system

Abstract

The system according to this embodiment aims to understand employee satisfaction in detail and to grasp the state of the organization in real time. [Solution] The system according to the embodiment comprises a question addition unit, an opinion collection unit, an opinion analysis unit, a result aggregation unit, and a solution presentation unit. The question addition unit adds open-ended questions. The opinion collection unit collects opinions from employees. The opinion analysis unit analyzes the opinions collected by the opinion collection unit. The result aggregation unit aggregates the results based on the opinions analyzed by the opinion analysis unit. The solution presentation unit presents solutions based on the results aggregated by the result aggregation unit.

Description

Technical Field

[0004] ,

[0006] , , ,

[0005] , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to grasp the satisfaction of employees in detail and it is difficult to grasp the state of the organization in real time.

[0005] The system according to the embodiment aims to grasp the satisfaction of employees in detail and grasp the state of the organization in real time.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a question addition unit, an opinion collection unit, an opinion analysis unit, a result aggregation unit, and a solution presentation unit. The question addition unit adds open-ended questions. The opinion collection unit collects opinions from employees. The opinion analysis unit analyzes the opinions collected by the opinion collection unit. The result aggregation unit aggregates the results based on the opinions analyzed by the opinion analysis unit. The solution presentation unit presents solutions based on the results aggregated by the result aggregation unit. [Effects of the Invention]

[0007] The system according to this embodiment can grasp employee satisfaction in detail and understand the state of the organization in real time. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] 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.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The employee satisfaction survey system according to an embodiment of the present invention is a system for measuring and surveying employee satisfaction. This system collects employee opinions, has AI analyze the results and summarize them, and proposes solutions, thereby enabling real-time understanding of the organization's state and promoting improvement. The employee satisfaction survey system collects employee opinions by adding open-ended questions and an anonymous suggestion box. Next, the AI ​​analyzes the collected opinions and summarizes the results. Furthermore, by increasing the frequency of collection and aggregating employee opinions through an annual survey and the installation of a suggestion box, the AI ​​aggregates the results based on the aggregated opinions and creates a report for reporting. Finally, the AI ​​even proposes solutions, creating a state where continuous improvement can be achieved without burden. This mechanism makes it easier for employee voices to be reflected in the internal environment, reducing the burden on departmental and organizational HR. For example, the employee satisfaction survey system adds open-ended questions to the monthly EN survey, allowing employees to freely write their opinions. In addition, an anonymous suggestion box is installed where employees can always submit their opinions, allowing them to anonymously post complaints and requests. This makes it possible to collect the genuine voices of employees in real time. Next, the AI ​​analyzes the collected opinions and summarizes the results. The AI ​​analyzes opinions collected from open-ended questions and anonymous suggestion boxes, extracting important information. For example, it categorizes employee complaints and requests and identifies frequently occurring problems. This allows for a detailed understanding of the organization's state. Furthermore, the frequency of collection is increased, and employee opinions are aggregated through annual surveys and the installation of suggestion boxes. For example, a large-scale survey is conducted once a year to collect a wide range of employee opinions. In addition, an anonymous suggestion box is installed where employees can submit their opinions at any time, allowing for the continuous collection of employee opinions. Based on the aggregated opinions, the AI ​​summarizes the results and creates a report. For example, the AI ​​analyzes the collected opinions, extracts important information, and automatically creates a report. This allows the organization leader to understand the organization's state in real time. Finally, the AI ​​even proposes solutions, creating a system where continuous improvement is possible without burden. For example, the AI ​​proposes improvement measures based on the collected opinions and presents them to the organization leader.This allows organizations to quickly implement improvements and increase employee satisfaction. This system makes it easier for employee feedback to be reflected in the work environment, reducing the burden on departmental and organizational HR departments. For example, employee dissatisfaction and requests are quickly identified and addressed appropriately, leading to increased employee satisfaction. Furthermore, the AI ​​automatically compiles results and generates reports, reducing the burden on HR departments. This improves overall organizational efficiency and increases employee satisfaction. Thus, the employee satisfaction survey system can facilitate organizational improvement by gaining a detailed understanding of employee opinions and suggesting appropriate solutions.

[0029] The employee satisfaction survey system according to this embodiment comprises a question addition unit, an opinion collection unit, an opinion analysis unit, a results aggregation unit, and a solution presentation unit. The question addition unit adds open-ended questions. For example, the question addition unit adds open-ended questions to a monthly EN survey, allowing employees to freely express their opinions. The question addition unit can also flexibly set the format of the questions to allow employees to freely express their opinions. For example, the question addition unit can set formats such as open-ended, short-answer, and long-answer. The opinion collection unit collects employee opinions. For example, the opinion collection unit can install an anonymous suggestion box where employees can always submit their opinions, allowing them to anonymously post complaints and requests. The opinion collection unit can also devise a location and method for installing the suggestion box to make it easier for employees to submit their opinions. For example, the opinion collection unit can install a physical suggestion box in a conspicuous location in the office. The opinion collection unit can also allow employees to submit their opinions via the internet using an online form. The Opinion Analysis Department analyzes the opinions collected by the Opinion Collection Department. For example, the Opinion Analysis Department uses AI to analyze opinions collected from open-ended questions and anonymous suggestion boxes, extracting important information. For instance, the Opinion Analysis Department classifies employee complaints and requests, identifying frequently occurring problems. The Opinion Analysis Department can also analyze the content of opinions using text mining technology. For example, the Opinion Analysis Department uses text mining technology to extract keywords from opinions and understand trends. The Results Aggregation Department aggregates the results based on the opinions analyzed by the Opinion Analysis Department. For example, the Results Aggregation Department uses AI to aggregate the results based on the aggregated opinions and create reports. For instance, the Results Aggregation Department analyzes the collected opinions, extracts important information, and automatically creates reports. The Results Aggregation Department can also visually display the aggregated results as graphs and charts. For example, the Results Aggregation Department displays the aggregated results as graphs and charts, allowing organizational leaders to understand the organization's status in real time. The Solution Presentation Department presents solutions based on the results aggregated by the Results Aggregation Department. The solution proposal department, for example, uses AI to propose improvement measures based on collected opinions and presents them to the organizational leader.For example, the solution proposal unit proposes specific improvement measures based on the collected opinions and presents them to the organizational head. The solution proposal unit can also monitor the implementation status of the improvement measures and propose additional improvements as needed. For instance, if the improvement is not progressing, the solution proposal unit can monitor the implementation status and propose additional improvements. In this way, the employee satisfaction survey system according to this embodiment can promote organizational improvement by gaining a detailed understanding of employee satisfaction and proposing appropriate solutions.

[0030] The question addition section allows for the addition of open-ended questions. For example, it can be used to add open-ended questions to a monthly EN survey, allowing employees to freely express their opinions. Specifically, the question addition section allows for flexible question formatting to enable employees to freely express their opinions and feelings. For example, it can offer formats such as open-ended, short-answer, and long-answer responses. This allows employees to describe their thoughts and feelings in detail, providing more specific feedback. Furthermore, the question addition section can be designed to elicit employee opinions by carefully considering the content and format of the questions. For example, it can add questions that encourage employees to specifically describe problems and areas for improvement they perceive. In addition, the question addition section can be designed to make it easier for employees to write their opinions by carefully considering the order and layout of the questions. For example, it can arrange the questions in a way that allows employees to write their opinions in a relaxed manner and provide an easy-to-answer layout. This allows the question addition section to collect employee opinions in detail and improve the accuracy of employee satisfaction surveys.

[0031] The opinion collection department collects employee opinions. For example, the opinion collection department can install an anonymous suggestion box where employees can submit their opinions at any time, allowing them to post complaints and requests anonymously. Specifically, the opinion collection department can place a physical suggestion box in a prominent location within the office. This makes it easy for employees to submit their opinions. The opinion collection department can also use an online form to allow employees to submit their opinions via the internet. The online form is designed to allow employees to submit their opinions anonymously, thus protecting their privacy. Furthermore, the opinion collection department can devise ways to place and install the suggestion box to make it easier for employees to submit their opinions. For example, the opinion collection department can place suggestion boxes in multiple locations within the office, allowing employees to submit their opinions from anywhere. The opinion collection department can also regularly review the placement of the suggestion boxes to create an environment that facilitates the collection of employee opinions. In this way, the opinion collection department can efficiently collect employee opinions and improve the accuracy of employee satisfaction surveys.

[0032] The Opinion Analysis Department analyzes the opinions collected by the Opinion Collection Department. For example, the Opinion Analysis Department uses AI to analyze opinions collected from open-ended questions and anonymous suggestion boxes, extracting important information. Specifically, the Opinion Analysis Department can use natural language processing technology to analyze employee opinions and classify their content. For instance, it can categorize employee complaints and requests to identify frequently occurring problems. Furthermore, the Opinion Analysis Department can use text mining technology to extract keywords from opinions and understand trends. For example, it can extract keywords such as "salary," "work environment," and "relationship with superiors" from employee opinions and understand trends in opinions related to these keywords. In addition, the Opinion Analysis Department can use AI to perform sentiment analysis of employee opinions. For example, it can classify positive and negative opinions from employee feedback to understand trends in employee satisfaction. This allows the Opinion Analysis Department to analyze employee opinions in detail and improve the accuracy of employee satisfaction surveys.

[0033] The results aggregation unit aggregates results based on the opinions analyzed by the opinion analysis unit. The results aggregation unit can, for example, use AI to aggregate the aggregated opinions and create reports. Specifically, the results aggregation unit can analyze the collected opinions, extract important information, and automatically create reports. For example, the results aggregation unit can aggregate employee opinions by category and understand the trends in opinions within each category. Furthermore, the results aggregation unit can visually display the aggregated results as graphs and charts. For example, the results aggregation unit can display the aggregated results as graphs and charts, allowing organizational leaders to understand the state of the organization in real time. In addition, the results aggregation unit can understand fluctuations in employee satisfaction by comparing current results with past data. For example, the results aggregation unit can compare the results of past employee satisfaction surveys with current results to understand fluctuations in employee satisfaction. This allows the results aggregation unit to understand trends in employee satisfaction and use this information to improve the organization.

[0034] The Solution Proposal Department proposes solutions based on the results compiled by the Results Aggregation Department. For example, the Solution Proposal Department uses AI to propose improvement measures based on the collected opinions and presents them to the organizational leader. Specifically, the Solution Proposal Department can analyze employee opinions and propose specific improvement measures. For example, it can propose improvement measures such as "salary review," "improvement of working environment," and "strengthening communication with superiors" from among employee opinions and present them to the organizational leader. The Solution Proposal Department can also monitor the implementation status of improvement measures and propose additional improvement measures as needed. For example, it can monitor the implementation status of improvement measures and propose additional improvement measures if progress has not been made. Furthermore, the Solution Proposal Department can evaluate the effectiveness of improvement measures and revise them as needed. For example, it can conduct an employee satisfaction survey after the implementation of improvement measures to evaluate their effectiveness and revise them as needed. In this way, the Solution Proposal Department can propose specific improvement measures aimed at improving employee satisfaction and promote organizational improvement.

