improve and streamline them.

[1315] "Providing education and training" refers to providing education and training programs to employees and workers to enable them to acquire the necessary knowledge and skills.

[1316] The following describes an embodiment of the present invention. The system shown below visualizes the true nature of employees, collects and analyzes feedback and emotional data, and plans and notifies appropriate measures.

[1317] System Configuration

[1318] The system consists of the following major components:

[1319] 1. Interactive ES survey function: This function visualizes the true nature of employees and uses a chatbot with artificial intelligence.

[1320] 2. Two-way dialogue function: Using the interactive ES survey function, employees and the system exchange information in both directions.

[1321] 3. Feedback collection function: Collect feedback from workers via voice and text.

[1322] 4. Sentiment analysis function: Analyze the sentiment of the collected feedback. Specifically, use a sentiment analysis engine such as Google Cloud Natural Language API.

[1323] 5. Countermeasures planning function: Based on the analysis results, measures such as improving the work environment, reviewing business processes, and providing education and training are planned.

[1324] 6. Notification function: Notify managers and workers of the planned measures. For example, send notifications using the Slack API.

[1325] Program processing explanation

[1326] The server first collects feedback from employees using an interactive ES survey function. This feedback is collected through voice input and text input. Next, the collected feedback is analyzed using a sentiment analysis function to understand the employee's emotional state. Sentiment analysis is performed using the Google Cloud Natural Language API.

[1327] Based on the analysis results, the countermeasure planning function will propose appropriate countermeasures. For example, if the emotion analysis result indicates "stress," it will suggest providing stress management training. Finally, the notification function will notify managers and workers of the proposed countermeasures. Notifications are sent in real time using the Slack API.

[1328] Specific examples

[1329] For example, if a worker provides feedback such as, "My work these days has been very stressful," the emotion analysis engine will determine this as "stress." Based on this result, the countermeasure planning function will suggest providing stress management training, and the notification function will notify the manager of the countermeasure.

[1330] Prompt Sentence Examples

[1331] Collect feedback from workers, analyze their emotions, and develop appropriate measures. For example, if the feedback is "My recent work has been very stressful," the emotion analysis engine will determine this as "stress" and suggest providing stress management training.

[1332] In this way, it becomes possible to grasp employee feedback and changes in emotions in real time and to plan prompt and appropriate measures based on that information, which contributes to creating a comfortable working environment for employees and improving business performance.

[1333] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1334] Step 1:

[1335] The server collects feedback from employees using an interactive ES survey function.

[1336] Input: Employee voice or text feedback.

[1337] Data processing: The voice data is converted into text using voice recognition software (e.g., Google Speech-to-Text API).

[1338] Output: Feedback data in text format.

[1339] Step 2:

[1340] The server sends the collected feedback data to the sentiment analysis function.

[1341] Input: Feedback data in text format.

[1342] Data Computation: Analyze the sentiment of the feedback using a sentiment analysis engine (e.g., Google Cloud Natural Language API).

[1343] Output: Sentiment analysis results (e.g., "stressed," "anxious," "satisfied," etc.).

[1344] Step 3:

[1345] The server plans countermeasures based on the results of emotion analysis.

[1346] Input: Sentiment analysis results.

[1347] Data calculation: Using a generative AI model, countermeasures corresponding to the analysis results are proposed. For example, if the condition is judged to be "stress," the system will suggest providing stress management training.

[1348] Output: Planned measures (e.g., "Provide stress management training").

[1349] Step 4:

[1350] The server notifies administrators and workers of the proposed countermeasures using a notification function.

[1351] Input: proposed measures.

[1352] Data processing: Generate notification messages and send them using a notification system (e.g., Slack API).

[1353] Output: Notification messages sent to managers and workers.

[1354] Step 5:

[1355] The user (administrator or worker) checks the notified countermeasures and takes the necessary action.

[1356] Input: Notification message.

[1357] Specific action: The administrator takes action based on the notified measures, such as scheduling stress management training.

[1358] Output: Measure implementation status.

[1359] In this way, the server can grasp employee feedback and changes in emotions in real time, and based on that, can plan and notify prompt and appropriate measures, which will contribute to creating a comfortable working environment for employees and improving business performance.

[1360] Example 3

[1361] Next, a description will be given of Example 3 of Form Example 3. 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."

[1362] Conventional employee feedback systems make it difficult to fully grasp employee opinions and feelings, making it difficult to formulate appropriate measures. Furthermore, analyzing feedback and formulating improvement measures takes a great deal of time and effort, making them insufficient in today's business environment, where rapid response is required. Furthermore, there was a lack of systems for effectively implementing specific measures that contribute to creating a comfortable working environment for employees and improving business performance.

[1363] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1364] In this invention, the server includes means for having an interactive survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for collecting feedback from employees, means for analyzing the collected feedback using a natural language processing tool, means for extracting frequently occurring keywords and emotions from the analysis results, means for generating improvement measures using a generative AI model based on the extracted data, and means for notifying a manager of the generated improvement measures. This makes it possible to quickly and accurately grasp the opinions and emotions of employees and to plan and implement appropriate countermeasures.

[1365] The "interactive survey function" is a function that collects employee opinions and feelings and highlights issues through two-way communication.

[1366] "Two-way dialogue" is a communication process in which employees and systems exchange information with each other.

[1367] "Means of planning countermeasures to issues" is the process of generating specific improvement measures based on collected data that will contribute to creating a comfortable working environment for employees and improving business performance.

[1368] "Feedback collection methods" are the processes of collecting employee opinions and feelings through digital forms and survey systems.

[1369] A "natural language processing tool" is a software tool for analyzing text data and extracting meaning and emotion.

[1370] "Means for extracting frequently occurring keywords and emotions" refers to the process of identifying and extracting specific keywords and emotions from the analyzed feedback data.

[1371] A "generative AI model" is an artificial intelligence model that automatically generates appropriate improvement measures based on collected data.

[1372] "Means for notifying administrators" refers to the process of communicating generated improvements to administrators via email or messaging tools.

[1373] MODE FOR CARRYING OUT THE INVENTION

[1374] The present invention is a system for collecting and analyzing feedback from employees and formulating appropriate improvement measures. A specific embodiment of this system is described below.

[1375] 1. Gathering feedback

[1376] The server provides a form where employees can enter their feedback. This form is implemented as a web application and can be accessed through a browser. For example, an employee can enter, "Recently, communication within my team has been poor, and I'm feeling stressed," and click the submit button.

[1377] 2. Receiving and storing feedback

[1378] The server receives the submitted feedback and stores it in a database, which uses a relational database (e.g., MySQL or PostgreSQL).

[1379] 3. Feedback Analysis

[1380] The server passes the saved feedback data to a natural language processing (NLP) tool, specifically using Google Cloud Natural Language API or IBM Watson Natural Language Understanding. The server receives the analysis results returned from the NLP tool and extracts frequently occurring keywords and phrases from the feedback. For example, if the keyword "difficulty in communication" appears frequently, it passes that information on to the next step.

[1381] 4. Emotion analysis

[1382] The server uses an emotion engine (e.g., Affectiva or IBM Watson Tone Analyzer) to analyze the emotions contained in the feedback, identifying emotions such as "stress" or "frustration."

[1383] 5. Integrating data and generating remediation measures

[1384] The server integrates data obtained from the NLP tool and the emotion engine. For example, if the keyword "difficulty in communication" and the emotion "stress" appear simultaneously, the server uses this information to proceed to the next step. Based on the integrated data, the server uses a generative AI model to generate improvement measures. For example, it suggests "providing training to improve communication skills" or "creating an open space."

