system

Abstract

We provide the system. [Solution] The means of designing and distributing questionnaires, A means for collecting and analyzing responses to the aforementioned questionnaire, A means for generating improvement suggestions based on analysis results, A means for generating and notifying an action plan based on the aforementioned improvement proposal, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Enhancing employee engagement is an important issue for companies, but achieving this requires quickly and accurately collecting feedback from employees and taking appropriate actions. However, with conventional methods, the design of questionnaires, the collection and analysis of responses, and the implementation of improvement measures based on feedback are complicated and time-consuming, making it difficult to effectively improve employee engagement. Therefore, there is a need for a system that can efficiently perform these processes.

Means for Solving the Problems

[0005] This invention relates to a system that automatically collects and analyzes employee opinions and satisfaction levels, and based on this, creates appropriate feedback and action plans for improvement. The system includes means for designing and distributing questionnaires, means for collecting and analyzing questionnaire responses, means for generating improvement suggestions based on the analysis results, and means for generating and notifying action plans based on the improvement suggestions. This makes it possible to quickly and accurately reflect employee feedback in business activities and effectively improve employee engagement.

[0006] A "survey" is a collection of questions based on a specific purpose, and is a method for collecting feedback and opinions from the target audience.

[0007] "Design and distribution" refers to the process of creating a questionnaire for a specific target group of people and delivering that questionnaire through appropriate channels.

[0008] "Collection and analysis" refers to the process of gathering data obtained from distributed questionnaires and analyzing its contents.

[0009] "Sentiment analysis" is a technique that extracts emotional elements from collected feedback and determines whether they are positive or negative.

[0010] An "improvement proposal" is a specific measure to improve or optimize a given issue, based on the analyzed data.

[0011] An "action plan" is a document that outlines the steps to take in formulating a concrete action plan based on improvement suggestions and putting it into practice.

[0012] "Tracking implementation status" is the process of checking the progress of an action plan and monitoring whether it is being carried out as planned. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0027] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The employee engagement assistant according to the present invention is a system for improving employee satisfaction within a company and streamlining the direct implementation of feedback. This system primarily uses a server, terminals, and users to perform various processes.

[0035] The server first uses a generative AI model to design a survey for the target employees. The designed survey is dynamically adjusted based on specific needs and objectives, ensuring it includes appropriate questions tailored to each employee's role and responsibilities. This survey is then distributed to employees via email or a dedicated application.

[0036] The terminal notifies employees that a survey has been distributed and provides an interface for them to review and respond to its contents. Employees, as users, answer the questions displayed on the terminal, and their responses are immediately transmitted to the server. The server stores the collected data in a database and then performs sentiment analysis to reveal the emotional tone of the feedback.

[0037] Based on the analysis results, the server generates specific improvement suggestions to enhance employee engagement. These suggestions identify problems across the entire company or within specific departments and develop solutions. Based on the proposed improvements, it automatically generates more specific action plans and notifies the relevant personnel as needed.

[0038] The administrator, as a user, receives notifications from the server, reviews the proposed action plan, and makes necessary adjustments and allocates resources as needed. In this process, feedback directly related to practical work is easily incorporated, such as "generalizing feedback from monthly meetings" or "making further adjustments to improve workplace comfort."

[0039] The system of this invention helps to ensure that plans are progressing appropriately by regularly tracking the progress of action plans and providing administrators with notifications as needed. In this way, a series of steps for improving engagement are efficiently managed, leading to increased corporate productivity and sustained improvements in employee satisfaction.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server designs surveys according to the company's needs. It utilizes a generative AI model to set appropriate questions based on employee roles and job responsibilities. After design, the surveys are distributed to employees via email or a dedicated application.

[0043] Step 2:

[0044] The terminal notifies employees of the distribution of the survey and displays an interface for answering. Employees, as users, answer the questions on the terminal and send their responses to the server.

[0045] Step 3:

[0046] The server stores the received survey responses in a database. Next, it performs sentiment analysis of the responses using natural language processing techniques to identify positive and negative feedback.

[0047] Step 4:

[0048] Based on the results of sentiment analysis, the server automatically generates specific improvement suggestions to enhance employee engagement. These suggestions are designed to address issues at the overall level or in specific departments.

[0049] Step 5:

[0050] Based on the proposed improvements, the server will create a concrete action plan and notify the relevant departments. The notification will include the necessary resource allocation and implementation plan.

[0051] Step 6:

[0052] The administrator, as a user, reviews the notified action plan and, if necessary, arranges resources and prepares for specific implementation.

[0053] Step 7:

[0054] The server tracks the implementation status of the action plan. It monitors whether progress is on track and notifies responsible parties of reminders as needed.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] Effectively improving employee engagement within a company is crucial for increasing organizational productivity. However, traditional approaches have limitations in accurately collecting and analyzing employee feedback, resulting in challenges in the rapid development and implementation of improvement measures. Furthermore, the process of analyzing the emotional aspects of feedback and translating this into concrete action plans is not sufficiently automated.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for designing a questionnaire based on prompt text using a generative AI model, means for distributing the designed questionnaire via electronic notification, and means for collecting questionnaire responses and storing them in a database. This enables immediate analysis of employee feedback and the automatic generation of specific improvement suggestions and action plans based on emotional tendencies.

[0060] A "generative AI model" is an algorithm that learns from data and generates information based on natural language prompts.

[0061] A "prompt statement" is an instruction given to a generative AI model for generating information.

[0062] A "survey" is a set of questions designed to collect specific information.

[0063] "Electronic notification" refers to a method of transmitting information to a recipient in a digital format.

[0064] A "database" is a system that systematically stores information and saves it in a searchable format.

[0065] "Sentiment analysis" is the process of identifying emotional tendencies and feelings within text data.

[0066] An "improvement suggestion" is specific advice or a strategy for solving a particular problem.

[0067] An "action plan" is a specific plan of actions to be taken in order to achieve a particular goal.

[0068] This system aims to improve employee engagement and consists mainly of three elements: servers, terminals, and users.

[0069] Server embodiment:

[0070] The server designs the survey using a generative AI model, generating individual questions by inputting prompts during this process. The generative AI model used is a large-scale natural language processing model. The survey is dynamically adjusted to include questions specific to job roles and responsibilities within the company. For example, a prompt such as "Create questions about stress management for the sales department" will generate questions tailored to a specific job role. This designed survey is then delivered to terminals via electronic means. Simultaneously, the server manages the response data and performs sentiment analysis on the collected responses. This utilizes sentiment analysis software to extract emotional tendencies from the text data.

[0071] Terminal embodiment:

[0072] The terminal receives questionnaires distributed from the server and displays them to employees as a user interface. Users answer the questionnaires through this terminal and input data processed by a generative AI model. The responses are sent to the server in real time and stored in the database.

[0073] User embodiment:

[0074] Employees, as users, can easily access distributed questionnaires and freely provide feedback and opinions on their daily work. Administrators, as users, receive proposed improvement measures and action plans via notifications from the server and begin implementing the measures. For example, if there is a suggestion to "hold lunch meetings to strengthen communication between teams," administrators can use this as a basis to create a concrete action plan.

[0075] In this way, the collaboration between the server, terminal, and user enables an efficient feedback loop for improving engagement.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server designs the survey using a generative AI model. A prompt is provided as input, and the generative AI model generates questions appropriate to each employee's role and responsibilities. The resulting survey is provided as a set of questions tailored to individual needs. Specifically, the prompt "Create questions about improving teamwork for the marketing department" is used as input, and the result is output as a set of questions.

[0079] Step 2:

[0080] The server distributes the designed questionnaires to employee terminals via email or a dedicated application. The inputs used are the questionnaire to be distributed and the recipient employee's email address or application identifier. The output is achieved by transmitting these to the terminals over the internet.

[0081] Step 3:

[0082] The terminal notifies employees of distributed surveys and provides an interface to display their contents. The input is survey data received from the server, which is output in the form of a notification and displayed on the screen. Specific actions include the display of pop-up notifications and in-application messages on the terminal screen.

[0083] Step 4:

[0084] Employees, as users, answer surveys through the terminal's interface. The input is the response data entered by the user on the interface. As output, this response data is sent from the terminal to the server and stored in a database. Specifically, data is collected through selection of options and text input.

[0085] Step 5:

[0086] The server performs sentiment analysis using the received survey responses. The input data is the responses submitted by the user, and the output is the analysis results. The sentiment analysis software identifies emotional tendencies within the text data and classifies them into categories such as positive, negative, and neutral.

[0087] Step 6:

[0088] The server generates improvement suggestions based on the sentiment analysis results. The analysis results are used as input, and the generating AI model is used again to output specific suggestions. As a result, optimal improvement measures based on employee feedback are proposed. For example, "improving team morale through improved communication" might be output.

[0089] Step 7:

[0090] The server automatically creates an action plan based on the generated improvement suggestions and notifies the administrator user. The input is the generated improvement suggestions, and the notification informs the administrator of the next steps to implement the plan. Specifically, the administrator is notified via email or internal company communication tools.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] In today's work environment, where collaboration between employees and machinery is increasing, improving employee satisfaction and obtaining effective feedback are crucial challenges. Conventional methods have failed to efficiently collect employee feedback, making it difficult to quickly propose improvements and formulate action plans. This invention aims to provide a means for continuously and efficiently obtaining employee feedback in a collaborative environment with machinery, and for quickly implementing improvement measures based on that feedback.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for designing and distributing questionnaires, means for collecting and analyzing responses to the questionnaires, means for generating improvement suggestions based on the analysis results, means for generating and notifying action plans based on the improvement suggestions, means for obtaining feedback in a collaborative environment with work machines, and means for processing the collected feedback. This makes it possible to efficiently obtain feedback from employees and to quickly and accurately improve the work environment.

[0096] A "survey" is a set of questions designed to collect information, primarily used to assess employees' opinions and feelings.

[0097] "Means of design and distribution" refers to the process or technology for determining the content of the questionnaire and supplying it to the target audience.

[0098] "Means for collecting and analyzing responses" refers to the techniques and methods for gathering information obtained from subjects and analyzing that data.

[0099] "Methods for generating improvement proposals based on analysis results" refers to techniques that use data analysis results to identify problems in work and the work environment, and to devise plans for improvement.

[0100] "Means for generating and notifying action plans based on improvement suggestions" refers to methods and technologies for planning specific improvement measures and informing relevant parties.

[0101] "Means of obtaining feedback in a collaborative environment with work machines" refers to methods for collecting opinions and reactions from employees in situations where employees and machines work together.

[0102] "Means for processing collected feedback" refers to techniques or processes for organizing the opinions and reactions received and using them to solve problems or propose improvements.

[0103] The system implementing this invention includes a program for efficiently collecting and analyzing employee feedback. The server first utilizes a generative AI model to design questionnaires, dynamically adjusting questions to suit specific tasks and job roles. The designed questionnaires are then distributed to users via email or a dedicated application.

[0104] The terminal notifies the user that a survey has been distributed and provides an interface for the user to review and respond to the content. The user answers the questions displayed on the terminal, and the responses are immediately transmitted to the server. The server stores the collected data in a database and performs sentiment analysis using natural language processing libraries (e.g., NLTK or spaCy). Based on the results, it identifies problems and generates suggestions for improvement.

[0105] Improvement suggestions are converted into detailed action plans by the server and notified to relevant parties. These notifications are delivered to administrators' terminals via tools such as Microsoft® PowerAutomate, allowing administrators to adjust resources and implement the plans.

[0106] For example, if a factory receives many comments stating that "the lighting in the work area is insufficient," the server will use sentiment analysis to identify the problem, generate a suggestion to increase lighting, and notify the person in charge.

[0107] An example of a prompt would be, "What emotions are identified from this feedback? Please identify specific areas that need improvement."

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The server designs the survey using a generative AI model. This process dynamically generates questions that take into account employee roles and job responsibilities. Inputs include employee profile information and specific company needs, and the output is a customized survey.

[0111] Step 2:

[0112] The server distributes the designed questionnaire to terminals via email or a dedicated application. Inputs include the customized questionnaire and employee contact information, while output is the sending of the questionnaire to the employee's terminal.

[0113] Step 3:

[0114] The terminal notifies the user that a survey has arrived and provides an interface for answering the survey. The input is the received survey, and the output is the user's responses. The user answers the questions using the terminal's interface.

[0115] Step 4:

[0116] User responses are immediately forwarded to the server, which stores them in a database. The input is the user's response data, and the output is an updated entry in the database.

[0117] Step 5:

[0118] The server uses natural language processing libraries (NLTK and spaCy) to perform sentiment analysis on the collected data. The input is response data stored in a database, and the output is the result of the sentiment analysis. This result reveals the emotional tone of the feedback.