[0035] The opinion collection department will install an anonymous suggestion box so that employees can submit their opinions anonymously. The opinion collection department may, for example, install a physical anonymous suggestion box in a conspicuous location within the office. Alternatively, the opinion collection department may use an online form so that employees can submit their opinions anonymously via the internet. For example, the opinion collection department may install an online form so that employees can submit their opinions anonymously. This allows for the collection of frank opinions because employees can submit their opinions anonymously. The methods for installing and operating the anonymous suggestion box include, but are not limited to, physical boxes or online forms. Some or all of the above-described processes in the opinion collection department may be performed using, for example, AI, or not using AI. For example, the opinion collection department may input the opinions collected through the online form into a generating AI and have the generating AI classify and analyze the opinions.

[0036] The results aggregation department compiles results based on opinions collected from an annual survey and suggestion boxes. For example, the results aggregation department conducts a large-scale annual survey to broadly collect employee opinions. The results aggregation department also installs an anonymous suggestion box where employees can submit their opinions at any time, allowing them to post their opinions on a daily basis. For example, the results aggregation department conducts an annual survey to broadly collect employee opinions. This allows for the compilation of detailed results based on the opinions from the annual survey and suggestion boxes. The specific content and implementation method of the annual survey include, but are not limited to, the questions, answer format, and timing. Some or all of the above processing in the results aggregation department may be performed using, for example, AI, or not using AI. For example, the results aggregation department can input opinions collected from the survey and suggestion boxes into a generating AI and have the generating AI perform opinion aggregation and analysis.

[0037] The solution proposal unit proposes improvement measures based on opinions collected using AI. For example, the solution proposal unit uses AI to propose improvement measures based on collected opinions and presents them to the organizational leader. For example, the solution proposal unit proposes specific improvement measures based on collected opinions and presents them to the organizational leader. The solution proposal unit can also monitor the implementation status of the improvement measures and propose additional improvement measures as needed. For example, the solution proposal unit monitors the implementation status of the improvement measures and proposes additional improvement measures if progress has not been made. This allows for the rapid proposal of appropriate improvement measures by using AI. Specific AI technologies and algorithms include, but are not limited to, machine learning, natural language processing, and deep learning. Some or all of the above-described processes in the solution proposal unit may be performed using AI or not. For example, the solution proposal unit can input collected opinions into a generating AI and have the generating AI execute the proposal of improvement measures.

[0038] The Opinion Analysis Department classifies employee complaints and requests and identifies frequently occurring problems. For example, the Opinion Analysis Department uses AI to analyze opinions collected from open-ended questions and anonymous suggestion boxes, extracting important information. The Opinion Analysis Department can also analyze the content of opinions using text mining techniques. For example, the Opinion Analysis Department uses text mining techniques to extract keywords from opinions and understand trends. This allows for the identification of frequently occurring problems, thereby clarifying areas for organizational improvement. Specific criteria and methods for classification include, but are not limited to, categorization, tagging, and clustering. Some or all of the above-described processes in the Opinion Analysis Department may be performed using AI, or not. For example, the Opinion Analysis Department can input collected opinions into a generating AI and have the generating AI perform the classification and analysis of the opinions.

[0039] The results aggregation unit automatically generates reports for reporting. For example, the results aggregation unit uses AI to aggregate results based on collected opinions and generate reports. For example, the results aggregation unit analyzes collected opinions, extracts important information, and automatically generates reports. The results aggregation unit can also visually display the aggregated results as graphs and charts. For example, the results aggregation unit displays the aggregated results as graphs and charts, allowing organizational leaders to understand the organization's status in real time. This enables organizational leaders to understand the organization's status in real time by automatically generating reports. The specific content and format of the reports include, but are not limited to, text reports, graphs, and dashboards. Some or all of the above-described processes in the results aggregation unit may be performed using, for example, AI, or not using AI. For example, the results aggregation unit can input collected opinions into a generating AI and have the generating AI create the report.

[0040] The question addition unit analyzes past survey results and dynamically generates questions based on frequently occurring issues. For example, the question addition unit uses AI to analyze past survey results and dynamically generate questions based on frequently occurring issues. For instance, the question addition unit automatically generates relevant questions based on frequently occurring issues in past surveys. The question addition unit can also add questions on specific themes based on past survey results. Furthermore, the question addition unit can improve questions by incorporating feedback obtained from past surveys. This allows for the provision of more relevant questions by generating questions based on past survey results. Specific examples of past survey results and analysis methods include, but are not limited to, response data, statistical analysis, and trend analysis. Some or all of the above-described processes in the question addition unit may be performed using, for example, AI, or without AI. For example, the question addition unit can input past survey results into a generation AI and have the generation AI perform the question generation.

[0041] The question addition unit presents different questions depending on the employee's position and department when adding questions. For example, the question addition unit might use AI to present different questions depending on the employee's position and department. For instance, it might provide strategic questions to management and questions related to daily operations to general employees. The question addition unit can also provide questions tailored to the specific work content of each department. Furthermore, it can provide customized questions based on combinations of position and department. This allows for the collection of more appropriate opinions by providing questions tailored to each position and department. Specific classification methods and criteria for positions and departments include, but are not limited to, management, technical departments, and sales departments. Some or all of the above-described processes in the question addition unit may be performed using, for example, AI, or without AI. For example, the question addition unit can input employee position and department information into a generating AI and have the generating AI generate questions.

[0042] The question addition unit customizes questions according to the employee's working hours and work style when adding questions. For example, the question addition unit can use AI to customize questions according to the employee's working hours and work style when adding questions. For example, the question addition unit can provide employees on night shifts with questions about nighttime work. It can also provide employees working remotely with questions about working from home. Furthermore, it can provide employees on a flextime system with questions about flexible working hours. By providing questions tailored to working hours and work styles, more appropriate opinions can be collected. Specific classification methods and criteria for working hours and work styles include, but are not limited to, full-time, part-time, and shift work. Some or all of the above processing in the question addition unit may be performed using, for example, AI, or without AI. For example, the question addition unit can input information about the employee's working hours and work style into a generating AI and have the generating AI perform the question customization.

[0043] The question addition unit personalizes questions by referencing the employee's past response history when adding a question. For example, the question addition unit may use AI to personalize questions by referencing the employee's past response history when adding a question. For instance, the question addition unit may prioritize questions related to specific themes based on past response history. Furthermore, the question addition unit can provide questions tailored to the employee's interests based on past response history. It can also analyze past response history and provide questions tailored to the employee's needs. This allows for the collection of more relevant opinions by personalizing questions based on past response history. Specific examples of past response history and methods of reference include, but are not limited to, response databases and history management systems. Some or all of the above-described processes in the question addition unit may be performed using, for example, AI, or without AI. For example, the question addition unit may input the employee's past response history into a generating AI and have the generating AI perform question personalization.

[0044] The opinion collection department analyzes employees' past opinion submission history and selects the optimal collection method when collecting opinions. For example, the opinion collection department may use AI to analyze employees' past opinion submission history and select the optimal collection method. For instance, the opinion collection department may select a collection method preferred by employees based on their past opinion submission history. Furthermore, the opinion collection department can select the method that makes it easiest for employees to submit their opinions based on their past opinion submission history. The opinion collection department can also analyze past opinion submission history and select a collection method that meets employee needs. This allows for more effective opinion collection by selecting the optimal collection method based on past opinion submission history. Specific selection criteria and methods for the optimal collection method include, but are not limited to, online forms, interviews, and group discussions. Some or all of the above-described processes in the opinion collection department may be performed using AI, or not. For example, the opinion collection department may input employees' past opinion submission history into a generating AI and have the generating AI select the collection method.

[0045] The opinion collection unit filters opinions based on the employee's current projects and areas of interest. For example, the opinion collection unit may use AI to filter opinions based on the employee's current projects and areas of interest. For instance, the opinion collection unit may prioritize collecting opinions related to the current project. The opinion collection unit can also collect relevant opinions based on the employee's areas of interest. Furthermore, the opinion collection unit can adjust the timing of opinion collection according to the progress of the current project. This allows for the collection of more relevant opinions by filtering them based on the current project and areas of interest. Specific methods and criteria for identifying current projects and areas of interest include, but are not limited to, project management tools and surveys on areas of interest. Some or all of the above processing in the opinion collection unit may be performed using, for example, AI, or not. For example, the opinion collection unit may input information on the employee's current projects and areas of interest into a generating AI and have the generating AI perform the filtering of opinions.

[0046] The opinion collection department prioritizes collecting highly relevant opinions by considering the geographical location information of employees during opinion collection. For example, the opinion collection department may use AI to prioritize collecting highly relevant opinions by considering the geographical location information of employees during opinion collection. For example, the opinion collection department may prioritize collecting opinions related to specific areas within the office based on geographical location information. Furthermore, the opinion collection department can prioritize collecting opinions from remote workers based on geographical location information. The opinion collection department can also prioritize collecting opinions related to specific regions based on geographical location information. This allows for the collection of more appropriate opinions by prioritizing highly relevant opinions based on geographical location information. Specific methods for acquiring and using geographical location information include, but are not limited to, GPS data and address information. Some or all of the above-described processes in the opinion collection department may be performed using, for example, AI, or without AI. For example, the opinion collection department may input employee geographical location information into a generating AI and have the generating AI collect opinions.

[0047] The opinion collection department analyzes employees' social media activity and collects relevant opinions during the opinion collection process. For example, the opinion collection department may use AI to analyze employees' social media activity and collect relevant opinions during the opinion collection process. For example, the opinion collection department may collect opinions related to employees' areas of interest based on their social media activity. The opinion collection department can also collect employee complaints and requests based on their social media activity. Furthermore, the opinion collection department can analyze social media activity and collect opinions that meet employee needs. This allows for the collection of opinions that meet employee needs by collecting relevant opinions based on social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, post content, follower count, and engagement rate. Some or all of the above-described processes in the opinion collection department may be performed using AI, or not. For example, the opinion collection department may input employee social media activity data into a generating AI and have the generating AI collect opinions.