[1385] 6. Notification of remedial measures

[1386] The server notifies administrators of generated remediation actions via email (e.g., Gmail API) or internal messaging tools (e.g., Slack or Microsoft Teams).

[1387] Examples of specific examples and prompts

[1388] A user enters "Recently, communication within the team has been going poorly, and I'm feeling stressed" into the feedback form and clicks the submit button. The server analyzes this feedback and extracts the keywords and emotions of "difficulty in communication" and "stress." Based on this, the server suggests "Providing training to improve communication skills."

[1389] Example prompt sentence:

[1390] "Analyze employee feedback and extract frequently occurring keywords and emotions, such as 'difficulty in communication' or 'stress.'"

[1391] "Based on the extracted keywords and sentiment, propose appropriate improvement measures. For example, 'Provide training to improve communication skills' or 'Establish an open space.'"

[1392] The above is a specific embodiment for carrying out the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1393] Step 1:

[1394] The user enters their opinions and feelings into the feedback form and clicks the submit button. The input data is, for example, text such as "Recently, communication within my team has not been going well, and I am feeling stressed." The server receives this input data and stores it in a database. The output is the feedback data stored in the database.

[1395] Step 2:

[1396] The server passes the saved feedback data to a natural language processing (NLP) tool. Specifically, it uses Google Cloud Natural Language API or IBM Watson Natural Language Understanding. The input is the feedback data retrieved from the database. The server receives the analysis results returned from the NLP tool and extracts frequently occurring keywords and phrases from the feedback. The output is the extracted keywords and phrases.

[1397] Step 3:

[1398] The server uses an emotion engine (e.g., Affectiva or IBM Watson Tone Analyzer) to analyze the emotions contained in the feedback. The input is the feedback data retrieved from the database. The server receives the analysis results returned by the emotion engine and identifies the emotions contained in the feedback. The output is the identified emotion data.

[1399] Step 4:

[1400] The server integrates data from the NLP tool and the emotion engine. The inputs are extracted keywords and phrases and identified emotion data. The server uses a generative AI model to generate remediation recommendations based on this data. The output is the generated remediation recommendations.

[1401] Step 5:

[1402] The server notifies the administrator of the generated remediation. The input is the generated remediation. The notification is via email (e.g., Gmail API) or internal messaging tools (e.g., Slack or Microsoft Teams). The output is the notification sent to the administrator.

[1403] The above is the specific processing flow of the program of this system.

[1404] (Application example 3)

[1405] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1406] The problems are that communication within traditional factories is difficult and the working environment has not been sufficiently improved. In particular, it is difficult to properly understand workers' emotions and feedback and to plan specific measures based on that. This can increase worker stress and reduce work efficiency.

[1407] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1408] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating measures for issues highlighted by the two-way dialogue, means for analyzing employees' emotions using an emotion engine, means for formulating measures for improving the work environment and communication skills based on the analysis results, and means for generating prompt sentences using a generative AI model. This makes it possible to simultaneously grasp the feedback and emotions of workers and quickly formulate specific measures.

[1409] The "interactive ES survey function" is a function that collects information through two-way dialogue in order to visualize the true nature of employees.

[1410] "Two-way interaction" is a form of communication in which the system and the user exchange information with each other.

[1411] "Means for formulating countermeasures" is a function that plans specific improvement measures and countermeasures based on collected information and analysis results.

[1412] An "emotion engine" is a technology that analyzes a user's emotions and identifies their emotional state.

[1413] A "generative AI model" is a model that uses artificial intelligence to generate prompts and other output for a specific task.

[1414] A "prompt" is an instruction that can be input into a generative AI model to obtain a specific output.

[1415] "Improving the working environment" refers to creating a physical and psychological environment that allows workers to work more efficiently and comfortably.

[1416] "Improving communication skills" refers to efforts to improve the ability of employees and workers to effectively communicate information and understand each other.

[1417] The system for implementing this invention includes an interactive ES survey function for visualizing the true nature of employees, an emotion engine, and a prompt sentence generation function using a generative AI model. Specific embodiments are described below.

[1418] System Configuration

[1419] The system consists of three main components: a server, a terminal, and a user.

[1420] server

[1421] The server has the following functions:

[1422] 1. Interactive ES survey function: Provides a chatbot function to collect employee feedback. The chatbot uses artificial intelligence to conduct conversations in natural language.

[1423] 2. Emotion Engine: Analyzes collected feedback data and identifies employee emotions. Natural Language Processing (NLP) technology is used to analyze text data.

[1424] 3. Countermeasure planning function: Based on feedback data and emotion analysis results, measures are planned to improve the work environment and communication skills.

[1425] 4. Generative AI model: Generates prompts and creates instructions to obtain output for a specific task.

[1426] Terminal

[1427] A terminal is a device through which a user inputs feedback, and includes smartphones, tablets, and PCs.

[1428] User

[1429] Users are employees and workers who use the system, input feedback, and receive suggestions for countermeasures from the system.

[1430] Processing flow

[1431] 1. Feedback collection: Users use their devices to enter feedback through an interactive ES survey function, for example, by entering specific opinions such as "I feel stressed because there is too much work."

[1432] 2. Emotion Analysis: The server uses an emotion engine to analyze the feedback data and identify the user's emotion, for example, "stress."

[1433] 3. Countermeasures Planning: Based on the analysis results, the server will propose measures to improve the work environment and communication skills, such as "adjusting the workload" or "introducing tools to improve work efficiency."

[1434] 4. Prompt generation: A generative AI model is used to generate prompts, such as "Collect feedback from workers in the factory and analyze their emotions using an emotion engine. Based on the analysis results, please devise measures to improve the work environment and communication skills."

[1435] Specific examples

[1436] For example, if there is a lot of feedback in a factory that "the workload is too heavy and it's stressful," the emotion engine will identify the emotion as "stress" and suggest countermeasures such as "adjusting the workload" or "introducing tools to improve work efficiency." In this way, it is possible to simultaneously grasp the feedback and emotions of workers and quickly devise specific countermeasures.

[1437] Prompt Sentence Examples

[1438] "Collect feedback from workers in your factory and analyze their emotions using the emotion engine. Based on the analysis results, plan measures to improve the working environment and communication skills."

[1439] In this way, the system can create a comfortable working environment for workers and improve work efficiency.

[1440] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1441] Step 1:

[1442] Users use their devices to input feedback through the interactive ES survey function. Specifically, users provide feedback interactively to the chatbot using devices such as smartphones or PCs. For example, they can input specific opinions such as "I feel stressed because I have too much work to do." The input data is sent to the server in text format.

[1443] Step 2:

[1444] The server passes the received feedback data to the emotion engine. The emotion engine analyzes the text data using natural language processing (NLP) techniques and identifies the user's emotion. For example, it identifies the emotion "stress." The input is the feedback text data, and the output is the identified emotion data.

[1445] Step 3:

[1446] The server uses its countermeasure planning function to propose specific countermeasures based on the emotion data and feedback data obtained from the emotion engine. For example, it may propose "adjusting the workload" or "introducing tools to improve work efficiency." The input is emotion data and feedback data, and the output is the proposed countermeasures.

[1447] Step 4:

[1448] The server generates prompts using a generative AI model. The generative AI model creates instructions for specific tasks based on proposed countermeasures. For example, it generates a prompt such as, "Collect feedback from workers in the factory and analyze their emotions using an emotion engine. Based on the analysis results, devise countermeasures to improve the work environment and communication skills." The input is the proposed countermeasures, and the output is the prompt.

[1449] Step 5:

[1450] The server provides the generated prompt sentence to the user, who can then review it through a terminal and add feedback as needed. This allows the system to continually improve. The input is the prompt sentence, and the output is the user's additional feedback.