[0119] Step 6:

[0120] The server generates improvement suggestions based on the results of sentiment analysis. The input is the results of sentiment analysis, and the output is specific improvement suggestions. Improvement measures are formulated using a generative AI model.

[0121] Step 7:

[0122] Based on the improvement suggestions, the server generates a detailed action plan and notifies the necessary stakeholders through tools such as Microsoft Power Automate. The input is the improvement suggestions, and the output is the notification to stakeholders and the sharing of the action plan.

[0123] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0124] The system according to the present invention aims to improve employee engagement by automatically collecting and analyzing feedback from employees, and generating and implementing improvement suggestions and action plans based on the results. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, thereby enabling the provision of appropriate feedback and suggestions based on a deeper understanding of emotions.

[0125] The server first uses a generative AI model to design questionnaires tailored to employees' roles and work needs. This process dynamically adjusts the questions by incorporating not only past user feedback but also input from an emotion engine. The completed questionnaires are distributed to each employee via email or internal applications.

[0126] The terminal notifies employees when a survey is distributed and provides an interface for users to answer the survey. Employees can also record their emotional state while answering the survey, and this information is also sent to the server via the terminal.

[0127] The server stores survey results and sentiment data in a database and performs data analysis using natural language processing technology. Here, the sentiment engine recognizes changes in the user's emotions in real time and provides accurate sentiment feedback for the survey.

[0128] Based on the analysis results, the server generates improvement suggestions to enhance employee engagement. The priority of each suggestion is dynamically adjusted by incorporating the analysis results from the emotion engine. In response to these suggestions, the server develops a concrete action plan and notifies the specific steps to be taken.

[0129] Administrators approve action plans notified by the server and secure or adjust the relevant resources. Suggestions may include, for example, "holding refreshment seminars to reduce stress levels" or "implementing a peer review system to facilitate smooth exchange of ideas."

[0130] Furthermore, the server has an action plan tracking function and monitors progress in real time. This system allows users to continuously understand whether the plan is on track and to fine-tune the project as needed. Through these functions, the system contributes to improving employee engagement and maintaining corporate productivity.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The server designs employee surveys using a generative AI model. Here, the server references data from an emotion engine and dynamically adjusts questions, taking into account the user's past emotional tendencies. The surveys are sent via email or a dedicated application, whichever distribution method is chosen.

[0134] Step 2:

[0135] The terminal displays notifications of received surveys to the employee user. The terminal launches an interface for the user to answer the survey and supports the input of responses. During this process, the terminal captures the user's emotions and sends that data to the server.

[0136] Step 3:

[0137] The server stores survey responses and sentiment data submitted from the terminals in a database. The server uses natural language processing techniques to perform sentiment analysis on the text data and extract the positive and negative aspects of the feedback.

[0138] Step 4:

[0139] The server generates improvement suggestions based on emotional data supplied by the emotion engine. This process prioritizes suggestions based on the emotional data and evaluates the importance of the issues that need addressing. The generated suggestions are then developed into concrete action plans.

[0140] Step 5:

[0141] The server notifies relevant parties of the generated action plan. The administrator, as the user, reviews this notification and takes necessary resource procurement and internal coordination based on the proposal. The notification may include, for example, "hold a monthly feedback meeting" or "concretize workplace improvement measures."

[0142] Step 6:

[0143] The server provides the ability to monitor the implementation of action plans and track progress in real time. If necessary, the server sends reminders to users and prompts quick action if the plan falls behind schedule.

[0144] Step 7:

[0145] The administrator, as a user, reviews progress reports from the server and makes necessary adjustments. This enables the rapid implementation of engagement improvement measures based on feedback within the company, contributing to maintaining the vitality of the entire organization.

[0146] (Example 2)

[0147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0148] To improve employee engagement and maintain productivity, it is essential to efficiently and accurately collect and analyze employee feedback. However, traditional methods have limitations in terms of efficiency and accuracy in feedback collection, and it is particularly difficult to respond to subtle changes in emotions. Effectively addressing this challenge is necessary.

[0149] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0150] In this invention, the server includes a design means using a generation model to generate information gathering questions according to roles, a means for individually providing the designed questions using information and communication technology, and a means for collecting answers to the questions through a receiving medium. This enables the collection and analysis of feedback that takes into account the diverse needs and emotional changes of employees.

[0151] A "generative model" refers to an algorithm or technology that generates new information based on a large amount of data.

[0152] "Information and communication technology" refers to all technologies related to the transmission, reception, and processing of digital data.

[0153] A "receiving medium" refers to a device or interface used to import digital data from a user into a system.

[0154] "Natural language processing technology" refers to the technology used to analyze, understand, and generate human language using computers.

[0155] An "emotion analysis engine" refers to a software component that recognizes and analyzes a user's emotional state and changes from data.

[0156] An "action plan" refers to a series of specific steps and activities set out to achieve a particular goal.

[0157] "Management information" refers to the data and reports necessary to monitor and evaluate the progress of a project or plan.

[0158] The system of this invention is built around automated feedback collection and suggestion generation to improve employee engagement. Key technological elements incorporated include generative AI models, information and communication technologies, natural language processing technologies, and sentiment analysis engines.

[0159] The server utilizes a generative AI model to generate questionnaires tailored to employees' roles and job needs. By considering past feedback data and incorporating data from an emotion analysis engine, it enables more flexible and appropriate questions. This allows employees to provide specific feedback on their work environment and job satisfaction.

[0160] The terminal provides an interface for distributing questionnaires designed by the server directly to employees using information and communication technology, and for receiving responses. Employees answer the questionnaires through this interface and record their emotional state. This data is transmitted to the server via the receiving medium.

[0161] The server analyzes collected survey responses and sentiment data using natural language processing technology. The sentiment analysis engine evaluates employee sentiment changes in real time and provides detailed feedback based on this analysis. Based on the analysis results, the server generates improvement suggestions and develops an optimal action plan. This plan is notified to administrators via information and communication technology, enabling its implementation.

[0162] As a concrete example, the generative AI model can be provided with the following prompt, allowing for the customization of questions to understand employee needs: "Create a survey to gather feedback on the work environment and job duties to improve employee job satisfaction. Also, include questions to identify stressors that employees experience."

[0163] This system functions as a crucial resource in a company's human resource strategy, contributing to improved employee satisfaction and productivity.

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The server inputs prompts into a generative AI model, which then generates survey questions based on employee roles and work needs. Specifically, the server collects past feedback data and data from a sentiment analysis engine and passes it to the generative AI model. This results in a customized set of questions being output.

[0167] Step 2:

[0168] The server distributes the generated questionnaire to the terminals using information and communication technology. The input consists of the questionnaire questions generated in step 1, and these are sent to each employee's terminal using email addresses or the company's messaging system. The output is a questionnaire link accessible to the employee.

[0169] Step 3:

[0170] The terminal notifies employees of the distributed survey and displays the response interface. Specifically, the terminal automatically displays the received survey link in a notification window, and when the user clicks it, the web interface opens. The input is the survey link sent in step 2, and the output is the user's response screen.

[0171] Step 4:

[0172] Users answer questionnaires via their devices and record their emotional state. Specific actions include entering information into text fields and selecting from emotional options. Input is the questionnaire questions, and output is employee response data and emotional data.

[0173] Step 5:

[0174] The device sends user-entered responses and sentiment data to the server. Specifically, when the "Send" button is pressed, the device uploads the data to the server in real time. The input consists of the user's response data and sentiment data, and the output is the raw data stored on the server.

[0175] Step 6:

[0176] The server analyzes the received survey responses and sentiment data using natural language processing techniques. The input is the raw data sent in step 5, which is used to execute the analysis algorithm. The output is detailed feedback information, including sentiment data.

[0177] Step 7:

[0178] The server generates improvement suggestions to enhance employee engagement based on the analysis results. Specific actions include prioritizing based on data from the sentiment analysis engine. The input is the analysis results from step 6, and the output is improvement suggestions and an action plan.

[0179] Step 8:

[0180] The server notifies the administrator of the generated improvement suggestions and action plan, and then moves to the implementation phase. The input is the plan content generated in step 7, and the output is the detailed action steps delivered to the administrator. Specific actions include posting information on the dashboard and sending alerts.

[0181] (Application Example 2)

[0182] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0183] In modern society, improving employee engagement is crucial for increasing organizational productivity and efficiency. However, traditional surveys and evaluation methods fail to adequately capture employees' emotions and potential problems. Furthermore, while there is a need for improvement suggestions and communication methods that take emotional states into account, a reliable system for achieving this is lacking.

[0184] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0185] In this invention, the server includes means for designing and distributing questionnaires, means for collecting and analyzing responses to the questionnaires, means for generating improvement suggestions based on the analysis results, means for monitoring the user's emotional state using emotion analysis technology, means for integrating and analyzing emotional data and response data, and means for suggesting appropriate communication methods using generative AI technology. This enables appropriate feedback and improvement suggestions based on the emotional state of employees, thereby improving engagement.

[0186] "Means for designing and distributing questionnaires" refers to a function that dynamically constructs questions tailored to the user's role and business needs, and efficiently distributes them via email or application.

[0187] "Means for collecting and analyzing survey responses" refers to a mechanism for collecting data provided by users and analyzing that data.

[0188] "Methods for generating improvement suggestions" refers to a process that automatically creates useful suggestions for users based on insights obtained from analyzed data.

[0189] "Methods for monitoring a user's emotional state using emotion analysis technology" refers to technologies that capture emotional trends by acquiring user emotional data and tracking its changes in real time.

[0190] "Methods for integrating and analyzing emotional data and response data" refers to a process that combines changes in emotions with survey responses to comprehensively evaluate the user's state.

[0191] "A means of suggesting appropriate communication methods using generative AI technology" refers to a function that utilizes AI models to suggest the optimal communication style and content based on the user's emotional state and responses.

[0192] To implement this invention, a system configuration is required in which a server, a terminal, and a user each play their respective roles.

[0193] The server designs surveys based on users' roles and business needs, and dynamically generates appropriate questions using a generative AI model. Next, it distributes the surveys via email and internal applications. The server aggregates survey response data and sentiment data transmitted from devices, and monitors users' emotional states using sentiment analysis technology. This allows for the integration of response and sentiment data, enabling advanced data analysis and the generation of improvement suggestions.

[0194] The device notifies the user of surveys and provides a response interface. Users can record their emotional state through the device, and this information is sent to a server for analysis.

[0195] The user (administrator) reviews the improvement suggestions and action plans provided by the server and arranges and adjusts the necessary resources. The server uses generative AI technology to suggest the optimal communication method based on the user's emotional state. This allows the user to practice stress management and improve communication.

[0196] For example, a manager who notices a decline in employee motivation can use this system to adopt effective engagement strategies based on the employee's emotional state and feedback data. By using prompts such as, "Based on employee A's feedback, please suggest improvements tailored to his stress level," the generative AI model provides practical solutions.

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The server uses a generative AI model to design surveys related to the user's role and tasks. It receives past feedback and information from the sentiment engine as input and generates dynamically adjusted survey questions as output. This process appropriately customizes the content of the questions to accurately reflect the user's needs.

[0200] Step 2:

[0201] The server distributes the designed questionnaire to users' terminals via email or internal applications. The generated questionnaire arrives on the terminal, and the user is notified. The input here is the content of the generated questionnaire, and the output is the sending of the questionnaire to each user.

[0202] Step 3:

[0203] Users answer questionnaires via a device. The device receives the user's responses as input and also sends additional data about the user's emotional state to the server. The specific functions of the device are providing an input interface and transmitting data.

[0204] Step 4:

[0205] The server stores received survey responses and sentiment data in a database and analyzes them using natural language processing techniques. User response data and sentiment data are used as input, and the output includes analysis results and identification of potential problems. Specifically, the system performs text analysis and sentiment evaluation.

[0206] Step 5:

[0207] The server generates improvement suggestions based on the analysis results. These suggestions are optimized using a real-time AI model that takes into account fluctuating emotional states based on emotion analysis technology. The input here is the analysis results, and the output is improvement suggestions customized for each individual user.

[0208] Step 6:

[0209] The server develops a concrete action plan based on the generated improvement suggestions and notifies the user. The input is improvement suggestions, and the output is an actionable plan notified to the user. The server's specific actions are designing and notifying the action plan.

[0210] Step 7:

[0211] The user reviews the provided action plan and arranges and coordinates the necessary resources. This process requires the user to understand the proposal and take action based on it. The output is the specific actions taken based on the plan.

[0212] Step 8:

[0213] The server tracks the implementation status of action plans and monitors progress in real time. Inputs are action feedback from each user, and outputs are real-time reports of overall progress. The server's specific functions are progress management and status updates.