[0048] The opinion analysis unit applies different analysis algorithms depending on the employee's position and department during opinion analysis. For example, the opinion analysis unit can use AI to apply different analysis algorithms depending on the employee's position and department during opinion analysis. For example, the opinion analysis unit can apply a strategic analysis algorithm to management personnel depending on their position. The opinion analysis unit can also apply analysis algorithms tailored to the different work content of each department. Furthermore, the opinion analysis unit can apply customized analysis algorithms based on the combination of position and department. This allows for more accurate analysis by applying analysis algorithms tailored to position and department. Specific types of analysis algorithms and application methods include, but are not limited to, machine learning algorithms and statistical models. Some or all of the above-described processes in the opinion analysis unit may be performed using AI, for example, or without AI. For example, the opinion analysis unit can input employee position and department information into a generating AI and have the generating AI execute the application of analysis algorithms.

[0049] The opinion analysis unit improves the accuracy of its analysis by referring to the employee's past opinion submission history during opinion analysis. The opinion analysis unit uses, for example, AI to improve the accuracy of its analysis by referring to the employee's past opinion submission history during opinion analysis. For example, the opinion analysis unit analyzes employee opinions more accurately based on past opinion submission history. The opinion analysis unit can also analyze past opinion submission history to identify frequently occurring problems. Furthermore, the opinion analysis unit can refer to past opinion submission history and perform analysis tailored to the employee's needs. This allows for more accurate analysis by performing analysis based on past opinion submission history. Specific methods and criteria for improving analysis accuracy include, but are not limited to, data quality, algorithm accuracy, and evaluation metrics. Some or all of the above-described processes in the opinion analysis unit may be performed using, for example, AI, or without AI. For example, the opinion analysis unit can input the employee's past opinion submission history into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0050] The opinion analysis unit considers the geographical location information of employees when analyzing opinions. The opinion analysis unit uses, for example, AI to consider the geographical location information of employees when analyzing opinions. For example, the opinion analysis unit analyzes opinions about a specific area within the office based on geographical location information. The opinion analysis unit can also analyze opinions from remote workers based on geographical location information. Furthermore, the opinion analysis unit can analyze opinions related to a specific region based on geographical location information. This allows for more relevant analysis by performing analysis based on geographical location information. Specific methods for acquiring and using geographical location information include, but are not limited to, GPS data and address information. Some or all of the above-described processes in the opinion analysis unit may be performed using, for example, AI, or without AI. For example, the opinion analysis unit can input the geographical location information of employees into a generating AI and have the generating AI perform the analysis.

[0051] The opinion analysis unit improves the accuracy of its analysis by referring to relevant literature on employees during opinion analysis. The opinion analysis unit uses, for example, AI to improve the accuracy of its analysis by referring to relevant literature on employees during opinion analysis. For example, the opinion analysis unit analyzes employees' opinions more accurately based on relevant literature. The opinion analysis unit can also classify employees' opinions by referring to relevant literature. Furthermore, the opinion analysis unit can analyze employees' opinions based on relevant literature and identify frequently occurring problems. As a result, more accurate analysis can be performed by performing analysis based on relevant literature. Specific methods of referring to and using relevant literature include, but are not limited to, academic papers, technical reports, and industry reports. Some or all of the above processing in the opinion analysis unit may be performed using, for example, AI, or not using AI. For example, the opinion analysis unit can input employees' relevant literature into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0052] The results aggregation unit applies different aggregation algorithms depending on the employee's position and department when aggregating results. For example, the results aggregation unit can use AI to apply different aggregation algorithms depending on the employee's position and department when aggregating results. For example, the results aggregation unit can apply a strategic aggregation algorithm to management-level employees depending on their position. The results aggregation unit can also apply aggregation algorithms tailored to the different work content of each department. Furthermore, the results aggregation unit can apply a customized aggregation algorithm based on the combination of position and department. This allows for more accurate aggregation by applying aggregation algorithms tailored to position and department. Specific types and application methods of aggregation algorithms include, but are not limited to, weighted average, median, and mode. Some or all of the above processing in the results aggregation unit may be performed using, for example, AI, or without AI. For example, the results aggregation unit can input employee position and department information into a generating AI and have the generating AI execute the application of the aggregation algorithm.

[0053] The results aggregation unit improves the accuracy of the aggregation by referring to the employee's past opinion submission history when aggregating results. The results aggregation unit can, for example, use AI to improve the accuracy of the aggregation by referring to the employee's past opinion submission history when aggregating results. For example, the results aggregation unit aggregates employee opinions more accurately based on past opinion submission history. The results aggregation unit can also analyze past opinion submission history and identify frequently occurring problems. Furthermore, the results aggregation unit can refer to past opinion submission history and perform aggregation according to the employee's needs. This allows for more accurate aggregation by performing aggregation based on past opinion submission history. Specific methods and criteria for improving aggregation accuracy include, but are not limited to, data quality, algorithm accuracy, and evaluation indicators. Some or all of the above processing in the results aggregation unit may be performed using, for example, AI, or without AI. For example, the results aggregation unit can input the employee's past opinion submission history into a generating AI and have the generating AI perform the aggregation accuracy improvement.

[0054] The results aggregation unit considers the geographical location information of employees when aggregating results. The results aggregation unit uses, for example, AI to consider the geographical location information of employees when aggregating results. For example, the results aggregation unit aggregates opinions on specific areas within the office based on geographical location information. The results aggregation unit can also aggregate opinions from remote workers based on geographical location information. Furthermore, the results aggregation unit can aggregate opinions related to specific regions based on geographical location information. This allows for more relevant aggregation by performing aggregation based on geographical location information. Specific methods for acquiring and using geographical location information include, but are not limited to, GPS data and address information. Some or all of the above processing in the results aggregation unit may be performed using, for example, AI, or without AI. For example, the results aggregation unit can input the geographical location information of employees into a generating AI and have the generating AI perform the aggregation.

[0055] The results aggregation unit improves the accuracy of its aggregations by referring to relevant literature related to employees during the aggregation process. The results aggregation unit can, for example, use AI to improve the accuracy of its aggregations by referring to relevant literature related to employees during the aggregation process. For example, the results aggregation unit can more accurately aggregate employee opinions based on relevant literature. The results aggregation unit can also classify employee opinions by referring to relevant literature. Furthermore, the results aggregation unit can aggregate employee opinions based on relevant literature and identify frequently occurring problems. As a result, more accurate aggregations can be performed by basing the aggregation on relevant literature. Specific methods of referencing and using relevant literature include, but are not limited to, academic papers, technical reports, and industry reports. Some or all of the above-described processes in the results aggregation unit may be performed using, for example, AI, or not using AI. For example, the results aggregation unit can input employee relevant literature into a generating AI and have the generating AI perform the task of improving the accuracy of the aggregation.

[0056] The solution presentation unit presents different solutions depending on the employee's position and department. For example, the solution presentation unit uses AI to present different solutions depending on the employee's position and department. For instance, the solution presentation unit presents strategic solutions to management based on their position. Furthermore, the solution presentation unit can present solutions tailored to the different work content of each department. It can also present customized solutions based on combinations of position and department. This allows for the presentation of more appropriate solutions by providing solutions tailored to each position and department. The specific content and presentation methods of the solutions include, but are not limited to, improvement suggestions, action plans, and recommendations. Some or all of the above-described processes in the solution presentation unit may be performed using, for example, AI, or without AI. For example, the solution presentation unit can input employee position and department information into a generating AI and have the generating AI perform the solution presentation.

[0057] The solution presentation unit improves the accuracy of solutions by referring to the employee's past feedback history when presenting solutions. For example, the solution presentation unit uses AI to improve the accuracy of solutions by referring to the employee's past feedback history when presenting solutions. For example, the solution presentation unit presents solutions that reflect the employee's opinions based on past feedback history. The solution presentation unit can also analyze past feedback history and present solutions to frequently occurring problems. Furthermore, the solution presentation unit can refer to past feedback history and present solutions that meet the employee's needs. This allows for the provision of more appropriate solutions by presenting solutions based on past feedback history. Specific methods and criteria for improving the accuracy of solutions include, but are not limited to, data quality, algorithm accuracy, and evaluation metrics. Some or all of the above-described processes in the solution presentation unit may be performed using, for example, AI, or without AI. For example, the solution presentation unit can input the employee's past feedback history into a generating AI and have the generating AI perform the improvement of solution accuracy.

[0058] The solution presentation unit presents the optimal solution when considering the employee's geographical location information. For example, the solution presentation unit may use AI to present the optimal solution when considering the employee's geographical location information. For example, the solution presentation unit may present a solution for a specific area within the office based on geographical location information. Furthermore, the solution presentation unit can present solutions for remote workers based on geographical location information. It can also present solutions related to specific regions based on geographical location information. This allows for the provision of more appropriate solutions by presenting solutions based on geographical location information. Specific methods for acquiring and using geographical location information include, but are not limited to, GPS data and address information. Some or all of the above-described processes in the solution presentation unit may be performed using, for example, AI, or without AI. For example, the solution presentation unit may input the employee's geographical location information into a generating AI and have the generating AI perform the solution presentation.

[0059] The solution-providing unit analyzes employees' social media activity and proposes solutions when presenting solutions. The solution-providing unit may, for example, use AI to analyze employees' social media activity and propose solutions when presenting solutions. For example, the solution-providing unit may present solutions related to employees' areas of interest based on their social media activity. The solution-providing unit can also present solutions to employees' complaints and requests based on their social media activity. Furthermore, the solution-providing unit can analyze social media activity and present solutions tailored to employees' needs. In this way, by presenting solutions based on social media activity, solutions tailored to employees' needs can be provided. Specific methods and criteria for analyzing social media activity include, but are not limited to, post content, follower count, and engagement rate. Some or all of the above-described processes in the solution-providing unit may be performed using, for example, AI, or not using AI. For example, the solution-providing unit may input employee social media activity data into a generating AI and have the generating AI execute solution proposals.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The employee satisfaction survey system can adjust the method of collecting employee opinions according to the employee's working hours and work style. For example, night shift employees can be provided with a special questionnaire to collect opinions on nighttime work. Remote workers can be provided with an online form to collect opinions on working from home. Furthermore, employees on a flexible working hours system can be provided with a questionnaire to collect opinions on flexible working hours. This allows for the collection of more relevant opinions by gathering opinions tailored to the employee's working hours and work style. The opinion collection unit can select the optimal opinion collection method based on information about the employee's working hours and work style. For example, information about the employee's working hours and work style can be input into a generating AI, and the generating AI can then select the opinion collection method.

[0062] The employee satisfaction survey system can adjust its opinion collection methods based on employees' current projects and areas of interest. For example, it can provide questionnaires that prioritize collecting opinions related to current projects. It can also provide special questionnaires to collect relevant opinions based on employees' areas of interest. Furthermore, it can adjust the timing of opinion collection according to the progress of current projects. This allows for the collection of more relevant opinions by collecting opinions based on current projects and areas of interest. The opinion collection unit can select the optimal opinion collection method based on information about employees' current projects and areas of interest. For example, information about employees' current projects and areas of interest can be input into a generating AI, and the generating AI can then select the opinion collection method.