[1451] In this way, the system can simultaneously grasp the feedback and emotions of workers and quickly devise specific countermeasures.

[1452] 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.

[1453] 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> ) 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.

[1454] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1455] 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.

[1456] [Third embodiment]

[1457] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1458] 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.

[1459] 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).

[1460] 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.

[1461] 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.

[1462] 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).

[1463] 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.

[1464] 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.

[1465] 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.

[1466] 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.

[1467] 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.

[1468] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1469] "Example 1"

[1470] One aspect of the present invention is a system with an interactive ES survey function that visualizes the true nature of employees. This system uses a chatbot with artificial intelligence to engage in two-way dialogue with employees. The chatbot generates appropriate responses to input from employees and understands their opinions and issues.

[1471] "Example 2"

[1472] Furthermore, one aspect of the present invention is a function that proposes countermeasures for issues that have been identified through two-way dialogue. Based on the identified issues, this function proposes countermeasures that contribute to creating a comfortable working environment for employees and improving business performance. For example, based on feedback from employees, it proposes measures such as improving the work environment, reviewing business processes, and providing education and training.

[1473] "Example 3"

[1474] As a concrete example, if feedback from employees indicates that they often find it difficult to communicate, countermeasures such as providing training to improve communication skills or creating open spaces can be proposed. This will create a comfortable working environment for employees and improve business performance.

[1475] The processing flow of each embodiment will be described below.

[1476] "Example 1"

[1477] Step 1: The system receives input from employees. This input is about their opinions and issues.

[1478] Step 2: The system then uses an artificial intelligence-powered chatbot to generate appropriate responses to the inputs, which are designed to better understand the employee's opinions and challenges.

[1479] Step 3: Finally, the system gathers employee opinions and issues through two-way dialogue and stores them in a database.

[1480] "Example 2"

[1481] Step 1: The system analyzes employee opinions and issues stored in the database.

[1482] Step 2: Next, based on the analysis results, the system will develop measures to create a comfortable working environment for employees and contribute to improving performance.

[1483] Step 3: Finally, the proposed measures are reported to the manager and implemented.

[1484] "Example 3"

[1485] Step 1: If the system detects a lot of "difficulty in communication" in employee feedback, it will identify this as an issue.

[1486] Step 2: Next, the system will develop countermeasures to address this issue, such as "providing training to improve communication skills" and "establishing open spaces."

[1487] Step 3: Finally, the proposed measures are reported to management and implemented, resulting in the creation of a comfortable working environment for employees and improved performance.

[1488] Example 1

[1489] Next, a description will be given of Example 1 of Form 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."

[1490] Traditional engagement surveys have made it difficult to accurately grasp employee opinions and issues, and lacked effective methods for visualizing the true nature of employees. As a result, it has been difficult to create a comfortable working environment for employees and to devise appropriate measures to contribute to improving performance. Furthermore, because real-time two-way dialogue is not possible, it has been impossible to quickly reflect employee opinions and issues.

[1491] 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.

[1492] In this invention, the server includes a means for a user to access the chatbot using a terminal, a means for the terminal to receive user input and send it to the server, a means for the server to generate a response to the user input using a generative AI model, a means for the server to send the generated response to the terminal, a means for the terminal to display the response from the server to the user, and a means for the server to analyze the user's input data and generate a report. This makes it possible to grasp employee opinions and issues in real time and quickly develop appropriate measures.

[1493] The "interactive engagement survey function" is a function that allows for two-way dialogue to understand employees' opinions and issues and visualize their true nature.

[1494] "Two-way dialogue" is a form of dialogue in which the user and the system exchange opinions and information in real time.

[1495] "Measures to address issues" refers to developing appropriate solutions to employee issues that have been highlighted through two-way dialogue.

[1496] A "terminal" is a device used by a user to access the system, including a PC, smartphone, etc.

[1497] The "server" is a central processing unit that receives user input data, generates responses using generative AI models, and analyzes the data.

[1498] A "generative AI model" is an artificial intelligence model that generates appropriate responses based on user input.

[1499] A "chatbot" is a program that interacts with users and generates responses using generative AI models.

[1500] A "report" is a report in which the server analyzes the data entered by the user and summarizes the opinions and issues of employees.

[1501] This invention is a system with an interactive engagement survey function to visualize the true nature of employees. This system is built around a chatbot using artificial intelligence, and grasps employees' opinions and issues through two-way dialogue with users (employees).

[1502] System configuration

[1503] Hardware

[1504] Terminal: A device used by a user to access the system, including a PC or smartphone.

[1505] Server: A central processing unit that receives user input data, generates responses using generative AI models, and analyzes the data.

[1506] software

[1507] Generative AI model: An artificial intelligence model that generates appropriate responses based on user input. Specifically, OpenAI's GPT-4 is used.

[1508] Chatbot: A program that interacts with users and generates responses using generative AI models.

[1509] System Operation

[1510] 1. A user accesses a chatbot using a device

[1511] Users can access the system's chatbot using devices such as PCs or smartphones, for example, through a dedicated web application or mobile application.

[1512] 2. The device receives the user's input and sends it to the server

[1513] When a user inputs text into the chatbot, the device sends the input data to the server. For example, a user might input, "I'm feeling stressed about a recent project."

[1514] 3. The server uses the generative AI model to generate a response to the user's input.

[1515] The server passes the received user input data to a generative AI model (e.g., OpenAI's GPT-4) and generates an appropriate response. Based on the user's input, the generative AI model generates a response such as, "Which specifically are you feeling stressed about?"

[1516] 4. The server generates a response and sends it to the device.

[1517] The server sends the responses generated by the generative AI model to the device, providing an appropriate response to the user's input in real time.

[1518] 5. The device displays the response from the server to the user.

[1519] The terminal displays the response received from the server to the user, who can then confirm the response from the chatbot and enter further details.

[1520] 6. The server analyzes the user's input data and generates a report

[1521] The server analyzes the input data collected from users and generates reports to understand employee opinions and issues, which managers can use to evaluate employee engagement and satisfaction.

[1522] Specific examples

[1523] For example, if a user types "I'm feeling stressed about a recent project," the following specific actions will occur:

[1524] 1. A user uses a device to type into the chatbot, "I'm feeling stressed about a recent project."

[1525] 2. The device sends this input to the server.

[1526] 3. The server uses a generative AI model (GPT-4) to generate a response: "What specifically are you feeling stressed about?"

[1527] 4. The server generates a response and sends it to the terminal.

[1528] 5. The device displays the response to the user: "Where specifically are you feeling stressed?"

[1529] 6. The server analyzes the user's input data and generates a report that includes the causes and frequency of employee stress.

[1530] Prompt Sentence Examples

[1531] Examples of prompts to input to a generative AI model include:

[1532] Prompt: "If an employee types in that they are feeling stressed about a recent project, how would you respond?"

[1533] In response to this prompt, the generative AI model generates the following response:

[1534] Sample response: "What specifically are you stressed about? How is the project progressing? How is your team communicating?"

[1535] In this way, the system visualizes the true nature of employees through dialogue with users and provides useful information to managers.

[1536] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1537] Step 1:

[1538] A user accesses the chatbot using a device

[1539] Users can access the system's chatbot using devices such as PCs or smartphones, for example, through a dedicated web application or mobile application.

[1540] Input: User's access request

[1541] Output: The chatbot interface is displayed.

[1542] Step 2:

[1543] The terminal receives the user's input and sends it to the server

[1544] When a user inputs text into the chatbot, the device sends the input data to the server. For example, a user might input, "I'm feeling stressed about a recent project."