[0214] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0215] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search)<url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0220] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0221] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0222] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0223] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0224] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0225] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0227] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0228] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0229] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0230] The employee engagement assistant according to the present invention is a system for improving employee satisfaction within a company and streamlining the direct implementation of feedback. This system primarily uses a server, terminals, and users to perform various processes.

[0231] The server first uses a generative AI model to design a survey for the target employees. The designed survey is dynamically adjusted based on specific needs and objectives, ensuring it includes appropriate questions tailored to each employee's role and responsibilities. This survey is then distributed to employees via email or a dedicated application.

[0232] The terminal notifies employees that a survey has been distributed and provides an interface for them to review and respond to its contents. Employees, as users, answer the questions displayed on the terminal, and their responses are immediately transmitted to the server. The server stores the collected data in a database and then performs sentiment analysis to reveal the emotional tone of the feedback.

[0233] Based on the analysis results, the server generates specific improvement suggestions to enhance employee engagement. These suggestions identify problems across the entire company or within specific departments and develop solutions. Based on the proposed improvements, it automatically generates more specific action plans and notifies the relevant personnel as needed.

[0234] The administrator, as a user, receives notifications from the server, reviews the proposed action plan, and makes necessary adjustments and allocates resources as needed. In this process, feedback directly related to practical work is easily incorporated, such as "generalizing feedback from monthly meetings" or "making further adjustments to improve workplace comfort."

[0235] The system of this invention helps to ensure that plans are progressing appropriately by regularly tracking the progress of action plans and providing administrators with notifications as needed. In this way, a series of steps for improving engagement are efficiently managed, leading to increased corporate productivity and sustained improvements in employee satisfaction.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The server designs surveys according to the company's needs. It utilizes a generative AI model to set appropriate questions based on employee roles and job responsibilities. After design, the surveys are distributed to employees via email or a dedicated application.

[0239] Step 2:

[0240] The terminal notifies employees of the distribution of the survey and displays an interface for answering. Employees, as users, answer the questions on the terminal and send their responses to the server.

[0241] Step 3:

[0242] The server stores the received survey responses in a database. Next, it performs sentiment analysis of the responses using natural language processing techniques to identify positive and negative feedback.

[0243] Step 4:

[0244] Based on the results of sentiment analysis, the server automatically generates specific improvement suggestions to enhance employee engagement. These suggestions are designed to address issues at the overall level or in specific departments.

[0245] Step 5:

[0246] Based on the proposed improvements, the server will create a concrete action plan and notify the relevant departments. The notification will include the necessary resource allocation and implementation plan.

[0247] Step 6:

[0248] The administrator, as a user, reviews the notified action plan and, if necessary, arranges resources and prepares for specific implementation.

[0249] Step 7:

[0250] The server tracks the implementation status of the action plan. It monitors whether progress is on track and notifies responsible parties of reminders as needed.

[0251] (Example 1)

[0252] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0253] Effectively improving employee engagement within a company is crucial for increasing organizational productivity. However, traditional approaches have limitations in accurately collecting and analyzing employee feedback, resulting in challenges in the rapid development and implementation of improvement measures. Furthermore, the process of analyzing the emotional aspects of feedback and translating this into concrete action plans is not sufficiently automated.

[0254] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0255] In this invention, the server includes means for designing a questionnaire based on prompt text using a generative AI model, means for distributing the designed questionnaire via electronic notification, and means for collecting questionnaire responses and storing them in a database. This enables immediate analysis of employee feedback and the automatic generation of specific improvement suggestions and action plans based on emotional tendencies.

[0256] A "generative AI model" is an algorithm that learns from data and generates information based on natural language prompts.

[0257] A "prompt statement" is an instruction given to a generative AI model for generating information.

[0258] A "survey" is a set of questions designed to collect specific information.

[0259] "Electronic notification" refers to a method of transmitting information to a recipient in a digital format.

[0260] A "database" is a system that systematically stores information and saves it in a searchable format.

[0261] "Sentiment analysis" is the process of identifying emotional tendencies and feelings within text data.

[0262] An "improvement suggestion" is specific advice or a strategy for solving a particular problem.

[0263] An "action plan" is a specific plan of actions to be taken in order to achieve a particular goal.

[0264] This system aims to improve employee engagement and consists mainly of three elements: servers, terminals, and users.

[0265] Server embodiment:

[0266] The server designs the survey using a generative AI model, generating individual questions by inputting prompts during this process. The generative AI model used is a large-scale natural language processing model. The survey is dynamically adjusted to include questions specific to job roles and responsibilities within the company. For example, a prompt such as "Create questions about stress management for the sales department" will generate questions tailored to a specific job role. This designed survey is then delivered to terminals via electronic means. Simultaneously, the server manages the response data and performs sentiment analysis on the collected responses. This utilizes sentiment analysis software to extract emotional tendencies from the text data.

[0267] Terminal embodiment:

[0268] The terminal receives questionnaires distributed from the server and displays them to employees as a user interface. Users answer the questionnaires through this terminal and input data processed by a generative AI model. The responses are sent to the server in real time and stored in the database.

[0269] User embodiment:

[0270] Employees, as users, can easily access distributed questionnaires and freely provide feedback and opinions on their daily work. Administrators, as users, receive proposed improvement measures and action plans via notifications from the server and begin implementing the measures. For example, if there is a suggestion to "hold lunch meetings to strengthen communication between teams," administrators can use this as a basis to create a concrete action plan.

[0271] In this way, the collaboration between the server, terminal, and user enables an efficient feedback loop for improving engagement.

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The server designs the survey using a generative AI model. A prompt is provided as input, and the generative AI model generates questions appropriate to each employee's role and responsibilities. The resulting survey is provided as a set of questions tailored to individual needs. Specifically, the prompt "Create questions about improving teamwork for the marketing department" is used as input, and the result is output as a set of questions.

[0275] Step 2:

[0276] The server distributes the designed questionnaires to employee terminals via email or a dedicated application. The inputs used are the questionnaire to be distributed and the recipient employee's email address or application identifier. The output is achieved by transmitting these to the terminals over the internet.

[0277] Step 3:

[0278] The terminal notifies employees of the distributed questionnaire by notification and provides an interface for displaying its content. The input is the questionnaire data received from the server, which is output in the form of a notification and also displayed on the screen. As a specific operation, a pop-up notification or an in-application message is displayed on the terminal screen.

[0279] Step 4:

[0280] The employee, who is the user, answers the questionnaire through the terminal interface. The input is the response data entered by the user on the interface. As the output, these response data are sent from the terminal to the server and stored in the database. Specifically, data is collected by selecting options or entering text.

[0281] Step 5:

[0282] The server performs sentiment analysis using the received questionnaire responses. The input data is the responses sent by the user, and the output is the analysis result. The sentiment analysis software identifies the sentiment trends in the text data and classifies them into categories such as positive, negative, and neutral.

[0283] Step 6:

[0284] The server generates improvement suggestions based on the sentiment analysis results. The analysis results are used as the input, and the generated AI model is reused to output specific suggestions. As a result, optimal improvement measures based on the employees' feedback are proposed. For example, "Improve team morale by enhancing communication" etc. are output.

[0285] Step 7:

[0286] The server automatically creates an action plan based on the generated improvement suggestions and notifies the user who is the administrator. The input is the generated improvement suggestions, and as a result of the notification, the next steps for executing the plan are communicated to the administrator. As a specific operation, the administrator is notified by email or an in-company communication tool.

[0287] (Application Example 1)

[0288] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0289] In a modern work environment, as the collaborative work between employees and work machines progresses, improving employee satisfaction and obtaining effective feedback are important issues. In the conventional method, feedback from employees was not efficiently collected, and it was difficult to formulate quick improvement suggestions and action plans. An object of the present invention is to provide means for continuously and efficiently obtaining employee feedback in a collaborative environment with work machines and quickly implementing improvement measures based on the feedback.

[0290] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0291] In this invention, the server includes means for designing and distributing a questionnaire, means for collecting and analyzing answers to the questionnaire, means for generating improvement suggestions based on the analysis results, means for generating and notifying an action plan based on the improvement suggestions, means for obtaining feedback in a collaborative environment with work machines, and means for processing the collected feedback. Thereby, it becomes possible to efficiently obtain feedback from employees and quickly and accurately improve the work environment.

[0292] A "questionnaire" is a series of questions designed to collect information and is mainly used to evaluate employees' opinions and feelings.

[0293] "Means of design and distribution" refers to the process or technology for determining the content of the questionnaire and supplying it to the target audience.

[0294] "Means for collecting and analyzing responses" refers to the techniques and methods for gathering information obtained from subjects and analyzing that data.

[0295] "Methods for generating improvement proposals based on analysis results" refers to techniques that use data analysis results to identify problems in work and the work environment, and to devise plans for improvement.

[0296] "Means for generating and notifying action plans based on improvement suggestions" refers to methods and technologies for planning specific improvement measures and informing relevant parties.

[0297] "Means of obtaining feedback in a collaborative environment with work machines" refers to methods for collecting opinions and reactions from employees in situations where employees and machines work together.

[0298] "Means for processing collected feedback" refers to techniques or processes for organizing the opinions and reactions received and using them to solve problems or propose improvements.

[0299] The system implementing this invention includes a program for efficiently collecting and analyzing employee feedback. The server first utilizes a generative AI model to design questionnaires, dynamically adjusting questions to suit specific tasks and job roles. The designed questionnaires are then distributed to users via email or a dedicated application.

[0300] The terminal notifies that the questionnaire has been distributed and provides an interface for the user to check the content and answer. The user answers the questions displayed on the terminal, and the answers are immediately transferred to the server. The server stores the collected data in a database and performs sentiment analysis using a natural language processing library (e.g., NLTK or spaCy). Based on the results, problems are identified and improvement suggestions are generated.

[0301] The improvement suggestions are converted by the server into a detailed action plan and notified to the relevant parties. This notification is distributed to the administrator's terminal through tools such as Microsoft PowerAutomate, and the administrator can adjust resources and implement the plan.

[0302] As a specific example, when there is a lot of feedback such as "The lighting in the work area is insufficient" in the factory work environment, the server associates this problem through sentiment analysis, generates a proposal for increasing lighting, and notifies the person in charge.

[0303] Examples of prompt sentences include "What is the sentiment identified from this feedback? Please specify the specific areas that need to be improved."

[0304] The flow of specific processing in Application Example 1 will be described using Figure 12.

[0305] Step 1:

[0306] The server designs the questionnaire using a generative AI model. In this process, questions are dynamically generated considering the employee's job position and work content. The inputs are the employee's profile information and the specific needs of the company, and the output is a customized questionnaire.

[0307] Step 2:

[0308] The server distributes the designed questionnaire to terminals via email or a dedicated application. Inputs include the customized questionnaire and employee contact information, while output is the sending of the questionnaire to the employee's terminal.

[0309] Step 3:

[0310] The terminal notifies the user that a survey has arrived and provides an interface for answering the survey. The input is the received survey, and the output is the user's responses. The user answers the questions using the terminal's interface.

[0311] Step 4:

[0312] User responses are immediately forwarded to the server, which stores them in a database. The input is the user's response data, and the output is an updated entry in the database.

[0313] Step 5:

[0314] The server uses natural language processing libraries (NLTK and spaCy) to perform sentiment analysis on the collected data. The input is response data stored in a database, and the output is the result of the sentiment analysis. This result reveals the emotional tone of the feedback.

[0315] Step 6:

[0316] The server generates improvement suggestions based on the results of sentiment analysis. The input is the results of sentiment analysis, and the output is specific improvement suggestions. Improvement measures are formulated using a generative AI model.

[0317] Step 7:

[0318] Based on the improvement suggestions, the server generates a detailed action plan and notifies the necessary stakeholders through tools such as Microsoft Power Automate. The input is the improvement suggestions, and the output is the notification to stakeholders and the sharing of the action plan.

[0319] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0320] The system according to the present invention aims to improve employee engagement by automatically collecting and analyzing feedback from employees, and generating and implementing improvement suggestions and action plans based on the results. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, thereby enabling the provision of appropriate feedback and suggestions based on a deeper understanding of emotions.

[0321] The server first uses a generative AI model to design questionnaires tailored to employees' roles and work needs. This process dynamically adjusts the questions by incorporating not only past user feedback but also input from an emotion engine. The completed questionnaires are distributed to each employee via email or internal applications.

[0322] The terminal notifies employees when a survey is distributed and provides an interface for users to answer the survey. Employees can also record their emotional state while answering the survey, and this information is also sent to the server via the terminal.

[0323] The server stores survey results and sentiment data in a database and performs data analysis using natural language processing technology. Here, the sentiment engine recognizes changes in the user's emotions in real time and provides accurate sentiment feedback for the survey.