[0063] The employee satisfaction survey system can adjust its opinion collection methods by considering employees' geographical location when gathering employee feedback. For example, it can provide a questionnaire that prioritizes collecting feedback on specific areas within the office. It can also provide an online form that prioritizes collecting feedback from remote workers. Furthermore, it can provide a questionnaire that prioritizes collecting feedback related to specific regions. By collecting feedback based on geographical location, it is possible to collect more relevant opinions. The feedback collection unit can select the optimal feedback collection method based on employees' geographical location information. For example, employees' geographical location information can be input into a generating AI, and the AI ​​can then select the appropriate feedback collection method.

[0064] The employee satisfaction survey system can collect employee opinions by analyzing their social media activity and gathering relevant feedback. For example, it can provide questionnaires to collect opinions related to employees' areas of interest based on their social media activity. It can also provide online forms to collect opinions on employee complaints and requests based on their social media activity. Furthermore, it can provide questionnaires to collect opinions tailored to employee needs by analyzing social media activity. This allows for the collection of opinions that meet employee needs by collecting feedback based on social media activity. The feedback collection unit can select the optimal feedback collection method based on employee social media activity data. For example, employee social media activity data can be input into a generating AI, and the generating AI can then select the feedback collection method.

[0065] The employee satisfaction survey system can analyze employees' past feedback history to select the most suitable feedback collection method. For example, it can select the feedback collection method preferred by employees based on their past feedback history. It can also select the method that employees find easiest to submit feedback to, based on their past feedback history. Furthermore, it can analyze past feedback history to select a feedback collection method that meets employee needs. This allows for more effective feedback collection by selecting the most suitable method based on past feedback history. The feedback collection unit can select the most suitable feedback collection method based on employees' past feedback history. For example, employees' past feedback history can be input into a generating AI, which can then perform the selection of the feedback collection method.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The question addition section allows you to add open-ended questions. For example, you can add open-ended questions to a monthly EN survey to allow employees to freely write their opinions. The question addition section can also be configured to accept various formats such as open-ended, short-answer, and long-answer responses. Step 2: The feedback department collects employee feedback. For example, they could install an anonymous suggestion box where employees can submit their complaints and requests anonymously. Alternatively, the feedback department could place a physical suggestion box in a prominent location within the office, or allow employees to submit feedback via the internet using an online form. Step 3: The Opinion Analysis Department analyzes the opinions collected by the Opinion Collection Department. For example, it uses AI to analyze opinions collected from open-ended questions and anonymous suggestion boxes, and extracts important information. The Opinion Analysis Department classifies employee complaints and requests and identifies frequently occurring problems. It also uses text mining technology to analyze the content of opinions, extract keywords, and understand trends in the opinions. Step 4: The results aggregation unit aggregates the results based on the opinions analyzed by the opinion analysis unit. For example, it aggregates the results based on opinions gathered using AI and creates a report for reporting. The results aggregation unit visually displays the aggregated results as graphs and charts, allowing organizational leaders to understand the state of the organization in real time. Step 5: The Solution Proposal Unit proposes solutions based on the results compiled by the Results Aggregation Unit. For example, it proposes improvement measures based on opinions collected using AI and presents them to the organizational head. The Solution Proposal Unit can also monitor the implementation status of the improvement measures and propose additional improvement measures as needed.

[0068] (Example of form 2) The employee satisfaction survey system according to an embodiment of the present invention is a system for measuring and surveying employee satisfaction. This system collects employee opinions, has AI analyze the results and summarize them, and proposes solutions, thereby enabling real-time understanding of the organization's state and promoting improvement. The employee satisfaction survey system collects employee opinions by adding open-ended questions and an anonymous suggestion box. Next, the AI ​​analyzes the collected opinions and summarizes the results. Furthermore, by increasing the frequency of collection and aggregating employee opinions through an annual survey and the installation of a suggestion box, the AI ​​aggregates the results based on the aggregated opinions and creates a report for reporting. Finally, the AI ​​even proposes solutions, creating a state where continuous improvement can be achieved without burden. This mechanism makes it easier for employee voices to be reflected in the internal environment, reducing the burden on departmental and organizational HR. For example, the employee satisfaction survey system adds open-ended questions to the monthly EN survey, allowing employees to freely write their opinions. In addition, an anonymous suggestion box is installed where employees can always submit their opinions, allowing them to anonymously post complaints and requests. This makes it possible to collect the genuine voices of employees in real time. Next, the AI ​​analyzes the collected opinions and summarizes the results. The AI ​​analyzes opinions collected from open-ended questions and anonymous suggestion boxes, extracting important information. For example, it categorizes employee complaints and requests and identifies frequently occurring problems. This allows for a detailed understanding of the organization's state. Furthermore, the frequency of collection is increased, and employee opinions are aggregated through annual surveys and the installation of suggestion boxes. For example, a large-scale survey is conducted once a year to collect a wide range of employee opinions. In addition, an anonymous suggestion box is installed where employees can submit their opinions at any time, allowing for the continuous collection of employee opinions. Based on the aggregated opinions, the AI ​​summarizes the results and creates a report. For example, the AI ​​analyzes the collected opinions, extracts important information, and automatically creates a report. This allows the organization leader to understand the organization's state in real time. Finally, the AI ​​even proposes solutions, creating a system where continuous improvement is possible without burden. For example, the AI ​​proposes improvement measures based on the collected opinions and presents them to the organization leader.This allows organizations to quickly implement improvements and increase employee satisfaction. This system makes it easier for employee feedback to be reflected in the work environment, reducing the burden on departmental and organizational HR departments. For example, employee dissatisfaction and requests are quickly identified and addressed appropriately, leading to increased employee satisfaction. Furthermore, the AI ​​automatically compiles results and generates reports, reducing the burden on HR departments. This improves overall organizational efficiency and increases employee satisfaction. Thus, the employee satisfaction survey system can facilitate organizational improvement by gaining a detailed understanding of employee opinions and suggesting appropriate solutions.

[0069] The employee satisfaction survey system according to this embodiment comprises a question addition unit, an opinion collection unit, an opinion analysis unit, a results aggregation unit, and a solution presentation unit. The question addition unit adds open-ended questions. For example, the question addition unit adds open-ended questions to a monthly EN survey, allowing employees to freely express their opinions. The question addition unit can also flexibly set the format of the questions to allow employees to freely express their opinions. For example, the question addition unit can set formats such as open-ended, short-answer, and long-answer. The opinion collection unit collects employee opinions. For example, the opinion collection unit can install an anonymous suggestion box where employees can always submit their opinions, allowing them to anonymously post complaints and requests. The opinion collection unit can also devise a location and method for installing the suggestion box to make it easier for employees to submit their opinions. For example, the opinion collection unit can install a physical suggestion box in a conspicuous location in the office. The opinion collection unit can also allow employees to submit their opinions via the internet using an online form. The Opinion Analysis Department analyzes the opinions collected by the Opinion Collection Department. For example, the Opinion Analysis Department uses AI to analyze opinions collected from open-ended questions and anonymous suggestion boxes, extracting important information. For instance, the Opinion Analysis Department classifies employee complaints and requests, identifying frequently occurring problems. The Opinion Analysis Department can also analyze the content of opinions using text mining technology. For example, the Opinion Analysis Department uses text mining technology to extract keywords from opinions and understand trends. The Results Aggregation Department aggregates the results based on the opinions analyzed by the Opinion Analysis Department. For example, the Results Aggregation Department uses AI to aggregate the results based on the aggregated opinions and create reports. For instance, the Results Aggregation Department analyzes the collected opinions, extracts important information, and automatically creates reports. The Results Aggregation Department can also visually display the aggregated results as graphs and charts. For example, the Results Aggregation Department displays the aggregated results as graphs and charts, allowing organizational leaders to understand the organization's status in real time. The Solution Presentation Department presents solutions based on the results aggregated by the Results Aggregation Department. The solution proposal department, for example, uses AI to propose improvement measures based on collected opinions and presents them to the organizational leader.For example, the solution proposal unit proposes specific improvement measures based on the collected opinions and presents them to the organizational head. The solution proposal unit can also monitor the implementation status of the improvement measures and propose additional improvements as needed. For instance, if the improvement is not progressing, the solution proposal unit can monitor the implementation status and propose additional improvements. In this way, the employee satisfaction survey system according to this embodiment can promote organizational improvement by gaining a detailed understanding of employee satisfaction and proposing appropriate solutions.

[0070] The question addition section allows for the addition of open-ended questions. For example, it can be used to add open-ended questions to a monthly EN survey, allowing employees to freely express their opinions. Specifically, the question addition section allows for flexible question formatting to enable employees to freely express their opinions and feelings. For example, it can offer formats such as open-ended, short-answer, and long-answer responses. This allows employees to describe their thoughts and feelings in detail, providing more specific feedback. Furthermore, the question addition section can be designed to elicit employee opinions by carefully considering the content and format of the questions. For example, it can add questions that encourage employees to specifically describe problems and areas for improvement they perceive. In addition, the question addition section can be designed to make it easier for employees to write their opinions by carefully considering the order and layout of the questions. For example, it can arrange the questions in a way that allows employees to write their opinions in a relaxed manner and provide an easy-to-answer layout. This allows the question addition section to collect employee opinions in detail and improve the accuracy of employee satisfaction surveys.

[0071] The opinion collection department collects employee opinions. For example, the opinion collection department can install an anonymous suggestion box where employees can submit their opinions at any time, allowing them to post complaints and requests anonymously. Specifically, the opinion collection department can place a physical suggestion box in a prominent location within the office. This makes it easy for employees to submit their opinions. The opinion collection department can also use an online form to allow employees to submit their opinions via the internet. The online form is designed to allow employees to submit their opinions anonymously, thus protecting their privacy. Furthermore, the opinion collection department can devise ways to place and install the suggestion box to make it easier for employees to submit their opinions. For example, the opinion collection department can place suggestion boxes in multiple locations within the office, allowing employees to submit their opinions from anywhere. The opinion collection department can also regularly review the placement of the suggestion boxes to create an environment that facilitates the collection of employee opinions. In this way, the opinion collection department can efficiently collect employee opinions and improve the accuracy of employee satisfaction surveys.