[1545] Input: User text input

[1546] Output: The input data is sent to the server

[1547] Step 3:

[1548] The server uses the generative AI model to generate responses to user input.

[1549] The server passes the received user input data to a generative AI model (e.g., OpenAI's GPT-4) and generates an appropriate response. Based on the user's input, the generative AI model generates a response such as, "Which specifically are you feeling stressed about?"

[1550] Input: User-entered data

[1551] Output: Response data from the generative AI model

[1552] Step 4:

[1553] Sends the server-generated response to the terminal

[1554] The server sends the responses generated by the generative AI model to the device, providing an appropriate response to the user's input in real time.

[1555] Input: Response data from a generative AI model

[1556] Output: Response data is sent to the terminal

[1557] Step 5:

[1558] The terminal displays the response from the server to the user

[1559] The terminal displays the response received from the server to the user, who can then confirm the response from the chatbot and enter further details.

[1560] Input: Response data from the server

[1561] Output: The response data is displayed to the user

[1562] Step 6:

[1563] The server analyzes the user's input data and generates a report

[1564] The server analyzes the input data collected from users and generates reports to understand employee opinions and issues, which managers can use to evaluate employee engagement and satisfaction.

[1565] Input: User-entered data

[1566] Output: Report based on the analysis results

[1567] In this way, the system visualizes the true nature of employees through dialogue with users and provides useful information to managers.

[1568] (Application example 1)

[1569] Next, a description will be given of Application Example 1 of Form 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."

[1570] Conventional interactive ES survey systems focus on collecting employee opinions and issues, but lack the means to collect the opinions and issues of workers working in factories and to improve the work environment and increase efficiency. In addition, there is a need for a system that can devise specific measures based on the information obtained through dialogue with workers.

[1571] 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.

[1572] In this invention, the server includes means having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating measures for issues highlighted by the two-way dialogue, means having an application installed on a robot for collecting opinions and issues of workers working in a factory, means for generating appropriate responses to inputs from workers using a generative AI model, and means for improving the work environment and streamlining the work environment based on the responses. This makes it possible to efficiently collect opinions and issues of workers working in a factory and to improve the work environment and streamline the work environment.

[1573] The "interactive ES survey function" is a function that collects opinions and issues through two-way dialogue in order to visualize the true nature of employees.

[1574] "Two-way dialogue" refers to interactive communication that uses artificial intelligence such as chatbots to exchange opinions with employees and workers in real time.

[1575] "Means for planning countermeasures to issues" refers to the function of planning and proposing specific improvement measures and countermeasures for issues that have been highlighted through two-way dialogue.

[1576] "Factory workers" are employees who perform manufacturing, assembly, and other tasks within a factory.

[1577] The "application installed on the robot" is software that is installed on the robots used in the factory and is used to collect opinions and issues through dialogue with workers.

[1578] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate appropriate responses or results based on input data.

[1579] "Means to improve the work environment and increase efficiency" is a function that implements specific measures to improve the work environment and increase work efficiency based on collected opinions and issues.

[1580] A system for implementing this invention includes means having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for planning countermeasures for issues highlighted by the two-way dialogue, means having an application installed on a robot for collecting the opinions and issues of workers working in a factory, means for generating appropriate responses to inputs from workers using a generative AI model, and means for improving the work environment and increasing efficiency based on the responses.

[1581] Program processing explanation

[1582] The server uses a Python program and the OpenAI API to utilize a generative AI model (e.g., GPT-3). Robots in the factory collect input from workers and send it to the server. The server uses the generative AI model to generate an appropriate response to the worker's input and sends the response back to the robot. The robot communicates the generated response to the worker.

[1583] Hardware and software used

[1584] Hardware: Robots in factories (e.g. collaborative robots)

[1585] Software: Python, OpenAI API

[1586] Data processing and calculation

[1587] Data processing: Input from the human is sent as prompts to the generative AI model.

[1588] Data computation: Generative AI models generate appropriate responses based on worker input.

[1589] Specific examples

[1590] For example, if a worker types, "I feel like the work environment is a little cold lately. Could you please turn up the heating?", the server will use the generative AI model to generate a response that reads, "Thank you for your feedback on the temperature of the work environment. I will report to the relevant department about adjusting the heating."

[1591] Prompt Sentence Examples

[1592] Dialogue with Workers: The working environment has been a little cold lately. Could you please turn up the heating?

[1593] Generate an appropriate response.

[1594] In this way, it is possible to efficiently collect the opinions and issues of workers working in the factory and improve the work environment and increase efficiency.

[1595] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1596] Step 1:

[1597] The user (worker) inputs opinions and issues to the robot. The input data is collected through the robot's sensors and interface. An example of input data is, "I feel like the working environment is a little cold lately. Could you please turn up the heating?"

[1598] Step 2:

[1599] The robot sends the collected input data to a server, which then analyzes the data and converts it into a format suitable for the generative AI model. During this conversion process, the input data is formatted as a prompt sentence.

[1600] Step 3:

[1601] The server sends a prompt to the generative AI model (e.g., GPT-3). The generative AI model generates an appropriate response based on the prompt. For example, if the prompt is "Dialogue with worker: I feel like the work environment is a little cold recently. Could you please turn up the heating?", the generative AI model will generate the response "Thank you for your feedback on the temperature of the work environment. I will report to the relevant department about adjusting the heating."

[1602] Step 4:

[1603] The server receives the response from the generative AI model and sends it to the robot, where it converts the response data into a format that the robot can understand.

[1604] Step 5:

[1605] The robot communicates the response received from the server to the worker. The robot presents the generated response to the worker using audio output and a display. For example, the robot may respond by voice, "Thank you for your feedback on the temperature of the work environment. We will report to the relevant department about adjusting the heating."

[1606] Step 6:

[1607] The server stores the collected opinions, challenges, and generated responses in a database, which is later used for analysis to improve the work environment and streamline it.

[1608] Step 7:

[1609] Based on the stored data, the server will propose specific measures to improve the work environment and increase efficiency, for example, by reporting proposals for adjusting the temperature of the work environment to the relevant department.

[1610] By following the steps above, it is possible to efficiently collect the opinions and issues of workers working in the factory, thereby improving the work environment and increasing efficiency.

[1611] Example 2

[1612] Next, a description will be given of Example 2 of Form 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."

[1613] With conventional interactive survey systems, it was difficult to effectively analyze employee feedback and develop specific countermeasures. Furthermore, there was a lack of means to quickly notify the results of the feedback analysis and implement countermeasures that would contribute to creating a comfortable working environment for employees and improving business performance.

[1614] 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.

[1615] In this invention, the server includes means for having an interactive survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for collecting feedback from users and analyzing the feedback using a generative AI model, and means for formulating specific countermeasures based on the analysis results and notifying the users. This makes it possible to effectively analyze feedback from employees and quickly formulate and notify specific countermeasures.

[1616] The "interactive survey function" is a function that collects and analyzes information through dialogue with the user.

[1617] "Two-way interaction" refers to an interaction in which the user and the system exchange information with each other.

[1618] "Issues" are problems or areas for improvement identified based on feedback from users.

[1619] "Countermeasures" are specific actions or measures implemented to address identified issues.

[1620] A "generative AI model" is a model that uses artificial intelligence to analyze data and generate results.

[1621] A "prompt" is a textual instruction that is input to a generative AI model.

[1622] "Feedback" refers to information such as opinions, impressions, and reports provided by users.

[1623] "Analysis" is the process of finding meaning and patterns based on collected data.

[1624] "Notification" refers to the act of informing the user of the analysis results and countermeasures.