[0324] Based on the analysis results, the server generates improvement suggestions to enhance employee engagement. The priority of each suggestion is dynamically adjusted by incorporating the analysis results from the emotion engine. In response to these suggestions, the server develops a concrete action plan and notifies the specific steps to be taken.

[0325] Administrators approve action plans notified by the server and secure or adjust the relevant resources. Suggestions may include, for example, "holding refreshment seminars to reduce stress levels" or "implementing a peer review system to facilitate smooth exchange of ideas."

[0326] Furthermore, the server has an action plan tracking function and monitors progress in real time. This system allows users to continuously understand whether the plan is on track and to fine-tune the project as needed. Through these functions, the system contributes to improving employee engagement and maintaining corporate productivity.

[0327] The following describes the processing flow.

[0328] Step 1:

[0329] The server designs employee surveys using a generative AI model. Here, the server references data from an emotion engine and dynamically adjusts questions, taking into account the user's past emotional tendencies. The surveys are sent via email or a dedicated application, whichever distribution method is chosen.

[0330] Step 2:

[0331] The terminal displays notifications of received surveys to the employee user. The terminal launches an interface for the user to answer the survey and supports the input of responses. During this process, the terminal captures the user's emotions and sends that data to the server.

[0332] Step 3:

[0333] The server stores survey responses and sentiment data submitted from the terminals in a database. The server uses natural language processing techniques to perform sentiment analysis on the text data and extract the positive and negative aspects of the feedback.

[0334] Step 4:

[0335] The server generates improvement suggestions based on emotional data supplied by the emotion engine. This process prioritizes suggestions based on the emotional data and evaluates the importance of the issues that need addressing. The generated suggestions are then developed into concrete action plans.

[0336] Step 5:

[0337] The server notifies relevant parties of the generated action plan. The administrator, as the user, reviews this notification and takes necessary resource procurement and internal coordination based on the proposal. The notification may include, for example, "hold a monthly feedback meeting" or "concretize workplace improvement measures."

[0338] Step 6:

[0339] The server provides the ability to monitor the implementation of action plans and track progress in real time. If necessary, the server sends reminders to users and prompts quick action if the plan falls behind schedule.

[0340] Step 7:

[0341] The administrator, as a user, reviews progress reports from the server and makes necessary adjustments. This enables the rapid implementation of engagement improvement measures based on feedback within the company, contributing to maintaining the vitality of the entire organization.

[0342] (Example 2)

[0343] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0344] To improve employee engagement and maintain productivity, it is essential to efficiently and accurately collect and analyze employee feedback. However, traditional methods have limitations in terms of efficiency and accuracy in feedback collection, and it is particularly difficult to respond to subtle changes in emotions. Effectively addressing this challenge is necessary.

[0345] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0346] In this invention, the server includes a design means using a generation model to generate information gathering questions according to roles, a means for individually providing the designed questions using information and communication technology, and a means for collecting answers to the questions through a receiving medium. This enables the collection and analysis of feedback that takes into account the diverse needs and emotional changes of employees.

[0347] A "generative model" refers to an algorithm or technology that generates new information based on a large amount of data.

[0348] "Information and communication technology" refers to all technologies related to the transmission, reception, and processing of digital data.

[0349] A "receiving medium" refers to a device or interface used to import digital data from a user into a system.

[0350] "Natural language processing technology" refers to the technology used to analyze, understand, and generate human language using computers.

[0351] An "emotion analysis engine" refers to a software component that recognizes and analyzes a user's emotional state and changes from data.

[0352] An "action plan" refers to a series of specific steps and activities set out to achieve a particular goal.

[0353] "Management information" refers to the data and reports necessary to monitor and evaluate the progress of a project or plan.

[0354] The system of this invention is built around automated feedback collection and suggestion generation to improve employee engagement. Key technological elements incorporated include generative AI models, information and communication technologies, natural language processing technologies, and sentiment analysis engines.

[0355] The server utilizes a generative AI model to generate questionnaires tailored to employees' roles and job needs. By considering past feedback data and incorporating data from an emotion analysis engine, it enables more flexible and appropriate questions. This allows employees to provide specific feedback on their work environment and job satisfaction.

[0356] The terminal provides an interface for distributing questionnaires designed by the server directly to employees using information and communication technology, and for receiving responses. Employees answer the questionnaires through this interface and record their emotional state. This data is transmitted to the server via the receiving medium.

[0357] The server analyzes collected survey responses and sentiment data using natural language processing technology. The sentiment analysis engine evaluates employee sentiment changes in real time and provides detailed feedback based on this analysis. Based on the analysis results, the server generates improvement suggestions and develops an optimal action plan. This plan is notified to administrators via information and communication technology, enabling its implementation.

[0358] As a concrete example, the generative AI model can be provided with the following prompt, allowing for the customization of questions to understand employee needs: "Create a survey to gather feedback on the work environment and job duties to improve employee job satisfaction. Also, include questions to identify stressors that employees experience."

[0359] This system functions as a crucial resource in a company's human resource strategy, contributing to improved employee satisfaction and productivity.

[0360] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0361] Step 1:

[0362] The server inputs prompts into a generative AI model, which then generates survey questions based on employee roles and work needs. Specifically, the server collects past feedback data and data from a sentiment analysis engine and passes it to the generative AI model. This results in a customized set of questions being output.

[0363] Step 2:

[0364] The server distributes the generated questionnaire to the terminals using information and communication technology. The input consists of the questionnaire questions generated in step 1, and these are sent to each employee's terminal using email addresses or the company's messaging system. The output is a questionnaire link accessible to the employee.

[0365] Step 3:

[0366] The terminal notifies employees of the distributed survey and displays the response interface. Specifically, the terminal automatically displays the received survey link in a notification window, and when the user clicks it, the web interface opens. The input is the survey link sent in step 2, and the output is the user's response screen.

[0367] Step 4:

[0368] Users answer questionnaires via their devices and record their emotional state. Specific actions include entering information into text fields and selecting from emotional options. Input is the questionnaire questions, and output is employee response data and emotional data.

[0369] Step 5:

[0370] The device sends user-entered responses and sentiment data to the server. Specifically, when the "Send" button is pressed, the device uploads the data to the server in real time. The input consists of the user's response data and sentiment data, and the output is the raw data stored on the server.

[0371] Step 6:

[0372] The server analyzes the received survey responses and sentiment data using natural language processing techniques. The input is the raw data sent in step 5, which is used to execute the analysis algorithm. The output is detailed feedback information, including sentiment data.

[0373] Step 7:

[0374] The server generates improvement suggestions to enhance employee engagement based on the analysis results. Specific actions include prioritizing based on data from the sentiment analysis engine. The input is the analysis results from step 6, and the output is improvement suggestions and an action plan.

[0375] Step 8:

[0376] The server notifies the administrator of the generated improvement suggestions and action plan, and then moves to the implementation phase. The input is the plan content generated in step 7, and the output is the detailed action steps delivered to the administrator. Specific actions include posting information on the dashboard and sending alerts.

[0377] (Application Example 2)

[0378] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0379] In modern society, improving employee engagement is crucial for increasing organizational productivity and efficiency. However, traditional surveys and evaluation methods fail to adequately capture employees' emotions and potential problems. Furthermore, while there is a need for improvement suggestions and communication methods that take emotional states into account, a reliable system for achieving this is lacking.

[0380] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0381] In this invention, the server includes means for designing and distributing questionnaires, means for collecting and analyzing responses to the questionnaires, means for generating improvement suggestions based on the analysis results, means for monitoring the user's emotional state using emotion analysis technology, means for integrating and analyzing emotional data and response data, and means for suggesting appropriate communication methods using generative AI technology. This enables appropriate feedback and improvement suggestions based on the emotional state of employees, thereby improving engagement.

[0382] "Means for designing and distributing questionnaires" refers to a function that dynamically constructs questions tailored to the user's role and business needs, and efficiently distributes them via email or application.

[0383] "Means for collecting and analyzing survey responses" refers to a mechanism for collecting data provided by users and analyzing that data.

[0384] "Methods for generating improvement suggestions" refers to a process that automatically creates useful suggestions for users based on insights obtained from analyzed data.

[0385] "Methods for monitoring a user's emotional state using emotion analysis technology" refers to technologies that capture emotional trends by acquiring user emotional data and tracking its changes in real time.

[0386] "Methods for integrating and analyzing emotional data and response data" refers to a process that combines changes in emotions with survey responses to comprehensively evaluate the user's state.

[0387] "A means of suggesting appropriate communication methods using generative AI technology" refers to a function that utilizes AI models to suggest the optimal communication style and content based on the user's emotional state and responses.

[0388] To implement this invention, a system configuration is required in which a server, a terminal, and a user each play their respective roles.

[0389] The server designs surveys based on users' roles and business needs, and dynamically generates appropriate questions using a generative AI model. Next, it distributes the surveys via email and internal applications. The server aggregates survey response data and sentiment data transmitted from devices, and monitors users' emotional states using sentiment analysis technology. This allows for the integration of response and sentiment data, enabling advanced data analysis and the generation of improvement suggestions.

[0390] The device notifies the user of surveys and provides a response interface. Users can record their emotional state through the device, and this information is sent to a server for analysis.

[0391] The user (administrator) reviews the improvement suggestions and action plans provided by the server and arranges and adjusts the necessary resources. The server uses generative AI technology to suggest the optimal communication method based on the user's emotional state. This allows the user to practice stress management and improve communication.

[0392] For example, a manager who notices a decline in employee motivation can use this system to adopt effective engagement strategies based on the employee's emotional state and feedback data. By using prompts such as, "Based on employee A's feedback, please suggest improvements tailored to his stress level," the generative AI model provides practical solutions.

[0393] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0394] Step 1:

[0395] The server uses a generative AI model to design surveys related to the user's role and tasks. It receives past feedback and information from the sentiment engine as input and generates dynamically adjusted survey questions as output. This process appropriately customizes the content of the questions to accurately reflect the user's needs.

[0396] Step 2:

[0397] The server distributes the designed questionnaire to users' terminals via email or internal applications. The generated questionnaire arrives on the terminal, and the user is notified. The input here is the content of the generated questionnaire, and the output is the sending of the questionnaire to each user.

[0398] Step 3:

[0399] Users answer questionnaires via a device. The device receives the user's responses as input and also sends additional data about the user's emotional state to the server. The specific functions of the device are providing an input interface and transmitting data.

[0400] Step 4:

[0401] The server stores received survey responses and sentiment data in a database and analyzes them using natural language processing techniques. User response data and sentiment data are used as input, and the output includes analysis results and identification of potential problems. Specifically, the system performs text analysis and sentiment evaluation.

[0402] Step 5:

[0403] The server generates improvement suggestions based on the analysis results. These suggestions are optimized using a real-time AI model that takes into account fluctuating emotional states based on emotion analysis technology. The input here is the analysis results, and the output is improvement suggestions customized for each individual user.

[0404] Step 6:

[0405] The server develops a concrete action plan based on the generated improvement suggestions and notifies the user. The input is improvement suggestions, and the output is an actionable plan notified to the user. The server's specific actions are designing and notifying the action plan.

[0406] Step 7:

[0407] The user reviews the provided action plan and arranges and coordinates the necessary resources. This process requires the user to understand the proposal and take action based on it. The output is the specific actions taken based on the plan.

[0408] Step 8:

[0409] The server tracks the implementation status of action plans and monitors progress in real time. Inputs are action feedback from each user, and outputs are real-time reports of overall progress. The server's specific functions are progress management and status updates.

[0410] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0411] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0412] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0413] [Third Embodiment]

[0414] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0415] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0416] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0417] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0418] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0419] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0420] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0421] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0422] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0423] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0424] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0425] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0426] The employee engagement assistant according to the present invention is a system for improving employee satisfaction within a company and streamlining the direct implementation of feedback. This system primarily uses a server, terminals, and users to perform various processes.

[0427] The server first uses a generative AI model to design a survey for the target employees. The designed survey is dynamically adjusted based on specific needs and objectives, ensuring it includes appropriate questions tailored to each employee's role and responsibilities. This survey is then distributed to employees via email or a dedicated application.

[0428] The terminal notifies employees that a survey has been distributed and provides an interface for them to review and respond to its contents. Employees, as users, answer the questions displayed on the terminal, and their responses are immediately transmitted to the server. The server stores the collected data in a database and then performs sentiment analysis to reveal the emotional tone of the feedback.

[0429] Based on the analysis results, the server generates specific improvement suggestions to enhance employee engagement. These suggestions identify problems across the entire company or within specific departments and develop solutions. Based on the proposed improvements, it automatically generates more specific action plans and notifies the relevant personnel as needed.

[0430] The administrator, as a user, receives notifications from the server, reviews the proposed action plan, and makes necessary adjustments and allocates resources as needed. In this process, feedback directly related to practical work is easily incorporated, such as "generalizing feedback from monthly meetings" or "making further adjustments to improve workplace comfort."