[0072] The Opinion Analysis Department analyzes the opinions collected by the Opinion Collection Department. For example, the Opinion Analysis Department uses AI to analyze opinions collected from open-ended questions and anonymous suggestion boxes, extracting important information. Specifically, the Opinion Analysis Department can use natural language processing technology to analyze employee opinions and classify their content. For instance, it can categorize employee complaints and requests to identify frequently occurring problems. Furthermore, the Opinion Analysis Department can use text mining technology to extract keywords from opinions and understand trends. For example, it can extract keywords such as "salary," "work environment," and "relationship with superiors" from employee opinions and understand trends in opinions related to these keywords. In addition, the Opinion Analysis Department can use AI to perform sentiment analysis of employee opinions. For example, it can classify positive and negative opinions from employee feedback to understand trends in employee satisfaction. This allows the Opinion Analysis Department to analyze employee opinions in detail and improve the accuracy of employee satisfaction surveys.

[0073] The results aggregation unit aggregates results based on the opinions analyzed by the opinion analysis unit. The results aggregation unit can, for example, use AI to aggregate the aggregated opinions and create reports. Specifically, the results aggregation unit can analyze the collected opinions, extract important information, and automatically create reports. For example, the results aggregation unit can aggregate employee opinions by category and understand the trends in opinions within each category. Furthermore, the results aggregation unit can visually display the aggregated results as graphs and charts. For example, the results aggregation unit can display the aggregated results as graphs and charts, allowing organizational leaders to understand the state of the organization in real time. In addition, the results aggregation unit can understand fluctuations in employee satisfaction by comparing current results with past data. For example, the results aggregation unit can compare the results of past employee satisfaction surveys with current results to understand fluctuations in employee satisfaction. This allows the results aggregation unit to understand trends in employee satisfaction and use this information to improve the organization.

[0074] The Solution Proposal Department proposes solutions based on the results compiled by the Results Aggregation Department. For example, the Solution Proposal Department uses AI to propose improvement measures based on the collected opinions and presents them to the organizational leader. Specifically, the Solution Proposal Department can analyze employee opinions and propose specific improvement measures. For example, it can propose improvement measures such as "salary review," "improvement of working environment," and "strengthening communication with superiors" from among employee opinions and present them to the organizational leader. The Solution Proposal Department can also monitor the implementation status of improvement measures and propose additional improvement measures as needed. For example, it can monitor the implementation status of improvement measures and propose additional improvement measures if progress has not been made. Furthermore, the Solution Proposal Department can evaluate the effectiveness of improvement measures and revise them as needed. For example, it can conduct an employee satisfaction survey after the implementation of improvement measures to evaluate their effectiveness and revise them as needed. In this way, the Solution Proposal Department can propose specific improvement measures aimed at improving employee satisfaction and promote organizational improvement.

[0075] The opinion collection department will install an anonymous suggestion box so that employees can submit their opinions anonymously. The opinion collection department may, for example, install a physical anonymous suggestion box in a conspicuous location within the office. Alternatively, the opinion collection department may use an online form so that employees can submit their opinions anonymously via the internet. For example, the opinion collection department may install an online form so that employees can submit their opinions anonymously. This allows for the collection of frank opinions because employees can submit their opinions anonymously. The methods for installing and operating the anonymous suggestion box include, but are not limited to, physical boxes or online forms. Some or all of the above-described processes in the opinion collection department may be performed using, for example, AI, or not using AI. For example, the opinion collection department may input the opinions collected through the online form into a generating AI and have the generating AI classify and analyze the opinions.

[0076] The results aggregation department compiles results based on opinions collected from an annual survey and suggestion boxes. For example, the results aggregation department conducts a large-scale annual survey to broadly collect employee opinions. The results aggregation department also installs an anonymous suggestion box where employees can submit their opinions at any time, allowing them to post their opinions on a daily basis. For example, the results aggregation department conducts an annual survey to broadly collect employee opinions. This allows for the compilation of detailed results based on the opinions from the annual survey and suggestion boxes. The specific content and implementation method of the annual survey include, but are not limited to, the questions, answer format, and timing. Some or all of the above processing in the results aggregation department may be performed using, for example, AI, or not using AI. For example, the results aggregation department can input opinions collected from the survey and suggestion boxes into a generating AI and have the generating AI perform opinion aggregation and analysis.

[0077] The solution proposal unit proposes improvement measures based on opinions collected using AI. For example, the solution proposal unit uses AI to propose improvement measures based on collected opinions and presents them to the organizational leader. For example, the solution proposal unit proposes specific improvement measures based on collected opinions and presents them to the organizational leader. The solution proposal unit can also monitor the implementation status of the improvement measures and propose additional improvement measures as needed. For example, the solution proposal unit monitors the implementation status of the improvement measures and proposes additional improvement measures if progress has not been made. This allows for the rapid proposal of appropriate improvement measures by using AI. Specific AI technologies and algorithms include, but are not limited to, machine learning, natural language processing, and deep learning. Some or all of the above-described processes in the solution proposal unit may be performed using AI or not. For example, the solution proposal unit can input collected opinions into a generating AI and have the generating AI execute the proposal of improvement measures.

[0078] The Opinion Analysis Department classifies employee complaints and requests and identifies frequently occurring problems. For example, the Opinion Analysis Department uses AI to analyze opinions collected from open-ended questions and anonymous suggestion boxes, extracting important information. The Opinion Analysis Department can also analyze the content of opinions using text mining techniques. For example, the Opinion Analysis Department uses text mining techniques to extract keywords from opinions and understand trends. This allows for the identification of frequently occurring problems, thereby clarifying areas for organizational improvement. Specific criteria and methods for classification include, but are not limited to, categorization, tagging, and clustering. Some or all of the above-described processes in the Opinion Analysis Department may be performed using AI, or not. For example, the Opinion Analysis Department can input collected opinions into a generating AI and have the generating AI perform the classification and analysis of the opinions.

[0079] The results aggregation unit automatically generates reports for reporting. For example, the results aggregation unit uses AI to aggregate results based on collected opinions and generate reports. For example, the results aggregation unit analyzes collected opinions, extracts important information, and automatically generates reports. The results aggregation unit can also visually display the aggregated results as graphs and charts. For example, the results aggregation unit displays the aggregated results as graphs and charts, allowing organizational leaders to understand the organization's status in real time. This enables organizational leaders to understand the organization's status in real time by automatically generating reports. The specific content and format of the reports include, but are not limited to, text reports, graphs, and dashboards. Some or all of the above-described processes in the results aggregation unit may be performed using, for example, AI, or not using AI. For example, the results aggregation unit can input collected opinions into a generating AI and have the generating AI create the report.

[0080] The question addition unit estimates the user's emotions and adjusts the content and format of the questions based on the estimated emotions. For example, the question addition unit may use AI to estimate the user's emotions and adjust the content and format of the questions based on the estimated emotions. For example, if the user is stressed, the question addition unit may provide simple and short questions to reduce the burden of answering. If the user is relaxed, the question addition unit may provide detailed questions to elicit deeper opinions. If the user is in a hurry, the question addition unit may provide multiple-choice questions to allow for quick answers. By adjusting the questions according to the user's emotions, the burden of answering is reduced and more accurate opinions can be collected. Specific methods and criteria for estimating the user's emotions include, but are not limited to, sentiment analysis, facial recognition, and survey results. Some or all of the processing described above in the question addition unit may be performed using, for example, an emotion engine or generative AI, or without using an emotion engine or generative AI. For example, the question addition section can input user facial expression data into a generating AI and have the AI ​​perform emotion estimation.

[0081] The question addition unit analyzes past survey results and dynamically generates questions based on frequently occurring issues. For example, the question addition unit uses AI to analyze past survey results and dynamically generate questions based on frequently occurring issues. For instance, the question addition unit automatically generates relevant questions based on frequently occurring issues in past surveys. The question addition unit can also add questions on specific themes based on past survey results. Furthermore, the question addition unit can improve questions by incorporating feedback obtained from past surveys. This allows for the provision of more relevant questions by generating questions based on past survey results. Specific examples of past survey results and analysis methods include, but are not limited to, response data, statistical analysis, and trend analysis. Some or all of the above-described processes in the question addition unit may be performed using, for example, AI, or without AI. For example, the question addition unit can input past survey results into a generation AI and have the generation AI perform the question generation.

[0082] The question addition unit presents different questions depending on the employee's position and department when adding questions. For example, the question addition unit might use AI to present different questions depending on the employee's position and department. For instance, it might provide strategic questions to management and questions related to daily operations to general employees. The question addition unit can also provide questions tailored to the specific work content of each department. Furthermore, it can provide customized questions based on combinations of position and department. This allows for the collection of more appropriate opinions by providing questions tailored to each position and department. Specific classification methods and criteria for positions and departments include, but are not limited to, management, technical departments, and sales departments. Some or all of the above-described processes in the question addition unit may be performed using, for example, AI, or without AI. For example, the question addition unit can input employee position and department information into a generating AI and have the generating AI generate questions.

[0083] The question addition section estimates the user's emotions and adjusts the order of the questions based on the estimated emotions. For example, the question addition section may use AI to estimate the user's emotions and adjust the order of the questions based on the estimated emotions. For example, if the user is stressed, the question addition section may start with easy questions and gradually increase the difficulty. Also, if the user is relaxed, the question addition section may place important questions first. Also, if the user is in a hurry, the question addition section may place important questions first and detailed questions later. By adjusting the order of questions according to the user's emotions, the burden on the respondent is reduced and more accurate opinions can be collected. Specific methods and criteria for adjusting the order of questions include, but are not limited to, importance, relevance, and the burden on the respondent. Some or all of the above processing in the question addition section may be performed using, for example, an emotion engine or generative AI, or without using an emotion engine or generative AI. For example, the question addition section can input user facial expression data into a generating AI and have the AI ​​perform emotion estimation.

[0084] The question addition unit customizes questions according to the employee's working hours and work style when adding questions. For example, the question addition unit can use AI to customize questions according to the employee's working hours and work style when adding questions. For example, the question addition unit can provide employees on night shifts with questions about nighttime work. It can also provide employees working remotely with questions about working from home. Furthermore, it can provide employees on a flextime system with questions about flexible working hours. By providing questions tailored to working hours and work styles, more appropriate opinions can be collected. Specific classification methods and criteria for working hours and work styles include, but are not limited to, full-time, part-time, and shift work. Some or all of the above processing in the question addition unit may be performed using, for example, AI, or without AI. For example, the question addition unit can input information about the employee's working hours and work style into a generating AI and have the generating AI perform the question customization.

[0085] The question addition unit personalizes questions by referencing the employee's past response history when adding a question. For example, the question addition unit may use AI to personalize questions by referencing the employee's past response history when adding a question. For instance, the question addition unit may prioritize questions related to specific themes based on past response history. Furthermore, the question addition unit can provide questions tailored to the employee's interests based on past response history. It can also analyze past response history and provide questions tailored to the employee's needs. This allows for the collection of more relevant opinions by personalizing questions based on past response history. Specific examples of past response history and methods of reference include, but are not limited to, response databases and history management systems. Some or all of the above-described processes in the question addition unit may be performed using, for example, AI, or without AI. For example, the question addition unit may input the employee's past response history into a generating AI and have the generating AI perform question personalization.