[1625] MODE FOR CARRYING OUT THE INVENTION

[1626] The present invention is a system that visualizes the true nature of employees, identifies issues through two-way dialogue, and proposes measures to address those issues. A specific embodiment of this system will be described below.

[1627] System configuration

[1628] 1. Interactive Survey Feature

[1629] The server has an interactive survey function, which collects and analyzes information through dialogue with users. Specifically, this function is realized by a chatbot using artificial intelligence.

[1630] 2. Two-way dialogue function

[1631] The server uses an interactive survey function to engage in a two-way dialogue with the user, through which feedback is collected from the user.

[1632] 3. Generative AI Models

[1633] The server inputs the collected feedback into a generative AI model (e.g., OpenAI's GPT-4), which analyzes the feedback and identifies challenges.

[1634] 4. Countermeasure planning function

[1635] The server then proposes countermeasures based on the issues identified by the generative AI model, which contribute to creating a comfortable working environment for employees and improving business performance.

[1636] 5. Notification function

[1637] The server notifies the user of the proposed measures, which are sent via the terminal, allowing the user to check the proposed measures.

[1638] Specific examples

[1639] For example, if a user enters feedback such as "Recently, my workload has increased and I've been working a lot of overtime," the device will send this feedback to the server. The server inputs the received feedback into a generative AI model, which then analyzes it to determine that "a review of the business process is necessary." Based on the results of this analysis, the server will propose specific measures, such as reviewing the business process and allocating additional personnel, and notify the user. The user can then check these measures through their device and take the necessary action.

[1640] Prompt Sentence Examples

[1641] "Recently, my workload has increased and I've been working a lot of overtime. Please suggest some solutions to this."

[1642] In this way, the server can effectively analyze feedback from users and quickly plan and notify specific countermeasures.

[1643] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1644] Program processing flow

[1645] Step 1: User Enters Feedback

[1646] Users input feedback about their work environment and work processes into the terminal. For example, they can input specific details such as, "Recently, the workload has increased and I've been working a lot of overtime."

[1647] Input: User feedback text

[1648] Output: Feedback data entered into the terminal

[1649] Step 2: The device sends feedback to the server

[1650] The terminal transmits the feedback input by the user to the server, where the feedback is converted into an appropriate format and then transmitted to the server.

[1651] Input: Feedback data entered into the terminal

[1652] Output: Feedback data sent to the server

[1653] Step 3: The server receives the feedback and inputs it as a prompt to the generative AI model.

[1654] The server receives feedback sent from the device and inputs it as a prompt to a generative AI model (e.g., OpenAI's GPT-4).

[1655] Input: Feedback data sent to the server

[1656] Output: The prompt sentence that is fed into the generative AI model

[1657] Step 4: Generative AI model analyzes feedback and identifies issues

[1658] The generative AI model analyzes the input prompt and identifies issues based on the feedback. For example, based on the feedback that "the workload has increased and overtime is becoming more frequent," it determines that a review of work processes and the allocation of additional personnel are necessary.

[1659] Input: The prompt given to the generative AI model

[1660] Output: Identified issues

[1661] Step 5: The server develops a plan of action based on the identified issues

[1662] The server then proposes countermeasures based on the issues identified by the generative AI model, such as reviewing business processes, allocating additional personnel, and providing education and training.

[1663] Input: Identified issues

[1664] Output: Planned countermeasures

[1665] Step 6: The server notifies the user of the proposed measures

[1666] The server notifies the user of the proposed measures, which are sent via the terminal, allowing the user to check the proposed measures.

[1667] Input: Proposed measures

[1668] Output: The action notified to the user

[1669] Specific examples of operation

[1670] For example, if a user enters feedback such as "Recently, my workload has increased and I've been working a lot of overtime," the device will send this feedback to the server. The server inputs the received feedback into a generative AI model, which then analyzes it to determine that "a review of the business process is necessary." Based on the results of this analysis, the server will propose specific measures, such as reviewing the business process and allocating additional personnel, and notify the user. The user can then check these measures through their device and take the necessary action.

[1671] (Application example 2)

[1672] Next, a description will be given of Application Example 2 of Form 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."

[1673] In conventional factory environments, it was difficult to effectively collect feedback from workers and to develop prompt and appropriate improvement measures based on that feedback. Furthermore, delays in improving the work environment and reviewing business processes led to problems such as a decline in work efficiency and a worsening workplace environment. This could lead to a decline in worker motivation and productivity, ultimately negatively impacting business performance.

[1674] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1675] In this invention, the server includes a means for having an interactive ES survey function for visualizing the true nature of employees, a means for conducting two-way dialogue using the interactive ES survey function, a means for formulating countermeasures for issues revealed by the two-way dialogue, a means for collecting feedback from workers in the factory, a means for generating improvement measures using a generative AI model based on the collected feedback, and a means for presenting the generated improvement measures to the workers. This makes it possible to effectively collect feedback from workers and quickly formulate appropriate improvement measures. This allows for the work environment to be improved and business processes to be reviewed quickly, thereby improving work efficiency and the workplace environment.

[1676] The "interactive ES survey function" is a function that collects and analyzes information through two-way dialogue in order to visualize the true nature of employees.

[1677] "Two-way dialogue" is a form of communication in which the system and the user exchange information with each other.

[1678] "Means for planning countermeasures to issues" is a function for devising specific improvement measures and solutions based on issues that have been highlighted through two-way dialogue.

[1679] "Means for collecting feedback" is a function for collecting information such as opinions, impressions, and problems from workers.

[1680] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate new information or suggestions from input data.

[1681] "Means for generating improvement measures" is a function that uses a generative AI model to devise specific improvement measures based on collected feedback.

[1682] "Means for presenting improvement measures" is a function that communicates the generated improvement measures to workers in an easy-to-understand manner.

[1683] The system for implementing this invention includes a series of processes that collect feedback from workers in a factory, generate improvement measures using a generative AI model based on the feedback, and present the measures to the workers. A specific embodiment of this system will be described below.

[1684] Hardware and Software Configuration

[1685] 1. Hardware:

[1686] Robot: A robot that interacts with workers in a factory.

[1687] Server: A server for running generative AI models and processing data.

[1688] 2. Software:

[1689] Interactive ES survey function: An interactive survey function that visualizes the true nature of employees. Implemented as a chatbot using artificial intelligence.

[1690] Generative AI models: Use generative AI models such as OpenAI's GPT-3 to generate improvements based on feedback.

[1691] Data collection and presentation capabilities: Software for collecting feedback from workers and presenting generated improvement recommendations.

[1692] Data processing and calculation flow

[1693] 1. Gathering Feedback:

[1694] The robot interacts with workers and collects feedback about the work environment and work processes.

[1695] The collected feedback is sent to a server.

[1696] 2. Generating improvement measures using generative AI models:

[1697] The server inputs the collected feedback into a generative AI model.

[1698] The generative AI model generates specific improvement measures based on the input feedback.

[1699] The generated remediation measures are stored on the server.

[1700] 3. Proposal of improvement measures:

[1701] The server sends the generated remedial measures to the robot.

[1702] The robot will suggest improvements to the worker and engage in additional dialogue as needed.

[1703] Specific examples

[1704] For example, if a worker gives feedback that "the workspace is too small and inefficient," the generative AI model will generate the following improvement measures:

[1705] We will review the layout of your workspace and propose new arrangements to ensure efficient movement.

[1706] These improvement measures are presented to workers through the robot and can be used to improve the working environment.

[1707] Prompt Sentence Examples

[1708] Below is an example of a prompt that can be fed into a generative AI model:

[1709] Based on the feedback below, please suggest ways to improve the factory environment.