[0431] The system of this invention helps to ensure that plans are progressing appropriately by regularly tracking the progress of action plans and providing administrators with notifications as needed. In this way, a series of steps for improving engagement are efficiently managed, leading to increased corporate productivity and sustained improvements in employee satisfaction.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] The server designs surveys according to the company's needs. It utilizes a generative AI model to set appropriate questions based on employee roles and job responsibilities. After design, the surveys are distributed to employees via email or a dedicated application.

[0435] Step 2:

[0436] The terminal notifies employees of the distribution of the survey and displays an interface for answering. Employees, as users, answer the questions on the terminal and send their responses to the server.

[0437] Step 3:

[0438] The server stores the received survey responses in a database. Next, it performs sentiment analysis of the responses using natural language processing techniques to identify positive and negative feedback.

[0439] Step 4:

[0440] Based on the results of sentiment analysis, the server automatically generates specific improvement suggestions to enhance employee engagement. These suggestions are designed to address issues at the overall level or in specific departments.

[0441] Step 5:

[0442] Based on the proposed improvements, the server will create a concrete action plan and notify the relevant departments. The notification will include the necessary resource allocation and implementation plan.

[0443] Step 6:

[0444] The administrator, as a user, reviews the notified action plan and, if necessary, arranges resources and prepares for specific implementation.

[0445] Step 7:

[0446] The server tracks the implementation status of the action plan. It monitors whether progress is on track and notifies responsible parties of reminders as needed.

[0447] (Example 1)

[0448] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0449] Effectively improving employee engagement within a company is crucial for increasing organizational productivity. However, traditional approaches have limitations in accurately collecting and analyzing employee feedback, resulting in challenges in the rapid development and implementation of improvement measures. Furthermore, the process of analyzing the emotional aspects of feedback and translating this into concrete action plans is not sufficiently automated.

[0450] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0451] In this invention, the server includes means for designing a questionnaire based on prompt text using a generative AI model, means for distributing the designed questionnaire via electronic notification, and means for collecting questionnaire responses and storing them in a database. This enables immediate analysis of employee feedback and the automatic generation of specific improvement suggestions and action plans based on emotional tendencies.

[0452] A "generative AI model" is an algorithm that learns from data and generates information based on natural language prompts.

[0453] A "prompt statement" is an instruction given to a generative AI model for generating information.

[0454] A "survey" is a set of questions designed to collect specific information.

[0455] "Electronic notification" refers to a method of transmitting information to a recipient in a digital format.

[0456] A "database" is a system that systematically stores information and saves it in a searchable format.

[0457] "Sentiment analysis" is the process of identifying emotional tendencies and feelings within text data.

[0458] An "improvement suggestion" is specific advice or a strategy for solving a particular problem.

[0459] An "action plan" is a specific plan of actions to be taken in order to achieve a particular goal.

[0460] This system aims to improve employee engagement and consists mainly of three elements: servers, terminals, and users.

[0461] Server embodiment:

[0462] The server designs the survey using a generative AI model, generating individual questions by inputting prompts during this process. The generative AI model used is a large-scale natural language processing model. The survey is dynamically adjusted to include questions specific to job roles and responsibilities within the company. For example, a prompt such as "Create questions about stress management for the sales department" will generate questions tailored to a specific job role. This designed survey is then delivered to terminals via electronic means. Simultaneously, the server manages the response data and performs sentiment analysis on the collected responses. This utilizes sentiment analysis software to extract emotional tendencies from the text data.

[0463] Terminal embodiment:

[0464] The terminal receives questionnaires distributed from the server and displays them to employees as a user interface. Users answer the questionnaires through this terminal and input data processed by a generative AI model. The responses are sent to the server in real time and stored in the database.

[0465] User embodiment:

[0466] Employees, as users, can easily access distributed questionnaires and freely provide feedback and opinions on their daily work. Administrators, as users, receive proposed improvement measures and action plans via notifications from the server and begin implementing the measures. For example, if there is a suggestion to "hold lunch meetings to strengthen communication between teams," administrators can use this as a basis to create a concrete action plan.

[0467] In this way, the collaboration between the server, terminal, and user enables an efficient feedback loop for improving engagement.

[0468] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0469] Step 1:

[0470] The server designs the survey using a generative AI model. A prompt is provided as input, and the generative AI model generates questions appropriate to each employee's role and responsibilities. The resulting survey is provided as a set of questions tailored to individual needs. Specifically, the prompt "Create questions about improving teamwork for the marketing department" is used as input, and the result is output as a set of questions.

[0471] Step 2:

[0472] The server distributes the designed questionnaires to employee terminals via email or a dedicated application. The inputs used are the questionnaire to be distributed and the recipient employee's email address or application identifier. The output is achieved by transmitting these to the terminals over the internet.

[0473] Step 3:

[0474] The terminal notifies employees of distributed surveys and provides an interface to display their contents. The input is survey data received from the server, which is output in the form of a notification and displayed on the screen. Specific actions include the display of pop-up notifications and in-application messages on the terminal screen.

[0475] Step 4:

[0476] Employees, as users, answer surveys through the terminal's interface. The input is the response data entered by the user on the interface. As output, this response data is sent from the terminal to the server and stored in a database. Specifically, data is collected through selection of options and text input.

[0477] Step 5:

[0478] The server performs sentiment analysis using the received survey responses. The input data is the responses submitted by the user, and the output is the analysis results. The sentiment analysis software identifies emotional tendencies within the text data and classifies them into categories such as positive, negative, and neutral.

[0479] Step 6:

[0480] The server generates improvement suggestions based on the sentiment analysis results. The analysis results are used as input, and the generating AI model is used again to output specific suggestions. As a result, optimal improvement measures based on employee feedback are proposed. For example, "improving team morale through improved communication" might be output.

[0481] Step 7:

[0482] The server automatically creates an action plan based on the generated improvement suggestions and notifies the administrator user. The input is the generated improvement suggestions, and the notification informs the administrator of the next steps to implement the plan. Specifically, the administrator is notified via email or internal company communication tools.

[0483] (Application Example 1)

[0484] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0485] In today's work environment, where collaboration between employees and machinery is increasing, improving employee satisfaction and obtaining effective feedback are crucial challenges. Conventional methods have failed to efficiently collect employee feedback, making it difficult to quickly propose improvements and formulate action plans. This invention aims to provide a means for continuously and efficiently obtaining employee feedback in a collaborative environment with machinery, and for quickly implementing improvement measures based on that feedback.

[0486] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0487] In this invention, the server includes means for designing and distributing questionnaires, means for collecting and analyzing responses to the questionnaires, means for generating improvement suggestions based on the analysis results, means for generating and notifying action plans based on the improvement suggestions, means for obtaining feedback in a collaborative environment with work machines, and means for processing the collected feedback. This makes it possible to efficiently obtain feedback from employees and to quickly and accurately improve the work environment.

[0488] A "survey" is a set of questions designed to collect information, primarily used to assess employees' opinions and feelings.

[0489] "Means of design and distribution" refers to the process or technology for determining the content of the questionnaire and supplying it to the target audience.

[0490] "Means for collecting and analyzing responses" refers to the techniques and methods for gathering information obtained from subjects and analyzing that data.

[0491] "Methods for generating improvement proposals based on analysis results" refers to techniques that use data analysis results to identify problems in work and the work environment, and to devise plans for improvement.

[0492] "Means for generating and notifying action plans based on improvement suggestions" refers to methods and technologies for planning specific improvement measures and informing relevant parties.

[0493] "Means of obtaining feedback in a collaborative environment with work machines" refers to methods for collecting opinions and reactions from employees in situations where employees and machines work together.

[0494] "Means for processing collected feedback" refers to techniques or processes for organizing the opinions and reactions received and using them to solve problems or propose improvements.

[0495] The system implementing this invention includes a program for efficiently collecting and analyzing employee feedback. The server first utilizes a generative AI model to design questionnaires, dynamically adjusting questions to suit specific tasks and job roles. The designed questionnaires are then distributed to users via email or a dedicated application.

[0496] The terminal notifies the user that a survey has been distributed and provides an interface for the user to review and respond to the content. The user answers the questions displayed on the terminal, and the responses are immediately transmitted to the server. The server stores the collected data in a database and performs sentiment analysis using natural language processing libraries (e.g., NLTK or spaCy). Based on the results, it identifies problems and generates suggestions for improvement.

[0497] Improvement suggestions are converted into detailed action plans by the server and notified to relevant parties. These notifications are delivered to administrators' terminals via tools such as Microsoft Power Automate, allowing administrators to adjust resources and implement the plans.

[0498] For example, if a factory receives many comments stating that "the lighting in the work area is insufficient," the server will use sentiment analysis to identify the problem, generate a suggestion to increase lighting, and notify the person in charge.

[0499] An example of a prompt would be, "What emotions are identified from this feedback? Please identify specific areas that need improvement."

[0500] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0501] Step 1:

[0502] The server designs the survey using a generative AI model. This process dynamically generates questions that take into account employee roles and job responsibilities. Inputs include employee profile information and specific company needs, and the output is a customized survey.

[0503] Step 2:

[0504] The server distributes the designed questionnaire to terminals via email or a dedicated application. Inputs include the customized questionnaire and employee contact information, while output is the sending of the questionnaire to the employee's terminal.

[0505] Step 3:

[0506] The terminal notifies the user that a survey has arrived and provides an interface for answering the survey. The input is the received survey, and the output is the user's responses. The user answers the questions using the terminal's interface.

[0507] Step 4:

[0508] User responses are immediately forwarded to the server, which stores them in a database. The input is the user's response data, and the output is an updated entry in the database.

[0509] Step 5:

[0510] The server uses natural language processing libraries (NLTK and spaCy) to perform sentiment analysis on the collected data. The input is response data stored in a database, and the output is the result of the sentiment analysis. This result reveals the emotional tone of the feedback.

[0511] Step 6:

[0512] The server generates improvement suggestions based on the results of sentiment analysis. The input is the results of sentiment analysis, and the output is specific improvement suggestions. Improvement measures are formulated using a generative AI model.

[0513] Step 7:

[0514] Based on the improvement suggestions, the server generates a detailed action plan and notifies the necessary stakeholders through tools such as Microsoft Power Automate. The input is the improvement suggestions, and the output is the notification to stakeholders and the sharing of the action plan.

[0515] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0516] The system according to the present invention aims to improve employee engagement by automatically collecting and analyzing feedback from employees, and generating and implementing improvement suggestions and action plans based on the results. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, thereby enabling the provision of appropriate feedback and suggestions based on a deeper understanding of emotions.

[0517] The server first uses a generative AI model to design questionnaires tailored to employees' roles and work needs. This process dynamically adjusts the questions by incorporating not only past user feedback but also input from an emotion engine. The completed questionnaires are distributed to each employee via email or internal applications.

[0518] The terminal notifies employees when a survey is distributed and provides an interface for users to answer the survey. Employees can also record their emotional state while answering the survey, and this information is also sent to the server via the terminal.

[0519] The server stores survey results and sentiment data in a database and performs data analysis using natural language processing technology. Here, the sentiment engine recognizes changes in the user's emotions in real time and provides accurate sentiment feedback for the survey.

[0520] Based on the analysis results, the server generates improvement suggestions to enhance employee engagement. The priority of each suggestion is dynamically adjusted by incorporating the analysis results from the emotion engine. In response to these suggestions, the server develops a concrete action plan and notifies the specific steps to be taken.

[0521] Administrators approve action plans notified by the server and secure or adjust the relevant resources. Suggestions may include, for example, "holding refreshment seminars to reduce stress levels" or "implementing a peer review system to facilitate smooth exchange of ideas."

[0522] Furthermore, the server has an action plan tracking function and monitors progress in real time. This system allows users to continuously understand whether the plan is on track and to fine-tune the project as needed. Through these functions, the system contributes to improving employee engagement and maintaining corporate productivity.

[0523] The following describes the processing flow.

[0524] Step 1:

[0525] The server designs employee surveys using a generative AI model. Here, the server references data from an emotion engine and dynamically adjusts questions, taking into account the user's past emotional tendencies. The surveys are sent via email or a dedicated application, whichever distribution method is chosen.

[0526] Step 2:

[0527] The terminal displays notifications of received surveys to the employee user. The terminal launches an interface for the user to answer the survey and supports the input of responses. During this process, the terminal captures the user's emotions and sends that data to the server.

[0528] Step 3:

[0529] The server stores survey responses and sentiment data submitted from the terminals in a database. The server uses natural language processing techniques to perform sentiment analysis on the text data and extract the positive and negative aspects of the feedback.

[0530] Step 4:

[0531] The server generates improvement suggestions based on emotional data supplied by the emotion engine. This process prioritizes suggestions based on the emotional data and evaluates the importance of the issues that need addressing. The generated suggestions are then developed into concrete action plans.