[0086] The opinion collection unit estimates the user's emotions and adjusts the timing of opinion collection based on the estimated emotions. The opinion collection unit may use AI, for example, to estimate the user's emotions and adjust the timing of opinion collection based on the estimated emotions. For example, the opinion collection unit may collect opinions during times when the user is relaxed. The opinion collection unit may also postpone opinion collection if the user is stressed. Furthermore, the opinion collection unit may also collect opinions quickly if the user is in a hurry. By adjusting the timing of opinion collection according to the user's emotions, more appropriate opinions can be collected. Specific methods and criteria for adjusting the timing of opinion collection include, but are not limited to, regular collection or collection after an event. Some or all of the above processing in the opinion collection unit may be performed using, for example, an emotion engine or generative AI, or without using an emotion engine or generative AI. For example, the opinion collection unit may input the user's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0087] The opinion collection department analyzes employees' past opinion submission history and selects the optimal collection method when collecting opinions. For example, the opinion collection department may use AI to analyze employees' past opinion submission history and select the optimal collection method. For instance, the opinion collection department may select a collection method preferred by employees based on their past opinion submission history. Furthermore, the opinion collection department can select the method that makes it easiest for employees to submit their opinions based on their past opinion submission history. The opinion collection department can also analyze past opinion submission history and select a collection method that meets employee needs. This allows for more effective opinion collection by selecting the optimal collection method based on past opinion submission history. Specific selection criteria and methods for the optimal collection method include, but are not limited to, online forms, interviews, and group discussions. Some or all of the above-described processes in the opinion collection department may be performed using AI, or not. For example, the opinion collection department may input employees' past opinion submission history into a generating AI and have the generating AI select the collection method.

[0088] The opinion collection unit filters opinions based on the employee's current projects and areas of interest. For example, the opinion collection unit may use AI to filter opinions based on the employee's current projects and areas of interest. For instance, the opinion collection unit may prioritize collecting opinions related to the current project. The opinion collection unit can also collect relevant opinions based on the employee's areas of interest. Furthermore, the opinion collection unit can adjust the timing of opinion collection according to the progress of the current project. This allows for the collection of more relevant opinions by filtering them based on the current project and areas of interest. Specific methods and criteria for identifying current projects and areas of interest include, but are not limited to, project management tools and surveys on areas of interest. Some or all of the above processing in the opinion collection unit may be performed using, for example, AI, or not. For example, the opinion collection unit may input information on the employee's current projects and areas of interest into a generating AI and have the generating AI perform the filtering of opinions.

[0089] The opinion collection unit estimates the user's emotions and determines the priority of opinions to collect based on the estimated emotions. The opinion collection unit may use AI, for example, to estimate the user's emotions and determine the priority of opinions to collect based on the estimated emotions. For example, if the user is stressed, the opinion collection unit will prioritize collecting important opinions. Also, if the user is relaxed, the opinion collection unit may prioritize collecting detailed opinions. Also, if the user is in a hurry, the opinion collection unit may prioritize collecting concise opinions. In this way, by determining the priority of opinions according to the user's emotions, more important opinions can be collected preferentially. Specific methods and criteria for determining opinion priority include, but are not limited to, importance, urgency, and impact. Some or all of the above processing in the opinion collection unit may be performed using, for example, an emotion engine or generative AI, or without using an emotion engine or generative AI. For example, the opinion collection unit may input the user's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0090] The opinion collection department prioritizes collecting highly relevant opinions by considering the geographical location information of employees during opinion collection. For example, the opinion collection department may use AI to prioritize collecting highly relevant opinions by considering the geographical location information of employees during opinion collection. For example, the opinion collection department may prioritize collecting opinions related to specific areas within the office based on geographical location information. Furthermore, the opinion collection department can prioritize collecting opinions from remote workers based on geographical location information. The opinion collection department can also prioritize collecting opinions related to specific regions based on geographical location information. This allows for the collection of more appropriate opinions by prioritizing highly relevant opinions based on geographical location information. Specific methods for acquiring and using geographical location information include, but are not limited to, GPS data and address information. Some or all of the above-described processes in the opinion collection department may be performed using, for example, AI, or without AI. For example, the opinion collection department may input employee geographical location information into a generating AI and have the generating AI collect opinions.

[0091] The opinion collection department analyzes employees' social media activity and collects relevant opinions during the opinion collection process. For example, the opinion collection department may use AI to analyze employees' social media activity and collect relevant opinions during the opinion collection process. For example, the opinion collection department may collect opinions related to employees' areas of interest based on their social media activity. The opinion collection department can also collect employee complaints and requests based on their social media activity. Furthermore, the opinion collection department can analyze social media activity and collect opinions that meet employee needs. This allows for the collection of opinions that meet employee needs by collecting relevant opinions based on social media activity. Specific methods and criteria for analyzing social media activity include, but are not limited to, post content, follower count, and engagement rate. Some or all of the above-described processes in the opinion collection department may be performed using AI, or not. For example, the opinion collection department may input employee social media activity data into a generating AI and have the generating AI collect opinions.

[0092] The opinion analysis unit estimates the user's emotions and adjusts the opinion analysis method based on the estimated user emotions. For example, the opinion analysis unit may use AI to estimate the user's emotions and adjust the opinion analysis method based on the estimated user emotions. For example, if the user is stressed, the opinion analysis unit may apply a concise analysis method. If the user is relaxed, the opinion analysis unit may apply a detailed analysis method. If the user is in a hurry, the opinion analysis unit may apply a method that allows for rapid analysis. By adjusting the opinion analysis method according to the user's emotions, more appropriate analysis can be performed. Specific methods and criteria for adjusting the opinion analysis method include, but are not limited to, text mining, sentiment analysis, and statistical analysis. Some or all of the above-described processes in the opinion analysis unit may be performed using, for example, an emotion engine or generative AI, or without using an emotion engine or generative AI. For example, the opinion analysis unit may input the user's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0093] The opinion analysis unit applies different analysis algorithms depending on the employee's position and department during opinion analysis. For example, the opinion analysis unit can use AI to apply different analysis algorithms depending on the employee's position and department during opinion analysis. For example, the opinion analysis unit can apply a strategic analysis algorithm to management personnel depending on their position. The opinion analysis unit can also apply analysis algorithms tailored to the different work content of each department. Furthermore, the opinion analysis unit can apply customized analysis algorithms based on the combination of position and department. This allows for more accurate analysis by applying analysis algorithms tailored to position and department. Specific types of analysis algorithms and application methods include, but are not limited to, machine learning algorithms and statistical models. Some or all of the above-described processes in the opinion analysis unit may be performed using AI, for example, or without AI. For example, the opinion analysis unit can input employee position and department information into a generating AI and have the generating AI execute the application of analysis algorithms.

[0094] The opinion analysis unit improves the accuracy of its analysis by referring to the employee's past opinion submission history during opinion analysis. The opinion analysis unit uses, for example, AI to improve the accuracy of its analysis by referring to the employee's past opinion submission history during opinion analysis. For example, the opinion analysis unit analyzes employee opinions more accurately based on past opinion submission history. The opinion analysis unit can also analyze past opinion submission history to identify frequently occurring problems. Furthermore, the opinion analysis unit can refer to past opinion submission history and perform analysis tailored to the employee's needs. This allows for more accurate analysis by performing analysis based on past opinion submission history. Specific methods and criteria for improving analysis accuracy include, but are not limited to, data quality, algorithm accuracy, and evaluation metrics. Some or all of the above-described processes in the opinion analysis unit may be performed using, for example, AI, or without AI. For example, the opinion analysis unit can input the employee's past opinion submission history into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0095] The opinion analysis unit estimates the user's emotions and adjusts the display method of the analysis results based on the estimated user emotions. For example, the opinion analysis unit may use AI to estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is stressed, the opinion analysis unit may provide a simple and highly visible display method. If the user is relaxed, the opinion analysis unit may provide a display method that includes detailed information. If the user is in a hurry, the opinion analysis unit may provide a display method that gets straight to the point. By adjusting the display method of the analysis results according to the user's emotions, a more visually appealing display can be achieved. Specific methods and criteria for adjusting the display method of the analysis results include, but are not limited to, graphs, dashboards, and reports. Some or all of the above-described processes in the opinion analysis unit may be performed using, for example, an emotion engine or generative AI, or without using an emotion engine or generative AI. For example, the opinion analysis unit may input the user's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0096] The opinion analysis unit considers the geographical location information of employees when analyzing opinions. The opinion analysis unit uses, for example, AI to consider the geographical location information of employees when analyzing opinions. For example, the opinion analysis unit analyzes opinions about a specific area within the office based on geographical location information. The opinion analysis unit can also analyze opinions from remote workers based on geographical location information. Furthermore, the opinion analysis unit can analyze opinions related to a specific region based on geographical location information. This allows for more relevant analysis by performing analysis based on geographical location information. Specific methods for acquiring and using geographical location information include, but are not limited to, GPS data and address information. Some or all of the above-described processes in the opinion analysis unit may be performed using, for example, AI, or without AI. For example, the opinion analysis unit can input the geographical location information of employees into a generating AI and have the generating AI perform the analysis.

[0097] The opinion analysis unit improves the accuracy of its analysis by referring to relevant literature on employees during opinion analysis. The opinion analysis unit uses, for example, AI to improve the accuracy of its analysis by referring to relevant literature on employees during opinion analysis. For example, the opinion analysis unit analyzes employees' opinions more accurately based on relevant literature. The opinion analysis unit can also classify employees' opinions by referring to relevant literature. Furthermore, the opinion analysis unit can analyze employees' opinions based on relevant literature and identify frequently occurring problems. As a result, more accurate analysis can be performed by performing analysis based on relevant literature. Specific methods of referring to and using relevant literature include, but are not limited to, academic papers, technical reports, and industry reports. Some or all of the above processing in the opinion analysis unit may be performed using, for example, AI, or not using AI. For example, the opinion analysis unit can input employees' relevant literature into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0098] The results aggregation unit estimates the user's emotions and adjusts the aggregation method based on the estimated emotions. For example, the results aggregation unit may use AI to estimate the user's emotions and adjust the aggregation method based on the estimated emotions. For example, if the user is stressed, the results aggregation unit may apply a simple aggregation method. If the user is relaxed, the results aggregation unit may apply a more detailed aggregation method. If the user is in a hurry, the results aggregation unit may apply a method that allows for rapid aggregation. By adjusting the aggregation method according to the user's emotions, more appropriate aggregation can be performed. Specific methods and criteria for adjusting the aggregation method include, but are not limited to, statistical methods and data aggregation algorithms. Some or all of the above processing in the results aggregation unit may be performed using, for example, an emotion engine or a generative AI, or without using an emotion engine or a generative AI. For example, the results aggregation unit may input the user's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0099] The results aggregation unit applies different aggregation algorithms depending on the employee's position and department when aggregating results. For example, the results aggregation unit can use AI to apply different aggregation algorithms depending on the employee's position and department when aggregating results. For example, the results aggregation unit can apply a strategic aggregation algorithm to management-level employees depending on their position. The results aggregation unit can also apply aggregation algorithms tailored to the different work content of each department. Furthermore, the results aggregation unit can apply a customized aggregation algorithm based on the combination of position and department. This allows for more accurate aggregation by applying aggregation algorithms tailored to position and department. Specific types and application methods of aggregation algorithms include, but are not limited to, weighted average, median, and mode. Some or all of the above processing in the results aggregation unit may be performed using, for example, AI, or without AI. For example, the results aggregation unit can input employee position and department information into a generating AI and have the generating AI execute the application of the aggregation algorithm.