[1710] Feedback: The workspace is small and inefficient

[1711] In this way, the system can effectively collect feedback from workers, develop quick and appropriate improvement measures, and improve the working environment and review business processes.

[1712] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1713] Step 1:

[1714] The robot interacts with workers and collects feedback about the work environment and work processes.

[1715] Input: Verbal or textual feedback from the worker.

[1716] Output: Collected feedback data.

[1717] How it works: The robot uses a built-in microphone and text input interface to collect feedback from workers in real time, which is then sent to a server as text data.

[1718] Step 2:

[1719] The server generates prompt sentences to input the collected feedback into the generative AI model.

[1720] Input: Collected feedback data.

[1721] Output: The prompt sentence to be input to the generative AI model.

[1722] Specific operation: The server analyzes the feedback data and generates an appropriate prompt. For example, in response to the feedback "The work space is small and inefficient," the server generates the prompt "Please suggest improvements to the factory environment based on the following feedback. Feedback: The work space is small and inefficient."

[1723] Step 3:

[1724] The server inputs a prompt sentence into the generative AI model and generates an improvement plan.

[1725] Input: The generated prompt statement.

[1726] Output: The improvements generated by the generative AI model.

[1727] Specific operation: The server inputs the generated prompt sentence into a generative AI model such as OpenAI's GPT-3. The generative AI model generates specific improvement measures based on the prompt sentence and returns them to the server.

[1728] Step 4:

[1729] The server sends the generated remedial measures to the robot.

[1730] Input: The improvements generated by the generative AI model.

[1731] Output: Remediation data sent to the robot.

[1732] Specific operation: The server sends the generated improvement measures to the robot as text data. The robot receives this data and prepares to present it to the worker.

[1733] Step 5:

[1734] The robot will suggest improvements to the worker and engage in additional dialogue as needed.

[1735] Input: Remediation data sent from the server.

[1736] Output: Suggested improvements and additional feedback to the worker.

[1737] Specific operation: The robot presents the received improvement measures to the worker via voice or text. If the worker provides additional feedback, the robot collects the feedback again and sends it to the server, thereby further improving the accuracy of the improvement measures.

[1738] Example 3

[1739] Next, a third embodiment of the third embodiment will be described. 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."

[1740] With conventional employee feedback systems, it was difficult to effectively identify employees' fundamental issues and develop appropriate countermeasures. Furthermore, feedback data was often collected and analyzed manually, making it difficult to develop efficient countermeasures. This resulted in issues such as the inability to create a comfortable working environment for employees or to fully improve business performance.

[1741] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1742] In this invention, the server includes means for having an interactive survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for collecting feedback data from employees, means for pre-processing the collected feedback data, means for extracting and analyzing keywords from the pre-processed data, means for generating countermeasures based on the analysis results, and means for presenting and implementing the generated countermeasures. This makes it possible to efficiently collect and analyze employee feedback and quickly formulate and implement appropriate countermeasures.

[1743] The "interactive survey function" is a function for collecting employee feedback and clarifying issues through two-way communication.

[1744] "Two-way dialogue" is a form of communication in which employees and systems exchange information with each other.

[1745] "Issue solutions" are specific action plans or measures to solve specific problems based on employee feedback.

[1746] "Feedback data" refers to information such as opinions, impressions, and evaluations provided by employees.

[1747] "Preprocessing" refers to processes such as cleaning, tokenizing, and removing stop words from collected feedback data to make it easier to analyze.

[1748] "Keyword extraction" is the process of identifying important words and phrases from feedback data.

[1749] "Analysis" is the process of understanding the content of the feedback and finding patterns and trends based on extracted keywords and data.

[1750] "Generating countermeasures" is the process of proposing specific solutions and improvements based on the analysis results.

[1751] "Presenting" is the act of showing the generated countermeasure plan to the user.

[1752] "Implementation" is the process of actually putting the proposed countermeasures into action.

[1753] This invention is a system that efficiently collects and analyzes feedback from employees and promptly plans and implements appropriate measures. A specific embodiment of this system will be described below.

[1754] The server has an interactive survey function that visualizes the true nature of employees. This interactive survey function uses a chatbot with artificial intelligence to collect feedback from employees. For example, feedback can be collected through an internal survey system, email, or chat tool.

[1755] The collected feedback data is pre-processed by the server, which includes data cleaning (removing unnecessary characters and symbols), tokenization (dividing sentences into words), and stop-word removal (removing frequent but meaningless words). This process is performed using Python libraries such as NLTK and spaCy.

[1756] The server extracts and analyzes keywords from the preprocessed data. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) and word clouds to identify frequently occurring keywords in the feedback. It checks whether there are many keywords related to "difficulty in communication," in particular.

[1757] Based on the analysis results, the server generates countermeasures. It uses a generative AI model to propose appropriate countermeasures. For example, the following prompt sentence is input into the generative AI model:

[1758] "Analyze employee feedback and generate countermeasures, especially when there is a lot of feedback about 'difficulty in communication.' Specific countermeasures include 'offering training to improve communication skills' and 'establishing open spaces.'"

[1759] The generated countermeasures are presented to the user via the terminal. The user can review the countermeasures and implement them as necessary. For example, they can arrange a training program to implement "training to improve communication skills." This will help create a comfortable working environment for employees and improve business performance.

[1760] For example, consider the following feedback from an employee:

[1761] "I feel like communication within the team hasn't been going well recently."

[1762] "There are few opportunities to share project progress."

[1763] "Communication is difficult when working remotely."

[1764] The server collects this feedback and analyzes it using NLP technology. As a result of the analysis, it is found that there is a lot of feedback about "difficulty in communication." Therefore, the server generates the following countermeasures:

[1765] "Provide training to improve communication skills."

[1766] "We will set up an open space and create a place where employees can communicate freely with each other."

[1767] The user can check these measures and put them into practice to create a comfortable working environment for employees and improve business performance. The flow of the specific process in the third embodiment will be described with reference to FIG.

[1768] Step 1:

[1769] The server collects feedback data from employees. The input includes feedback from the company's internal survey system, email, and chat tools. This data is collected centrally and stored in a database. The output is the collected feedback data.

[1770] Step 2:

[1771] The server preprocesses the collected feedback data. The input is the collected feedback data. Specific operations include cleaning the data (removing unnecessary characters and symbols), tokenizing (dividing sentences into words), and removing stop words (removing frequent but meaningless words). The output is the preprocessed data.

[1772] Step 3:

[1773] The server extracts and analyzes keywords from the preprocessed data. The input is the preprocessed data. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) and word clouds to identify frequently occurring keywords in the feedback. The output is the extracted keywords and their frequency information.

[1774] Step 4:

[1775] The server generates countermeasures based on the analysis results. The inputs are the extracted keywords and their frequency information. Specifically, it uses a generative AI model to suggest appropriate countermeasures. For example, the following prompt is input into the generative AI model: "Analyze feedback from employees and generate countermeasures in cases where there is a lot of feedback, especially regarding 'difficulty in communication.' Specific countermeasures include 'providing training to improve communication skills' and 'establishing open spaces.'" The generated countermeasures are obtained as output.

[1776] Step 5:

[1777] The terminal presents the generated countermeasure plan to the user. The input is the generated countermeasure plan. The specific operation is to display the countermeasure plan on the user's screen. The output is a state in which the user can check the countermeasure plan.

[1778] Step 6:

[1779] The user checks the proposed countermeasures and implements them as necessary. The input is the proposed countermeasures. A specific action, for example, arranging a training program to implement "training to improve communication skills," is the output: the countermeasures are implemented, creating a comfortable working environment for employees and improving performance.