[0532] Step 5:

[0533] The server notifies relevant parties of the generated action plan. The administrator, as the user, reviews this notification and takes necessary resource procurement and internal coordination based on the proposal. The notification may include, for example, "hold a monthly feedback meeting" or "concretize workplace improvement measures."

[0534] Step 6:

[0535] The server provides the ability to monitor the implementation of action plans and track progress in real time. If necessary, the server sends reminders to users and prompts quick action if the plan falls behind schedule.

[0536] Step 7:

[0537] The administrator, as a user, reviews progress reports from the server and makes necessary adjustments. This enables the rapid implementation of engagement improvement measures based on feedback within the company, contributing to maintaining the vitality of the entire organization.

[0538] (Example 2)

[0539] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0540] To improve employee engagement and maintain productivity, it is essential to efficiently and accurately collect and analyze employee feedback. However, traditional methods have limitations in terms of efficiency and accuracy in feedback collection, and it is particularly difficult to respond to subtle changes in emotions. Effectively addressing this challenge is necessary.

[0541] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0542] In this invention, the server includes a design means using a generation model to generate information gathering questions according to roles, a means for individually providing the designed questions using information and communication technology, and a means for collecting answers to the questions through a receiving medium. This enables the collection and analysis of feedback that takes into account the diverse needs and emotional changes of employees.

[0543] A "generative model" refers to an algorithm or technology that generates new information based on a large amount of data.

[0544] "Information and communication technology" refers to all technologies related to the transmission, reception, and processing of digital data.

[0545] A "receiving medium" refers to a device or interface used to import digital data from a user into a system.

[0546] "Natural language processing technology" refers to the technology used to analyze, understand, and generate human language using computers.

[0547] An "emotion analysis engine" refers to a software component that recognizes and analyzes a user's emotional state and changes from data.

[0548] An "action plan" refers to a series of specific steps and activities set out to achieve a particular goal.

[0549] "Management information" refers to the data and reports necessary to monitor and evaluate the progress of a project or plan.

[0550] The system of this invention is built around automated feedback collection and suggestion generation to improve employee engagement. Key technological elements incorporated include generative AI models, information and communication technologies, natural language processing technologies, and sentiment analysis engines.

[0551] The server utilizes a generative AI model to generate questionnaires tailored to employees' roles and job needs. By considering past feedback data and incorporating data from an emotion analysis engine, it enables more flexible and appropriate questions. This allows employees to provide specific feedback on their work environment and job satisfaction.

[0552] The terminal provides an interface for distributing questionnaires designed by the server directly to employees using information and communication technology, and for receiving responses. Employees answer the questionnaires through this interface and record their emotional state. This data is transmitted to the server via the receiving medium.

[0553] The server analyzes collected survey responses and sentiment data using natural language processing technology. The sentiment analysis engine evaluates employee sentiment changes in real time and provides detailed feedback based on this analysis. Based on the analysis results, the server generates improvement suggestions and develops an optimal action plan. This plan is notified to administrators via information and communication technology, enabling its implementation.

[0554] As a concrete example, the generative AI model can be provided with the following prompt, allowing for the customization of questions to understand employee needs: "Create a survey to gather feedback on the work environment and job duties to improve employee job satisfaction. Also, include questions to identify stressors that employees experience."

[0555] This system functions as a crucial resource in a company's human resource strategy, contributing to improved employee satisfaction and productivity.

[0556] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0557] Step 1:

[0558] The server inputs prompts into a generative AI model, which then generates survey questions based on employee roles and work needs. Specifically, the server collects past feedback data and data from a sentiment analysis engine and passes it to the generative AI model. This results in a customized set of questions being output.

[0559] Step 2:

[0560] The server distributes the generated questionnaire to the terminals using information and communication technology. The input consists of the questionnaire questions generated in step 1, and these are sent to each employee's terminal using email addresses or the company's messaging system. The output is a questionnaire link accessible to the employee.

[0561] Step 3:

[0562] The terminal notifies employees of the distributed survey and displays the response interface. Specifically, the terminal automatically displays the received survey link in a notification window, and when the user clicks it, the web interface opens. The input is the survey link sent in step 2, and the output is the user's response screen.

[0563] Step 4:

[0564] Users answer questionnaires via their devices and record their emotional state. Specific actions include entering information into text fields and selecting from emotional options. Input is the questionnaire questions, and output is employee response data and emotional data.

[0565] Step 5:

[0566] The device sends user-entered responses and sentiment data to the server. Specifically, when the "Send" button is pressed, the device uploads the data to the server in real time. The input consists of the user's response data and sentiment data, and the output is the raw data stored on the server.

[0567] Step 6:

[0568] The server analyzes the received survey responses and sentiment data using natural language processing techniques. The input is the raw data sent in step 5, which is used to execute the analysis algorithm. The output is detailed feedback information, including sentiment data.

[0569] Step 7:

[0570] The server generates improvement suggestions to enhance employee engagement based on the analysis results. Specific actions include prioritizing based on data from the sentiment analysis engine. The input is the analysis results from step 6, and the output is improvement suggestions and an action plan.

[0571] Step 8:

[0572] The server notifies the administrator of the generated improvement suggestions and action plan, and then moves to the implementation phase. The input is the plan content generated in step 7, and the output is the detailed action steps delivered to the administrator. Specific actions include posting information on the dashboard and sending alerts.

[0573] (Application Example 2)

[0574] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0575] In modern society, improving employee engagement is crucial for increasing organizational productivity and efficiency. However, traditional surveys and evaluation methods fail to adequately capture employees' emotions and potential problems. Furthermore, while there is a need for improvement suggestions and communication methods that take emotional states into account, a reliable system for achieving this is lacking.

[0576] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0577] In this invention, the server includes means for designing and distributing questionnaires, means for collecting and analyzing responses to the questionnaires, means for generating improvement suggestions based on the analysis results, means for monitoring the user's emotional state using emotion analysis technology, means for integrating and analyzing emotional data and response data, and means for suggesting appropriate communication methods using generative AI technology. This enables appropriate feedback and improvement suggestions based on the emotional state of employees, thereby improving engagement.

[0578] "Means for designing and distributing questionnaires" refers to a function that dynamically constructs questions tailored to the user's role and business needs, and efficiently distributes them via email or application.

[0579] "Means for collecting and analyzing survey responses" refers to a mechanism for collecting data provided by users and analyzing that data.

[0580] "Methods for generating improvement suggestions" refers to a process that automatically creates useful suggestions for users based on insights obtained from analyzed data.

[0581] "Methods for monitoring a user's emotional state using emotion analysis technology" refers to technologies that capture emotional trends by acquiring user emotional data and tracking its changes in real time.

[0582] "Methods for integrating and analyzing emotional data and response data" refers to a process that combines changes in emotions with survey responses to comprehensively evaluate the user's state.

[0583] "A means of suggesting appropriate communication methods using generative AI technology" refers to a function that utilizes AI models to suggest the optimal communication style and content based on the user's emotional state and responses.

[0584] To implement this invention, a system configuration is required in which a server, a terminal, and a user each play their respective roles.

[0585] The server designs surveys based on users' roles and business needs, and dynamically generates appropriate questions using a generative AI model. Next, it distributes the surveys via email and internal applications. The server aggregates survey response data and sentiment data transmitted from devices, and monitors users' emotional states using sentiment analysis technology. This allows for the integration of response and sentiment data, enabling advanced data analysis and the generation of improvement suggestions.

[0586] The device notifies the user of surveys and provides a response interface. Users can record their emotional state through the device, and this information is sent to a server for analysis.

[0587] The user (administrator) reviews the improvement suggestions and action plans provided by the server and arranges and adjusts the necessary resources. The server uses generative AI technology to suggest the optimal communication method based on the user's emotional state. This allows the user to practice stress management and improve communication.

[0588] For example, a manager who notices a decline in employee motivation can use this system to adopt effective engagement strategies based on the employee's emotional state and feedback data. By using prompts such as, "Based on employee A's feedback, please suggest improvements tailored to his stress level," the generative AI model provides practical solutions.

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The server uses a generative AI model to design surveys related to the user's role and tasks. It receives past feedback and information from the sentiment engine as input and generates dynamically adjusted survey questions as output. This process appropriately customizes the content of the questions to accurately reflect the user's needs.

[0592] Step 2:

[0593] The server distributes the designed questionnaire to users' terminals via email or internal applications. The generated questionnaire arrives on the terminal, and the user is notified. The input here is the content of the generated questionnaire, and the output is the sending of the questionnaire to each user.

[0594] Step 3:

[0595] Users answer questionnaires via a device. The device receives the user's responses as input and also sends additional data about the user's emotional state to the server. The specific functions of the device are providing an input interface and transmitting data.

[0596] Step 4:

[0597] The server stores received survey responses and sentiment data in a database and analyzes them using natural language processing techniques. User response data and sentiment data are used as input, and the output includes analysis results and identification of potential problems. Specifically, the system performs text analysis and sentiment evaluation.

[0598] Step 5:

[0599] The server generates improvement suggestions based on the analysis results. These suggestions are optimized using a real-time AI model that takes into account fluctuating emotional states based on emotion analysis technology. The input here is the analysis results, and the output is improvement suggestions customized for each individual user.

[0600] Step 6:

[0601] The server develops a concrete action plan based on the generated improvement suggestions and notifies the user. The input is improvement suggestions, and the output is an actionable plan notified to the user. The server's specific actions are designing and notifying the action plan.

[0602] Step 7:

[0603] The user reviews the provided action plan and arranges and coordinates the necessary resources. This process requires the user to understand the proposal and take action based on it. The output is the specific actions taken based on the plan.

[0604] Step 8:

[0605] The server tracks the implementation status of action plans and monitors progress in real time. Inputs are action feedback from each user, and outputs are real-time reports of overall progress. The server's specific functions are progress management and status updates.

[0606] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0607] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0608] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0609] [Fourth Embodiment]

[0610] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0611] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0612] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0613] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0614] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0615] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0616] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0617] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0618] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0619] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0620] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0621] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0622] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0623] The employee engagement assistant according to the present invention is a system for improving employee satisfaction within a company and streamlining the direct implementation of feedback. This system primarily uses a server, terminals, and users to perform various processes.

[0624] The server first uses a generative AI model to design a survey for the target employees. The designed survey is dynamically adjusted based on specific needs and objectives, ensuring it includes appropriate questions tailored to each employee's role and responsibilities. This survey is then distributed to employees via email or a dedicated application.

[0625] The terminal notifies employees that a survey has been distributed and provides an interface for them to review and respond to its contents. Employees, as users, answer the questions displayed on the terminal, and their responses are immediately transmitted to the server. The server stores the collected data in a database and then performs sentiment analysis to reveal the emotional tone of the feedback.

[0626] Based on the analysis results, the server generates specific improvement suggestions to enhance employee engagement. These suggestions identify problems across the entire company or within specific departments and develop solutions. Based on the proposed improvements, it automatically generates more specific action plans and notifies the relevant personnel as needed.

[0627] The administrator, as a user, receives notifications from the server, reviews the proposed action plan, and makes necessary adjustments and allocates resources as needed. In this process, feedback directly related to practical work is easily incorporated, such as "generalizing feedback from monthly meetings" or "making further adjustments to improve workplace comfort."

[0628] The system of this invention helps to ensure that plans are progressing appropriately by regularly tracking the progress of action plans and providing administrators with notifications as needed. In this way, a series of steps for improving engagement are efficiently managed, leading to increased corporate productivity and sustained improvements in employee satisfaction.

[0629] The following describes the processing flow.

[0630] Step 1:

[0631] The server designs surveys according to the company's needs. It utilizes a generative AI model to set appropriate questions based on employee roles and job responsibilities. After design, the surveys are distributed to employees via email or a dedicated application.

[0632] Step 2:

[0633] The terminal notifies employees of the distribution of the survey and displays an interface for answering. Employees, as users, answer the questions on the terminal and send their responses to the server.

[0634] Step 3:

[0635] The server stores the received survey responses in a database. Next, it performs sentiment analysis of the responses using natural language processing techniques to identify positive and negative feedback.

[0636] Step 4:

[0637] Based on the results of sentiment analysis, the server automatically generates specific improvement suggestions to enhance employee engagement. These suggestions are designed to address issues at the overall level or in specific departments.

[0638] Step 5:

[0639] Based on the proposed improvements, the server will create a concrete action plan and notify the relevant departments. The notification will include the necessary resource allocation and implementation plan.

[0640] Step 6:

[0641] The administrator, as a user, reviews the notified action plan and, if necessary, arranges resources and prepares for specific implementation.