[0100] The results aggregation unit improves the accuracy of the aggregation by referring to the employee's past opinion submission history when aggregating results. The results aggregation unit can, for example, use AI to improve the accuracy of the aggregation by referring to the employee's past opinion submission history when aggregating results. For example, the results aggregation unit aggregates employee opinions more accurately based on past opinion submission history. The results aggregation unit can also analyze past opinion submission history and identify frequently occurring problems. Furthermore, the results aggregation unit can refer to past opinion submission history and perform aggregation according to the employee's needs. This allows for more accurate aggregation by performing aggregation based on past opinion submission history. Specific methods and criteria for improving aggregation accuracy include, but are not limited to, data quality, algorithm accuracy, and evaluation indicators. Some or all of the above processing in the results aggregation unit may be performed using, for example, AI, or without AI. For example, the results aggregation unit can input the employee's past opinion submission history into a generating AI and have the generating AI perform the aggregation accuracy improvement.

[0101] The results aggregation unit estimates the user's emotions and adjusts the display method of the aggregated results based on the estimated user emotions. For example, the results aggregation unit may use AI to estimate the user's emotions and adjust the display method of the aggregated results based on the estimated user emotions. For example, if the user is stressed, the results aggregation unit may provide a simple and highly visible display method. If the user is relaxed, the results aggregation unit may provide a display method that includes detailed information. If the user is in a hurry, the results aggregation unit may provide a display method that gets straight to the point. By adjusting the display method of the aggregated results according to the user's emotions, a more visually appealing display can be achieved. Specific methods and criteria for adjusting the display method of the aggregated results include, but are not limited to, graphs, dashboards, and reports. Some or all of the above processing in the results aggregation unit may be performed using, for example, an emotion engine or generative AI, or without using an emotion engine or generative AI. For example, the results aggregation unit may input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0102] The results aggregation unit considers the geographical location information of employees when aggregating results. The results aggregation unit uses, for example, AI to consider the geographical location information of employees when aggregating results. For example, the results aggregation unit aggregates opinions on specific areas within the office based on geographical location information. The results aggregation unit can also aggregate opinions from remote workers based on geographical location information. Furthermore, the results aggregation unit can aggregate opinions related to specific regions based on geographical location information. This allows for more relevant aggregation by performing aggregation based on geographical location information. Specific methods for acquiring and using geographical location information include, but are not limited to, GPS data and address information. Some or all of the above processing in the results aggregation unit may be performed using, for example, AI, or without AI. For example, the results aggregation unit can input the geographical location information of employees into a generating AI and have the generating AI perform the aggregation.

[0103] The results aggregation unit improves the accuracy of its aggregations by referring to relevant literature related to employees during the aggregation process. The results aggregation unit can, for example, use AI to improve the accuracy of its aggregations by referring to relevant literature related to employees during the aggregation process. For example, the results aggregation unit can more accurately aggregate employee opinions based on relevant literature. The results aggregation unit can also classify employee opinions by referring to relevant literature. Furthermore, the results aggregation unit can aggregate employee opinions based on relevant literature and identify frequently occurring problems. As a result, more accurate aggregations can be performed by basing the aggregation on relevant literature. Specific methods of referencing and using relevant literature include, but are not limited to, academic papers, technical reports, and industry reports. Some or all of the above-described processes in the results aggregation unit may be performed using, for example, AI, or not using AI. For example, the results aggregation unit can input employee relevant literature into a generating AI and have the generating AI perform the task of improving the accuracy of the aggregation.

[0104] The solution presentation unit estimates the user's emotions and adjusts the method of presenting solutions based on the estimated emotions. For example, the solution presentation unit may use AI to estimate the user's emotions and adjust the method of presenting solutions based on the estimated emotions. For example, if the user is stressed, the solution presentation unit may present a concise and easy-to-implement solution. If the user is relaxed, the solution presentation unit may present a more detailed solution. If the user is in a hurry, the solution presentation unit may also present a solution that can be implemented quickly. In this way, by adjusting the method of presenting solutions according to the user's emotions, more actionable solutions can be provided. Specific methods and criteria for adjusting the method of presenting solutions include, but are not limited to, presentations, reports, and dashboards. Some or all of the above-described processes in the solution presentation unit may be performed using, for example, an emotion engine or generative AI, or without using an emotion engine or generative AI. For example, the solution presentation unit may input the user's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0105] The solution presentation unit presents different solutions depending on the employee's position and department. For example, the solution presentation unit uses AI to present different solutions depending on the employee's position and department. For instance, the solution presentation unit presents strategic solutions to management based on their position. Furthermore, the solution presentation unit can present solutions tailored to the different work content of each department. It can also present customized solutions based on combinations of position and department. This allows for the presentation of more appropriate solutions by providing solutions tailored to each position and department. The specific content and presentation methods of the solutions include, but are not limited to, improvement suggestions, action plans, and recommendations. Some or all of the above-described processes in the solution presentation unit may be performed using, for example, AI, or without AI. For example, the solution presentation unit can input employee position and department information into a generating AI and have the generating AI perform the solution presentation.

[0106] The solution presentation unit improves the accuracy of solutions by referring to the employee's past feedback history when presenting solutions. For example, the solution presentation unit uses AI to improve the accuracy of solutions by referring to the employee's past feedback history when presenting solutions. For example, the solution presentation unit presents solutions that reflect the employee's opinions based on past feedback history. The solution presentation unit can also analyze past feedback history and present solutions to frequently occurring problems. Furthermore, the solution presentation unit can refer to past feedback history and present solutions that meet the employee's needs. This allows for the provision of more appropriate solutions by presenting solutions based on past feedback history. Specific methods and criteria for improving the accuracy of solutions include, but are not limited to, data quality, algorithm accuracy, and evaluation metrics. Some or all of the above-described processes in the solution presentation unit may be performed using, for example, AI, or without AI. For example, the solution presentation unit can input the employee's past feedback history into a generating AI and have the generating AI perform the improvement of solution accuracy.

[0107] The solution presentation unit estimates the user's emotions and determines the priority of solutions based on the estimated emotions. For example, the solution presentation unit may use AI to estimate the user's emotions and determine the priority of solutions based on the estimated emotions. For example, if the user is feeling stressed, the solution presentation unit will prioritize presenting important solutions. If the user is relaxed, the solution presentation unit may prioritize presenting detailed solutions. If the user is in a hurry, the solution presentation unit may prioritize presenting solutions that can be implemented quickly. In this way, by determining the priority of solutions according to the user's emotions, more important solutions can be prioritized. Specific methods and criteria for determining the priority of solutions include, but are not limited to, importance, urgency, and impact. Some or all of the above processing in the solution presentation unit may be performed using, for example, an emotion engine or generative AI, or without using an emotion engine or generative AI. For example, the solution presentation unit may input the user's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0108] The solution presentation unit presents the optimal solution when considering the employee's geographical location information. For example, the solution presentation unit may use AI to present the optimal solution when considering the employee's geographical location information. For example, the solution presentation unit may present a solution for a specific area within the office based on geographical location information. Furthermore, the solution presentation unit can present solutions for remote workers based on geographical location information. It can also present solutions related to specific regions based on geographical location information. This allows for the provision of more appropriate solutions by presenting solutions based on geographical location information. Specific methods for acquiring and using geographical location information include, but are not limited to, GPS data and address information. Some or all of the above-described processes in the solution presentation unit may be performed using, for example, AI, or without AI. For example, the solution presentation unit may input the employee's geographical location information into a generating AI and have the generating AI perform the solution presentation.

[0109] The solution-providing unit analyzes employees' social media activity and proposes solutions when presenting solutions. The solution-providing unit may, for example, use AI to analyze employees' social media activity and propose solutions when presenting solutions. For example, the solution-providing unit may present solutions related to employees' areas of interest based on their social media activity. The solution-providing unit can also present solutions to employees' complaints and requests based on their social media activity. Furthermore, the solution-providing unit can analyze social media activity and present solutions tailored to employees' needs. In this way, by presenting solutions based on social media activity, solutions tailored to employees' needs can be provided. Specific methods and criteria for analyzing social media activity include, but are not limited to, post content, follower count, and engagement rate. Some or all of the above-described processes in the solution-providing unit may be performed using, for example, AI, or not using AI. For example, the solution-providing unit may input employee social media activity data into a generating AI and have the generating AI execute solution proposals.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The employee satisfaction survey system can adjust the method of collecting employee opinions according to the employee's working hours and work style. For example, night shift employees can be provided with a special questionnaire to collect opinions on nighttime work. Remote workers can be provided with an online form to collect opinions on working from home. Furthermore, employees on a flexible working hours system can be provided with a questionnaire to collect opinions on flexible working hours. This allows for the collection of more relevant opinions by gathering opinions tailored to the employee's working hours and work style. The opinion collection unit can select the optimal opinion collection method based on information about the employee's working hours and work style. For example, information about the employee's working hours and work style can be input into a generating AI, and the generating AI can then select the opinion collection method.

[0112] The employee satisfaction survey system can adjust its opinion collection methods based on employees' current projects and areas of interest. For example, it can provide questionnaires that prioritize collecting opinions related to current projects. It can also provide special questionnaires to collect relevant opinions based on employees' areas of interest. Furthermore, it can adjust the timing of opinion collection according to the progress of current projects. This allows for the collection of more relevant opinions by collecting opinions based on current projects and areas of interest. The opinion collection unit can select the optimal opinion collection method based on information about employees' current projects and areas of interest. For example, information about employees' current projects and areas of interest can be input into a generating AI, and the generating AI can then select the opinion collection method.