[1780] (Application example 3)

[1781] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1782] Conventional employee feedback systems lack specific measures to address communication difficulties, making it difficult to create a comfortable working environment for employees and contribute to improving business performance. In addition, feedback collection and analysis are often done manually, making it difficult to develop efficient measures.

[1783] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1784] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating countermeasures for issues highlighted by the two-way dialogue, means for collecting feedback and proposing countermeasures based on the analysis results, means for providing training content for improving communication skills based on the proposed countermeasures, and means for proposing the establishment of open spaces and layout changes. This makes it possible to efficiently collect and analyze employee feedback and quickly formulate and implement specific countermeasures.

[1785] The "Interactive ES Survey Function" is a function that conducts an engagement survey in an interactive format in order to visualize the true nature of employees.

[1786] "Two-way dialogue" is a process in which employees and the system exchange information with each other using the interactive ES survey function.

[1787] "Means for formulating countermeasures for issues" is a function for devising specific solutions to issues that have been highlighted through two-way dialogue.

[1788] "Means for collecting feedback" is a function for efficiently gathering opinions and feedback from employees.

[1789] "Means for proposing measures based on analysis results" is a function for analyzing collected feedback and proposing appropriate measures based on the results.

[1790] "Means of providing training content to improve communication skills" is a function that provides educational materials and programs to improve employees' communication abilities.

[1791] "Means to propose the creation of open spaces and layout changes" is a function that makes suggestions to improve the design and layout of workspaces in order to create an environment where employees can work comfortably.

[1792] A system for implementing this invention includes a server having an interactive ES survey function for visualizing the true nature of employees, a terminal for conducting two-way dialogue using the interactive ES survey function, and a program for planning countermeasures for issues that are highlighted by the two-way dialogue.

[1793] The server is equipped with a chatbot that uses artificial intelligence to collect feedback from employees. The collected feedback is analyzed within the server, and issues such as difficulty in communication are identified. Based on this, the server proposes specific measures.

[1794] The terminal is a device such as a smartphone or PC that provides an interface for employees to enter feedback. The feedback entered from the terminal is sent to a server and analyzed.

[1795] Based on the analysis results, the server provides training content to improve communication skills. It also proposes the creation of open spaces and layout changes, thereby creating a comfortable working environment for employees and improving business performance.

[1796] As a concrete example, the following feedback may be collected:

[1797] "It's difficult to communicate with robots."

[1798] "It's hard to communicate instructions while working"

[1799] "There are a lot of mistakes due to lack of communication."

[1800] Based on this feedback, the following prompt sentences are input into the generative AI model:

[1801] Example prompt sentence:

[1802] Feedback content:

[1803] 1. It's difficult to communicate with robots

[1804] 2. It's difficult to communicate instructions while working

[1805] 3. Lack of communication leads to many mistakes

[1806] Based on this feedback, suggest appropriate measures.

[1807] By inputting this prompt into a generative AI model, the server can obtain more specific countermeasures, such as providing training programs to improve communication skills or changing the layout of the workspace.

[1808] In this way, employee feedback can be collected and analyzed efficiently, and specific measures can be quickly developed and implemented.

[1809] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1810] Step 1:

[1811] The user uses the terminal to enter feedback.

[1812] Input: Feedback entered by the user into the device (e.g., "It's difficult to communicate with the robot").

[1813] Output: Feedback data sent from the device to the server.

[1814] Specific actions: The user enters feedback through the interface of a smartphone or computer and presses the send button.

[1815] Step 2:

[1816] The server collects the feedback.

[1817] Input: Feedback data sent from the device.

[1818] Output: Feedback data stored on the server.

[1819] Specific operation: The server receives the feedback data sent from the terminal and stores it in a database.

[1820] Step 3:

[1821] The server analyzes the feedback.

[1822] Input: Feedback data stored on the server.

[1823] Output: Analysis results (e.g., issues related to communication difficulties).

[1824] What it does: The server uses natural language processing (NLP) algorithms to analyze the feedback data and extract specific keywords and phrases.

[1825] Step 4:

[1826] The server generates a prompt based on the parsing results.

[1827] Input: Analysis results.

[1828] Output: The generated prompt statement.

[1829] Specific operation: Based on the analysis results, the server automatically generates prompt sentences to input into the generative AI model.

[1830] Example prompt sentence:

[1831] Feedback content:

[1832] 1. It's difficult to communicate with robots

[1833] 2. It's difficult to communicate instructions while working

[1834] 3. Lack of communication leads to many mistakes

[1835] Based on this feedback, suggest appropriate measures.

[1836] Step 5:

[1837] The server inputs a prompt sentence into the generative AI model and obtains countermeasure proposals.

[1838] Input: The generated prompt statement.

[1839] Output: Countermeasure proposals from the generative AI model.

[1840] Specific operation: The server inputs a prompt sentence into the generative AI model and obtains the countermeasures returned by the model.

[1841] Step 6:

[1842] The server proposes specific countermeasures based on the proposed countermeasures.

[1843] Input: Countermeasure proposals from a generative AI model.

[1844] Output: Specific countermeasure proposals (e.g., training content to improve communication skills, proposals for establishing open spaces).

[1845] Specific operation: The server proposes specific countermeasures to employees based on the countermeasures obtained from the generative AI model.

[1846] Step 7:

[1847] The user checks and implements the proposed measures.

[1848] Input: Specific measures proposed by the server.

[1849] Output: The results of the measures taken (e.g., attending training, creating open spaces).

[1850] Specific actions: The user checks the measures proposed by the server and takes action as necessary, for example, participating in training or setting up an open space.

[1851] 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.

[1852] "Example 1"

[1853] One embodiment of the present invention is a system that incorporates an emotion engine. This system has an interactive ES survey function that visualizes the true nature of employees, and uses the interactive ES survey function to conduct two-way dialogue. Furthermore, the emotion engine is used to analyze emotions from text input by employees, and the results are used as part of the dialogue. Specifically, if an employee inputs the text "Work didn't go well today," the emotion engine analyzes the text for emotions such as "disappointment" or "disappointment." Then, based on the analysis results, the interactive ES survey function provides an appropriate response to the employee.

[1854] "Example 2"

[1855] Another embodiment of the present invention is a system that proposes countermeasures based on the results of emotion analysis by an emotion engine. This system grasps changes in employees' emotions in real time and proposes countermeasures in response to those changes. Specifically, if the system senses that an employee's emotions are leaning toward "stress" or "anxiety," it proposes countermeasures such as "providing stress management training" or "strengthening the mental health support system."

[1856] "Example 3"

[1857] Another embodiment of the present invention is a system that combines an emotion engine with an interactive employee satisfaction survey function. This system simultaneously grasps employees' emotions and opinions and combines them to gain a deeper understanding. Specifically, it simultaneously grasps an employee's opinion that "I'm stressed because I have too much work" and their feelings of "stress," and based on the results, it proposes measures such as "adjusting the amount of work" or "introducing tools to improve work efficiency."

[1858] The processing flow of each embodiment will be described below.

[1859] "Example 1"

[1860] Step 1: Employees enter text through the interactive ES survey function.

[1861] Step 2: The emotion engine analyzes the emotions from the employee's text input.

[1862] Step 3: The interactive ES survey function uses the analysis results of the emotion engine to respond to employees.

[1863] "Example 2"

[1864] Step 1: The emotion engine identifies changes in employee emotions in real time.

[1865] Step 2: The emotion engine develops measures that correspond to changes in emotions.

[1866] Step 3: The planned measures are implemented to improve employee sentiment.

[1867] "Example 3"

[1868] Step 1: Employees enter their feelings and opinions through the interactive ES survey function.