[0642] Step 7:

[0643] The server tracks the implementation status of the action plan. It monitors whether progress is on track and notifies responsible parties of reminders as needed.

[0644] (Example 1)

[0645] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0646] Effectively improving employee engagement within a company is crucial for increasing organizational productivity. However, traditional approaches have limitations in accurately collecting and analyzing employee feedback, resulting in challenges in the rapid development and implementation of improvement measures. Furthermore, the process of analyzing the emotional aspects of feedback and translating this into concrete action plans is not sufficiently automated.

[0647] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0648] In this invention, the server includes means for designing a questionnaire based on prompt text using a generative AI model, means for distributing the designed questionnaire via electronic notification, and means for collecting questionnaire responses and storing them in a database. This enables immediate analysis of employee feedback and the automatic generation of specific improvement suggestions and action plans based on emotional tendencies.

[0649] A "generative AI model" is an algorithm that learns from data and generates information based on natural language prompts.

[0650] A "prompt statement" is an instruction given to a generative AI model for generating information.

[0651] A "survey" is a set of questions designed to collect specific information.

[0652] "Electronic notification" refers to a method of transmitting information to a recipient in a digital format.

[0653] A "database" is a system that systematically stores information and saves it in a searchable format.

[0654] "Sentiment analysis" is the process of identifying emotional tendencies and feelings within text data.

[0655] An "improvement suggestion" is specific advice or a strategy for solving a particular problem.

[0656] An "action plan" is a specific plan of actions to be taken in order to achieve a particular goal.

[0657] This system aims to improve employee engagement and consists mainly of three elements: servers, terminals, and users.

[0658] Server embodiment:

[0659] The server designs the survey using a generative AI model, generating individual questions by inputting prompts during this process. The generative AI model used is a large-scale natural language processing model. The survey is dynamically adjusted to include questions specific to job roles and responsibilities within the company. For example, a prompt such as "Create questions about stress management for the sales department" will generate questions tailored to a specific job role. This designed survey is then delivered to terminals via electronic means. Simultaneously, the server manages the response data and performs sentiment analysis on the collected responses. This utilizes sentiment analysis software to extract emotional tendencies from the text data.

[0660] Terminal embodiment:

[0661] The terminal receives questionnaires distributed from the server and displays them to employees as a user interface. Users answer the questionnaires through this terminal and input data processed by a generative AI model. The responses are sent to the server in real time and stored in the database.

[0662] User embodiment:

[0663] Employees, as users, can easily access distributed questionnaires and freely provide feedback and opinions on their daily work. Administrators, as users, receive proposed improvement measures and action plans via notifications from the server and begin implementing the measures. For example, if there is a suggestion to "hold lunch meetings to strengthen communication between teams," administrators can use this as a basis to create a concrete action plan.

[0664] In this way, the collaboration between the server, terminal, and user enables an efficient feedback loop for improving engagement.

[0665] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0666] Step 1:

[0667] The server designs the survey using a generative AI model. A prompt is provided as input, and the generative AI model generates questions appropriate to each employee's role and responsibilities. The resulting survey is provided as a set of questions tailored to individual needs. Specifically, the prompt "Create questions about improving teamwork for the marketing department" is used as input, and the result is output as a set of questions.

[0668] Step 2:

[0669] The server distributes the designed questionnaires to employee terminals via email or a dedicated application. The inputs used are the questionnaire to be distributed and the recipient employee's email address or application identifier. The output is achieved by transmitting these to the terminals over the internet.

[0670] Step 3:

[0671] The terminal notifies employees of distributed surveys and provides an interface to display their contents. The input is survey data received from the server, which is output in the form of a notification and displayed on the screen. Specific actions include the display of pop-up notifications and in-application messages on the terminal screen.

[0672] Step 4:

[0673] Employees, as users, answer surveys through the terminal's interface. The input is the response data entered by the user on the interface. As output, this response data is sent from the terminal to the server and stored in a database. Specifically, data is collected through selection of options and text input.

[0674] Step 5:

[0675] The server performs sentiment analysis using the received survey responses. The input data is the responses submitted by the user, and the output is the analysis results. The sentiment analysis software identifies emotional tendencies within the text data and classifies them into categories such as positive, negative, and neutral.

[0676] Step 6:

[0677] The server generates improvement suggestions based on the sentiment analysis results. The analysis results are used as input, and the generating AI model is used again to output specific suggestions. As a result, optimal improvement measures based on employee feedback are proposed. For example, "improving team morale through improved communication" might be output.

[0678] Step 7:

[0679] The server automatically creates an action plan based on the generated improvement suggestions and notifies the administrator user. The input is the generated improvement suggestions, and the notification informs the administrator of the next steps to implement the plan. Specifically, the administrator is notified via email or internal company communication tools.

[0680] (Application Example 1)

[0681] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0682] In today's work environment, where collaboration between employees and machinery is increasing, improving employee satisfaction and obtaining effective feedback are crucial challenges. Conventional methods have failed to efficiently collect employee feedback, making it difficult to quickly propose improvements and formulate action plans. This invention aims to provide a means for continuously and efficiently obtaining employee feedback in a collaborative environment with machinery, and for quickly implementing improvement measures based on that feedback.

[0683] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0684] In this invention, the server includes means for designing and distributing questionnaires, means for collecting and analyzing responses to the questionnaires, means for generating improvement suggestions based on the analysis results, means for generating and notifying action plans based on the improvement suggestions, means for obtaining feedback in a collaborative environment with work machines, and means for processing the collected feedback. This makes it possible to efficiently obtain feedback from employees and to quickly and accurately improve the work environment.

[0685] A "survey" is a set of questions designed to collect information, primarily used to assess employees' opinions and feelings.

[0686] "Means of design and distribution" refers to the process or technology for determining the content of the questionnaire and supplying it to the target audience.

[0687] "Means for collecting and analyzing responses" refers to the techniques and methods for gathering information obtained from subjects and analyzing that data.

[0688] "Methods for generating improvement proposals based on analysis results" refers to techniques that use data analysis results to identify problems in work and the work environment, and to devise plans for improvement.

[0689] "Means for generating and notifying action plans based on improvement suggestions" refers to methods and technologies for planning specific improvement measures and informing relevant parties.

[0690] "Means of obtaining feedback in a collaborative environment with work machines" refers to methods for collecting opinions and reactions from employees in situations where employees and machines work together.

[0691] "Means for processing collected feedback" refers to techniques or processes for organizing the opinions and reactions received and using them to solve problems or propose improvements.

[0692] The system implementing this invention includes a program for efficiently collecting and analyzing employee feedback. The server first utilizes a generative AI model to design questionnaires, dynamically adjusting questions to suit specific tasks and job roles. The designed questionnaires are then distributed to users via email or a dedicated application.

[0693] The terminal notifies the user that a survey has been distributed and provides an interface for the user to review and respond to the content. The user answers the questions displayed on the terminal, and the responses are immediately transmitted to the server. The server stores the collected data in a database and performs sentiment analysis using natural language processing libraries (e.g., NLTK or spaCy). Based on the results, it identifies problems and generates suggestions for improvement.

[0694] Improvement suggestions are converted into detailed action plans by the server and notified to relevant parties. These notifications are delivered to administrators' terminals via tools such as Microsoft Power Automate, allowing administrators to adjust resources and implement the plans.

[0695] For example, if a factory receives many comments stating that "the lighting in the work area is insufficient," the server will use sentiment analysis to identify the problem, generate a suggestion to increase lighting, and notify the person in charge.

[0696] An example of a prompt would be, "What emotions are identified from this feedback? Please identify specific areas that need improvement."

[0697] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0698] Step 1:

[0699] The server designs the survey using a generative AI model. This process dynamically generates questions that take into account employee roles and job responsibilities. Inputs include employee profile information and specific company needs, and the output is a customized survey.

[0700] Step 2:

[0701] The server distributes the designed questionnaire to terminals via email or a dedicated application. Inputs include the customized questionnaire and employee contact information, while output is the sending of the questionnaire to the employee's terminal.

[0702] Step 3:

[0703] The terminal notifies the user that a survey has arrived and provides an interface for answering the survey. The input is the received survey, and the output is the user's responses. The user answers the questions using the terminal's interface.

[0704] Step 4:

[0705] User responses are immediately forwarded to the server, which stores them in a database. The input is the user's response data, and the output is an updated entry in the database.

[0706] Step 5:

[0707] The server uses natural language processing libraries (NLTK and spaCy) to perform sentiment analysis on the collected data. The input is response data stored in a database, and the output is the result of the sentiment analysis. This result reveals the emotional tone of the feedback.

[0708] Step 6:

[0709] The server generates improvement suggestions based on the results of sentiment analysis. The input is the results of sentiment analysis, and the output is specific improvement suggestions. Improvement measures are formulated using a generative AI model.

[0710] Step 7:

[0711] Based on the improvement suggestions, the server generates a detailed action plan and notifies the necessary stakeholders through tools such as Microsoft Power Automate. The input is the improvement suggestions, and the output is the notification to stakeholders and the sharing of the action plan.

[0712] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0713] The system according to the present invention aims to improve employee engagement by automatically collecting and analyzing feedback from employees, and generating and implementing improvement suggestions and action plans based on the results. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, thereby enabling the provision of appropriate feedback and suggestions based on a deeper understanding of emotions.

[0714] The server first uses a generative AI model to design questionnaires tailored to employees' roles and work needs. This process dynamically adjusts the questions by incorporating not only past user feedback but also input from an emotion engine. The completed questionnaires are distributed to each employee via email or internal applications.

[0715] The terminal notifies employees when a survey is distributed and provides an interface for users to answer the survey. Employees can also record their emotional state while answering the survey, and this information is also sent to the server via the terminal.

[0716] The server stores survey results and sentiment data in a database and performs data analysis using natural language processing technology. Here, the sentiment engine recognizes changes in the user's emotions in real time and provides accurate sentiment feedback for the survey.

[0717] Based on the analysis results, the server generates improvement suggestions to enhance employee engagement. The priority of each suggestion is dynamically adjusted by incorporating the analysis results from the emotion engine. In response to these suggestions, the server develops a concrete action plan and notifies the specific steps to be taken.

[0718] Administrators approve action plans notified by the server and secure or adjust the relevant resources. Suggestions may include, for example, "holding refreshment seminars to reduce stress levels" or "implementing a peer review system to facilitate smooth exchange of ideas."

[0719] Furthermore, the server has an action plan tracking function and monitors progress in real time. This system allows users to continuously understand whether the plan is on track and to fine-tune the project as needed. Through these functions, the system contributes to improving employee engagement and maintaining corporate productivity.

[0720] The following describes the processing flow.

[0721] Step 1:

[0722] The server designs employee surveys using a generative AI model. Here, the server references data from an emotion engine and dynamically adjusts questions, taking into account the user's past emotional tendencies. The surveys are sent via email or a dedicated application, whichever distribution method is chosen.

[0723] Step 2:

[0724] The terminal displays notifications of received surveys to the employee user. The terminal launches an interface for the user to answer the survey and supports the input of responses. During this process, the terminal captures the user's emotions and sends that data to the server.

[0725] Step 3:

[0726] The server stores survey responses and sentiment data submitted from the terminals in a database. The server uses natural language processing techniques to perform sentiment analysis on the text data and extract the positive and negative aspects of the feedback.

[0727] Step 4:

[0728] The server generates improvement suggestions based on emotional data supplied by the emotion engine. This process prioritizes suggestions based on the emotional data and evaluates the importance of the issues that need addressing. The generated suggestions are then developed into concrete action plans.

[0729] Step 5:

[0730] The server notifies relevant parties of the generated action plan. The administrator, as the user, reviews this notification and takes necessary resource procurement and internal coordination based on the proposal. The notification may include, for example, "hold a monthly feedback meeting" or "concretize workplace improvement measures."

[0731] Step 6:

[0732] The server provides the ability to monitor the implementation of action plans and track progress in real time. If necessary, the server sends reminders to users and prompts quick action if the plan falls behind schedule.

[0733] Step 7:

[0734] The administrator, as a user, reviews progress reports from the server and makes necessary adjustments. This enables the rapid implementation of engagement improvement measures based on feedback within the company, contributing to maintaining the vitality of the entire organization.

[0735] (Example 2)

[0736] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0737] To improve employee engagement and maintain productivity, it is essential to efficiently and accurately collect and analyze employee feedback. However, traditional methods have limitations in terms of efficiency and accuracy in feedback collection, and it is particularly difficult to respond to subtle changes in emotions. Effectively addressing this challenge is necessary.

[0738] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0739] In this invention, the server includes a design means using a generation model to generate information gathering questions according to roles, a means for individually providing the designed questions using information and communication technology, and a means for collecting answers to the questions through a receiving medium. This enables the collection and analysis of feedback that takes into account the diverse needs and emotional changes of employees.

[0740] A "generative model" refers to an algorithm or technology that generates new information based on a large amount of data.

[0741] "Information and communication technology" refers to all technologies related to the transmission, reception, and processing of digital data.

[0742] A "receiving medium" refers to a device or interface used to import digital data from a user into a system.

[0743] "Natural language processing technology" refers to the technology used to analyze, understand, and generate human language using computers.

[0744] An "emotion analysis engine" refers to a software component that recognizes and analyzes a user's emotional state and changes from data.

[0745] An "action plan" refers to a series of specific steps and activities set out to achieve a particular goal.

[0746] "Management information" refers to the data and reports necessary to monitor and evaluate the progress of a project or plan.

[0747] The system of this invention is built around automated feedback collection and suggestion generation to improve employee engagement. Key technological elements incorporated include generative AI models, information and communication technologies, natural language processing technologies, and sentiment analysis engines.

[0748] The server utilizes a generative AI model to generate questionnaires tailored to employees' roles and job needs. By considering past feedback data and incorporating data from an emotion analysis engine, it enables more flexible and appropriate questions. This allows employees to provide specific feedback on their work environment and job satisfaction.

[0749] The terminal provides an interface for distributing questionnaires designed by the server directly to employees using information and communication technology, and for receiving responses. Employees answer the questionnaires through this interface and record their emotional state. This data is transmitted to the server via the receiving medium.

[0750] The server analyzes collected survey responses and sentiment data using natural language processing technology. The sentiment analysis engine evaluates employee sentiment changes in real time and provides detailed feedback based on this analysis. Based on the analysis results, the server generates improvement suggestions and develops an optimal action plan. This plan is notified to administrators via information and communication technology, enabling its implementation.

[0751] As a concrete example, the generative AI model can be provided with the following prompt, allowing for the customization of questions to understand employee needs: "Create a survey to gather feedback on the work environment and job duties to improve employee job satisfaction. Also, include questions to identify stressors that employees experience."

[0752] This system functions as a crucial resource in a company's human resource strategy, contributing to improved employee satisfaction and productivity.

[0753] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0754] Step 1:

[0755] The server inputs prompts into a generative AI model, which then generates survey questions based on employee roles and work needs. Specifically, the server collects past feedback data and data from a sentiment analysis engine and passes it to the generative AI model. This results in a customized set of questions being output.

[0756] Step 2:

[0757] The server distributes the generated questionnaire to the terminals using information and communication technology. The input consists of the questionnaire questions generated in step 1, and these are sent to each employee's terminal using email addresses or the company's messaging system. The output is a questionnaire link accessible to the employee.

[0758] Step 3:

[0759] The terminal notifies employees of the distributed survey and displays the response interface. Specifically, the terminal automatically displays the received survey link in a notification window, and when the user clicks it, the web interface opens. The input is the survey link sent in step 2, and the output is the user's response screen.

[0760] Step 4:

[0761] Users answer questionnaires via their devices and record their emotional state. Specific actions include entering information into text fields and selecting from emotional options. Input is the questionnaire questions, and output is employee response data and emotional data.

[0762] Step 5:

[0763] The device sends user-entered responses and sentiment data to the server. Specifically, when the "Send" button is pressed, the device uploads the data to the server in real time. The input consists of the user's response data and sentiment data, and the output is the raw data stored on the server.

[0764] Step 6:

[0765] The server analyzes the received survey responses and sentiment data using natural language processing techniques. The input is the raw data sent in step 5, which is used to execute the analysis algorithm. The output is detailed feedback information, including sentiment data.

[0766] Step 7:

[0767] The server generates improvement suggestions to enhance employee engagement based on the analysis results. Specific actions include prioritizing based on data from the sentiment analysis engine. The input is the analysis results from step 6, and the output is improvement suggestions and an action plan.

[0768] Step 8:

[0769] The server notifies the administrator of the generated improvement suggestions and action plan, and then moves to the implementation phase. The input is the plan content generated in step 7, and the output is the detailed action steps delivered to the administrator. Specific actions include posting information on the dashboard and sending alerts.

[0770] (Application Example 2)

[0771] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0772] In modern society, improving employee engagement is crucial for increasing organizational productivity and efficiency. However, traditional surveys and evaluation methods fail to adequately capture employees' emotions and potential problems. Furthermore, while there is a need for improvement suggestions and communication methods that take emotional states into account, a reliable system for achieving this is lacking.

[0773] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0774] In this invention, the server includes means for designing and distributing questionnaires, means for collecting and analyzing responses to the questionnaires, means for generating improvement suggestions based on the analysis results, means for monitoring the user's emotional state using emotion analysis technology, means for integrating and analyzing emotional data and response data, and means for suggesting appropriate communication methods using generative AI technology. This enables appropriate feedback and improvement suggestions based on the emotional state of employees, thereby improving engagement.

[0775] "Means for designing and distributing questionnaires" refers to a function that dynamically constructs questions tailored to the user's role and business needs, and efficiently distributes them via email or application.

[0776] "Means for collecting and analyzing survey responses" refers to a mechanism for collecting data provided by users and analyzing that data.

[0777] "Methods for generating improvement suggestions" refers to a process that automatically creates useful suggestions for users based on insights obtained from analyzed data.

[0778] "Methods for monitoring a user's emotional state using emotion analysis technology" refers to technologies that capture emotional trends by acquiring user emotional data and tracking its changes in real time.

[0779] "Methods for integrating and analyzing emotional data and response data" refers to a process that combines changes in emotions with survey responses to comprehensively evaluate the user's state.

[0780] "A means of suggesting appropriate communication methods using generative AI technology" refers to a function that utilizes AI models to suggest the optimal communication style and content based on the user's emotional state and responses.

[0781] To implement this invention, a system configuration is required in which a server, a terminal, and a user each play their respective roles.

[0782] The server designs surveys based on users' roles and business needs, and dynamically generates appropriate questions using a generative AI model. Next, it distributes the surveys via email and internal applications. The server aggregates survey response data and sentiment data transmitted from devices, and monitors users' emotional states using sentiment analysis technology. This allows for the integration of response and sentiment data, enabling advanced data analysis and the generation of improvement suggestions.

[0783] The device notifies the user of surveys and provides a response interface. Users can record their emotional state through the device, and this information is sent to a server for analysis.

[0784] The user (administrator) reviews the improvement suggestions and action plans provided by the server and arranges and adjusts the necessary resources. The server uses generative AI technology to suggest the optimal communication method based on the user's emotional state. This allows the user to practice stress management and improve communication.

[0785] For example, a manager who notices a decline in employee motivation can use this system to adopt effective engagement strategies based on the employee's emotional state and feedback data. By using prompts such as, "Based on employee A's feedback, please suggest improvements tailored to his stress level," the generative AI model provides practical solutions.

[0786] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0787] Step 1:

[0788] The server uses a generative AI model to design surveys related to the user's role and tasks. It receives past feedback and information from the sentiment engine as input and generates dynamically adjusted survey questions as output. This process appropriately customizes the content of the questions to accurately reflect the user's needs.

[0789] Step 2:

[0790] The server distributes the designed questionnaire to users' terminals via email or internal applications. The generated questionnaire arrives on the terminal, and the user is notified. The input here is the content of the generated questionnaire, and the output is the sending of the questionnaire to each user.

[0791] Step 3:

[0792] Users answer questionnaires via a device. The device receives the user's responses as input and also sends additional data about the user's emotional state to the server. The specific functions of the device are providing an input interface and transmitting data.

[0793] Step 4:

[0794] The server stores received survey responses and sentiment data in a database and analyzes them using natural language processing techniques. User response data and sentiment data are used as input, and the output includes analysis results and identification of potential problems. Specifically, the system performs text analysis and sentiment evaluation.

[0795] Step 5:

[0796] The server generates improvement suggestions based on the analysis results. These suggestions are optimized using a real-time AI model that takes into account fluctuating emotional states based on emotion analysis technology. The input here is the analysis results, and the output is improvement suggestions customized for each individual user.

[0797] Step 6:

[0798] The server develops a concrete action plan based on the generated improvement suggestions and notifies the user. The input is improvement suggestions, and the output is an actionable plan notified to the user. The server's specific actions are designing and notifying the action plan.

[0799] Step 7:

[0800] The user reviews the provided action plan and arranges and coordinates the necessary resources. This process requires the user to understand the proposal and take action based on it. The output is the specific actions taken based on the plan.

[0801] Step 8:

[0802] The server tracks the implementation status of action plans and monitors progress in real time. Inputs are action feedback from each user, and outputs are real-time reports of overall progress. The server's specific functions are progress management and status updates.

[0803] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0804] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0805] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0806] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0807] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0808] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0809] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0810] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0811] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0812] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0813] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0814] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0815] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0816] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0817] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0818] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0819] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0820] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0821] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0822] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0823] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0824] The following is further disclosed regarding the embodiments described above.

[0825] (Claim 1)

[0826] The means of designing and distributing questionnaires,

[0827] A means for collecting and analyzing responses to the aforementioned questionnaire,

[0828] A means for generating improvement suggestions based on analysis results,

[0829] A means for generating and notifying an action plan based on the aforementioned improvement proposal,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] The system according to claim 1, which performs sentiment analysis from questionnaire responses and identifies potential problems.

[0833] (Claim 3)

[0834] The system according to claim 1, which tracks the implementation status of action plans based on improvement suggestions and manages their progress.

[0835] "Example 1"

[0836] (Claim 1)

[0837] A method for designing a questionnaire based on prompt sentences using a generative AI model,

[0838] A means of distributing the designed questionnaire via electronic notification,

[0839] A means of collecting survey responses and storing them in a database,

[0840] A means of analyzing the sentiment of the collected responses and identifying the emotional tendencies of the feedback,

[0841] A means for generating improvement suggestions to promote employee engagement based on analysis results,

[0842] A means of automatically generating and notifying action plans based on improvement suggestions,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, which identifies potential problems through sentiment analysis and visualizes the analysis results.

[0846] (Claim 3)

[0847] The system according to claim 1 for tracking the implementation status of generated action plans, managing and reporting on their progress.

[0848] "Application Example 1"

[0849] (Claim 1)

[0850] The means of designing and distributing questionnaires,

[0851] A means for collecting and analyzing responses to the aforementioned questionnaire,

[0852] A means for generating improvement suggestions based on analysis results,

[0853] A means for generating and notifying an action plan based on the aforementioned improvement proposal,

[0854] Means of obtaining feedback in a collaborative environment with work machines,

[0855] Means for processing collected feedback,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, which performs sentiment analysis from questionnaire responses and identifies potential problems.

[0859] (Claim 3)

[0860] The system according to claim 1, which tracks the implementation status of action plans based on improvement suggestions and manages their progress.

[0861] "Example 2 of combining an emotion engine"

[0862] (Claim 1)

[0863] A design method using a generative model that generates information gathering questions according to the role,

[0864] A means of providing the aforementioned designed questions individually using information and communication technology,

[0865] A means for collecting answers to the aforementioned questions through a receiving medium,

[0866] A means for analyzing the response data using natural language processing technology,

[0867] A means for dynamically generating improvement suggestions based on the aforementioned analysis results and emotion analysis results,

[0868] A means of formulating an action plan based on the aforementioned improvement proposals and notifying it using information and communication technology,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, which analyzes response data using an emotion analysis engine to identify the changing emotional state of employees.

[0872] (Claim 3)

[0873] The system according to claim 1, which monitors the progress of an action plan in real time and provides management information using data processing technology.

[0874] "Application example 2 when combining with an emotional engine"

[0875] (Claim 1)

[0876] The means of designing and distributing questionnaires,

[0877] A means for collecting and analyzing responses to the aforementioned questionnaire,

[0878] A means for generating improvement suggestions based on analysis results,

[0879] A means for generating and notifying an action plan based on the aforementioned improvement proposal,

[0880] A means of monitoring a user's emotional state using emotion analysis technology,

[0881] A means of integrating and analyzing emotional data and response data,

[0882] A means of proposing appropriate communication methods using generative AI technology,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, which uses questionnaire responses and sentiment data to identify potential problems.

[0886] (Claim 3)

[0887] The system according to claim 1, which tracks the implementation status of action plans based on improvement suggestions, manages progress, and optimizes communication methods in real time. [Explanation of Symbols]

[0888] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. The means of designing and distributing questionnaires, A means for collecting and analyzing responses to the aforementioned questionnaire, A means for generating improvement suggestions based on analysis results, A means for generating and notifying an action plan based on the aforementioned improvement proposal, A system that includes this.

2. The system according to claim 1, which performs sentiment analysis from questionnaire responses and identifies potential problems.

3. The system according to claim 1, which tracks the implementation status of action plans based on improvement suggestions and manages their progress.

Images