[1869] Step 2: The emotion engine analyzes the emotions from the employee's text input.

[1870] Step 3: The interactive ES survey function combines the analysis results of the emotion engine with the opinions of employees to develop countermeasures.

[1871] Step 4: The proposed measures are implemented to improve employee sentiment and reflect their opinions.

[1872] Example 1

[1873] Next, a description will be given of Example 1 of Form 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."

[1874] With conventional interactive ES survey systems, it was difficult to accurately grasp employees' opinions and feelings, making it difficult to formulate appropriate measures. Furthermore, the system lacked the functionality to analyze employees' feelings and adjust responses based on them, making it difficult to fully visualize the true nature of employees. This made it difficult to effectively implement measures that would contribute to creating a comfortable working environment for employees and improving business performance.

[1875] 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.

[1876] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for formulating measures for issues highlighted by the two-way dialogue, means for receiving user input, means for analyzing the received input, means for generating an appropriate response based on the analysis results, means for performing emotion analysis, means for adjusting the response based on the emotion analysis results, and means for displaying the adjusted response to the user. This makes it possible to accurately grasp the opinions and emotions of employees and to formulate appropriate measures.

[1877] The "interactive ES survey function" is a function that collects employees' opinions and feelings and makes the true nature of employees visible through two-way dialogue.

[1878] "Two-way interaction" is a form of interaction in which a user and a system exchange information with each other, and is a process in which the system returns a response to a user's input.

[1879] "Means of planning countermeasures to issues" is the function of coming up with appropriate solutions to the issues employees face that have been highlighted through two-way dialogue.

[1880] "Means for receiving user input" refers to a function that receives text or data sent by a user to the system through a terminal.

[1881] The "means for analyzing received input" is a function for analyzing text or data received from a user and understanding its content.

[1882] The "means for generating an appropriate response" is a function for generating an appropriate reply to the user based on the analysis results.

[1883] The "means for performing emotion analysis" is a function for analyzing emotions from the user's text input and identifying those emotions.

[1884] The "means for adjusting the response based on the emotion analysis result" is a function that takes into account the emotion analysis result and appropriately changes the response to the user.

[1885] The "means for displaying the adjusted response to the user" is a function for transmitting the adjusted response to the user's terminal and displaying it on the screen.

[1886] This invention is an interactive ES survey system that visualizes the true nature of employees. This system combines an AI-based chatbot with an emotion analysis engine to collect opinions and emotions through two-way dialogue with employees and then formulates appropriate measures.

[1887] Hardware and software used

[1888] Hardware: Servers, terminals (PCs, smartphones)

[1889] Software: Chatbots (e.g., Dialogflow), sentiment analysis engines (e.g., IBM Watson Tone Analyzer)

[1890] System Overview

[1891] 1. User input:

[1892] The user uses a device to input text into the chatbot, for example, "Work didn't go well today."

[1893] 2. Server receives input:

[1894] The server receives input from the user and passes it to the chatbot, which then converts the input into JSON format and sends it to the chatbot's API.

[1895] 3. Chatbot response generation:

[1896] The chatbot generates an initial response to the user's input. For example, if the user inputs "Work didn't go well today," the chatbot generates a response such as "That must have been tough."

[1897] 4. Emotion analysis:

[1898] The server sends the chatbot's initial response and the user's input to the emotion analysis engine, which analyzes the user's emotions from the text. Specifically, it extracts emotions such as "disappointment" or "disappointment" from the text "Work didn't go well today."

[1899] 5. Adjusting the response:

[1900] The chatbot receives the results of the sentiment analysis and adjusts its response accordingly. For example, if the sentiment analysis results in "disappointment" or "disappointment," the chatbot might change its response to something like, "You've had a tough day. Is there anything I can help you with?"

[1901] 6. Displaying the response to the user:

[1902] The server sends the chatbot's final response to the user's device and displays it to the user, such as a message like, "You've had a rough day. Is there anything I can help you with?"

[1903] Examples and prompts

[1904] Examples:

[1905] User input: "Work didn't go well today."

[1906] Sentiment analysis engine analysis results: "Disappointed", "Disappointed"

[1907] The chatbot responds: "You've had a tough day. Is there anything I can help you with?"

[1908] Example prompt for a generative AI model:

[1909] If a user types "Work didn't go well today," use a sentiment analysis engine to analyze the sentiment and generate an appropriate response based on that.

[1910] This system makes it possible to accurately grasp the opinions and feelings of employees and devise appropriate measures, thereby contributing to creating a comfortable working environment for employees and improving business performance.

[1911] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1912] Step 1:

[1913] A user inputs text into the chatbot using a terminal, for example, "Work didn't go well today." The input text is sent from the terminal to the server.

[1914] Step 2:

[1915] The server receives input from the user. It converts the received text data into JSON format and sends it to the chatbot's API. The input is the user's text, and the output is JSON format data.

[1916] Step 3:

[1917] The chatbot generates an initial response to the user input received from the server. For example, it generates a response such as "That must have been difficult." The input is the user's text data in JSON format, and the output is the initial response text.

[1918] Step 4:

[1919] The server sends the chatbot's initial response and the user's input to the sentiment analysis engine. The sentiment analysis engine analyzes emotions from the user's text. Specifically, it extracts emotions such as "disappointment" or "disappointment" from the text "Work didn't go well today." The input is the user's text and the chatbot's initial response, and the output is the sentiment analysis result.

[1920] Step 5:

[1921] The chatbot receives the results of the sentiment analysis and adjusts the response. For example, if the result of the sentiment analysis is "disappointed" or "disappointed," the chatbot changes the response to something like, "You've had a tough day. Is there anything I can help you with?" The input is the sentiment analysis result, and the output is the adjusted response text.

[1922] Step 6:

[1923] The server sends the chatbot's final response to the user's device, which receives the response and displays it on its screen. For example, the message might read, "You've had a rough day. Is there anything I can help you with?" The input is the tailored response text, and the output is the message displayed on the user's device.

[1924] (Application example 1)

[1925] Next, a description will be given of Application Example 1 of Form 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."

[1926] While conventional interactive ES survey systems can grasp employee opinions and issues, it is difficult to analyze emotions and take appropriate action. Furthermore, while there is a need to understand the emotions and opinions of factory workers in real time and take appropriate action, there was no effective way to achieve this. This could lead to a decline in worker satisfaction and work efficiency.

[1927] 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.

[1928] In this invention, the server includes means for having an interactive ES survey function for visualizing the true nature of employees, means for conducting two-way dialogue using the interactive ES survey function, means for planning measures for issues highlighted by the two-way dialogue, means for analyzing the emotions and opinions of workers and taking appropriate measures, means for generating responses to inputs by workers using a generative AI model, and means for responding to encouragement to workers based on the results of the emotion analysis. This makes it possible to grasp the emotions and opinions of workers in real time and take appropriate m...

Claims

1. A means for acquiring user input for a chatbot having an interactive engagement survey function and a two-way dialogue function for visualizing the true nature of employees; A means for generating a response to the acquired user input using a generative AI model; means for presenting said response to a user through said chatbot; means for analyzing user input and generating reports; A system including:

2. A means of collecting employee feedback data; A means for pre-processing the collected feedback data; means for extracting and analyzing keywords from the preprocessed data; A means for generating countermeasures based on the analysis results; A means for presenting the generated countermeasures; A system including:

3. A means for acquiring user input for a chatbot having an interactive engagement survey function and a two-way dialogue function for visualizing the true nature of employees; A means for generating a response to the acquired user input using a generative AI model; A means for performing sentiment analysis; means for adjusting the response based on sentiment analysis results; means for presenting the adjusted response to the user; A system including:

Images