[0113] The employee satisfaction survey system can adjust its opinion collection methods by considering employees' geographical location when gathering employee feedback. For example, it can provide a questionnaire that prioritizes collecting feedback on specific areas within the office. It can also provide an online form that prioritizes collecting feedback from remote workers. Furthermore, it can provide a questionnaire that prioritizes collecting feedback related to specific regions. By collecting feedback based on geographical location, it is possible to collect more relevant opinions. The feedback collection unit can select the optimal feedback collection method based on employees' geographical location information. For example, employees' geographical location information can be input into a generating AI, and the AI ​​can then select the appropriate feedback collection method.

[0114] The employee satisfaction survey system can collect employee opinions by analyzing their social media activity and gathering relevant feedback. For example, it can provide questionnaires to collect opinions related to employees' areas of interest based on their social media activity. It can also provide online forms to collect opinions on employee complaints and requests based on their social media activity. Furthermore, it can provide questionnaires to collect opinions tailored to employee needs by analyzing social media activity. This allows for the collection of opinions that meet employee needs by collecting feedback based on social media activity. The feedback collection unit can select the optimal feedback collection method based on employee social media activity data. For example, employee social media activity data can be input into a generating AI, and the generating AI can then select the feedback collection method.

[0115] The employee satisfaction survey system can analyze employees' past feedback history to select the most suitable feedback collection method. For example, it can select the feedback collection method preferred by employees based on their past feedback history. It can also select the method that employees find easiest to submit feedback to, based on their past feedback history. Furthermore, it can analyze past feedback history to select a feedback collection method that meets employee needs. This allows for more effective feedback collection by selecting the most suitable method based on past feedback history. The feedback collection unit can select the most suitable feedback collection method based on employees' past feedback history. For example, employees' past feedback history can be input into a generating AI, which can then perform the selection of the feedback collection method.

[0116] The employee satisfaction survey system can estimate the user's emotions and adjust the content and format of questions based on those emotions. For example, if a user is stressed, simple and short questions can be provided to reduce the burden of answering. Conversely, if a user is relaxed, detailed questions can be provided to elicit deeper opinions. Furthermore, if a user is in a hurry, multiple-choice questions can be provided to allow for quick responses. In this way, by adjusting questions according to the user's emotions, the burden of answering is reduced and more accurate opinions can be collected. The question addition section can select the optimal question content and format based on the user's emotions. For example, user facial expression data can be input into a generating AI, and the AI ​​can perform emotion estimation.

[0117] The employee satisfaction survey system can estimate the user's emotions and adjust the order of questions based on those emotions. For example, if a user is stressed, it can start with easy questions and gradually increase the difficulty. If a user is relaxed, important questions can be placed first. Furthermore, if a user is in a hurry, important questions can be placed first, with more detailed questions later on. By adjusting the order of questions according to the user's emotions, the burden of answering can be reduced, and more accurate opinions can be collected. The question addition section can select the optimal question order based on the user's emotions. For example, user facial expression data can be input into a generating AI, and the AI ​​can perform emotion estimation.

[0118] The employee satisfaction survey system can estimate user emotions and adjust the timing of opinion collection based on those emotions. For example, it can collect opinions during times when users are relaxed. Conversely, if users are stressed, opinion collection can be postponed. Furthermore, if users are in a hurry, opinions can be collected in a shorter time. By adjusting the timing of opinion collection according to user emotions, more relevant opinions can be collected. The opinion collection unit can select the optimal timing for opinion collection based on user emotions. For example, user facial expression data can be input into a generating AI, and the AI ​​can perform emotion estimation.

[0119] The employee satisfaction survey system can estimate the user's emotions and prioritize opinions based on those emotions. For example, if a user is stressed, it can prioritize collecting important opinions. If a user is relaxed, it can prioritize collecting detailed opinions. Furthermore, if a user is in a hurry, it can prioritize collecting concise opinions. By prioritizing opinions according to the user's emotions, it is possible to collect more important opinions first. The opinion collection unit can select the optimal opinion priority based on the user's emotions. For example, user facial expression data can be input into a generating AI, and the AI ​​can perform emotion estimation.

[0120] The employee satisfaction survey system can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is stressed, it can provide a simple and highly visible display method. If the user is relaxed, it can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, it can provide a display method that gets straight to the point. In this way, by adjusting the display method of the analysis results according to the user's emotions, a more visually appealing display can be achieved. The opinion analysis unit can select the optimal display method of the analysis results based on the user's emotions. For example, user facial expression data can be input into a generating AI, and the generating AI can perform emotion estimation.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The question addition section allows you to add open-ended questions. For example, you can add open-ended questions to a monthly EN survey to allow employees to freely write their opinions. The question addition section can also be configured to accept various formats such as open-ended, short-answer, and long-answer responses. Step 2: The feedback department collects employee feedback. For example, they could install an anonymous suggestion box where employees can submit their complaints and requests anonymously. Alternatively, the feedback department could place a physical suggestion box in a prominent location within the office, or allow employees to submit feedback via the internet using an online form. Step 3: The Opinion Analysis Department analyzes the opinions collected by the Opinion Collection Department. For example, it uses AI to analyze opinions collected from open-ended questions and anonymous suggestion boxes, and extracts important information. The Opinion Analysis Department classifies employee complaints and requests and identifies frequently occurring problems. It also uses text mining technology to analyze the content of opinions, extract keywords, and understand trends in the opinions. Step 4: The results aggregation unit aggregates the results based on the opinions analyzed by the opinion analysis unit. For example, it aggregates the results based on opinions gathered using AI and creates a report for reporting. The results aggregation unit visually displays the aggregated results as graphs and charts, allowing organizational leaders to understand the state of the organization in real time. Step 5: The Solution Proposal Unit proposes solutions based on the results compiled by the Results Aggregation Unit. For example, it proposes improvement measures based on opinions collected using AI and presents them to the organizational head. The Solution Proposal Unit can also monitor the implementation status of the improvement measures and propose additional improvement measures as needed.

[0123] 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.

[0124] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the question addition unit, opinion collection unit, opinion analysis unit, result aggregation unit, and solution presentation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the question addition unit is implemented by the control unit 46A of the smart device 14 and adds descriptive questions. The opinion collection unit collects employee opinions using the communication I / F 44 of the smart device 14. The opinion analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected opinions. The result aggregation unit is implemented by the specific processing unit 290 of the data processing unit 12 and aggregates the results based on the analyzed opinions. The solution presentation unit is implemented by the specific processing unit 290 of the data processing unit 12 and presents solutions based on the aggregated results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] 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.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0130] 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.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0132] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] 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.

[0134] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] 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.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the question addition unit, opinion collection unit, opinion analysis unit, result aggregation unit, and solution presentation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the question addition unit is implemented by the control unit 46A of the smart glasses 214 and adds descriptive questions. The opinion collection unit collects employee opinions using the communication I / F 44 of the smart glasses 214. The opinion analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected opinions. The result aggregation unit is implemented by the specific processing unit 290 of the data processing unit 12 and aggregates the results based on the analyzed opinions. The solution presentation unit is implemented by the specific processing unit 290 of the data processing unit 12 and presents solutions based on the aggregated results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] 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.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0146] 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.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0148] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] 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.

[0150] 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.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] 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.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the question addition unit, opinion collection unit, opinion analysis unit, result aggregation unit, and solution presentation unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the question addition unit is implemented by the control unit 46A of the headset terminal 314 and adds descriptive questions. The opinion collection unit collects employee opinions using the communication I / F 44 of the headset terminal 314. The opinion analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected opinions. The result aggregation unit is implemented by the specific processing unit 290 of the data processing unit 12 and aggregates the results based on the analyzed opinions. The solution presentation unit is implemented by the specific processing unit 290 of the data processing unit 12 and presents solutions based on the aggregated results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] 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.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0162] 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.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0164] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] 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.

[0166] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] 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.

[0168] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] 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.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the question addition unit, opinion collection unit, opinion analysis unit, result aggregation unit, and solution presentation unit, is implemented by at least one of the robot 414 and the data processing unit 12. For example, the question addition unit is implemented by the control unit 46A of the robot 414 and adds descriptive questions. The opinion collection unit collects employee opinions using the communication I / F 44 of the robot 414. The opinion analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected opinions. The result aggregation unit is implemented by the specific processing unit 290 of the data processing unit 12 and aggregates the results based on the analyzed opinions. The solution presentation unit is implemented by the specific processing unit 290 of the data processing unit 12 and presents solutions based on the aggregated results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0176] 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.

[0177] Figure 9 shows the 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.

[0178] 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.

[0179] 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.

[0180] 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, and motorcycles, 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 based, for example, 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.

[0181] 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."

[0182] 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.

[0183] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] 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 other things 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.

[0193] 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.

[0194] (Note 1) A section for adding written response questions, The opinion gathering department collects employee opinions, An opinion analysis unit analyzes the opinions collected by the opinion collection unit, A results aggregation unit aggregates the results based on the opinions analyzed by the opinion analysis unit, The system includes a solution presentation unit that presents solutions based on the results compiled by the results compilation unit. A system characterized by the following features. (Note 2) The aforementioned opinion collection department, We will install an anonymous suggestion box so that employees can submit their opinions anonymously. The system described in Appendix 1, characterized by the features described herein. (Note 3) The results aggregation unit, The results are compiled based on opinions collected through an annual survey and suggestion box. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned solution presentation unit, Based on feedback collected using AI, we propose improvement measures. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned opinion analysis unit, Classify employee complaints and requests to identify frequently occurring problems. The system described in Appendix 1, characterized by the features described herein. (Note 6) The results aggregation unit, Automatically generate reports for reporting purposes. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned section for adding questions is, The system estimates the user's emotions and adjusts the content and format of the questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned section for adding questions is, Analyze past survey results and dynamically generate questions based on frequently occurring problems. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned section for adding questions is, When adding questions, different questions will be presented depending on the employee's position and department. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned section for adding questions is, The system estimates the user's emotions and adjusts the order of the questions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned section for adding questions is, When adding questions, customize them according to the employee's working hours and work style. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned section for adding questions is, When adding a question, personalize it by referring to the employee's past response history. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned opinion collection department, We estimate the user's emotions and adjust the timing of opinion collection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned opinion collection department, When collecting opinions, we analyze employees' past opinion submission history and select the most suitable collection method. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned opinion collection department, When collecting opinions, filter them based on employees' current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned opinion collection department, It estimates user sentiment and determines the priority of opinions to collect based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned opinion collection department, When collecting opinions, we prioritize collecting highly relevant opinions by considering the geographical location of employees. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned opinion collection department, When gathering feedback, analyze employees' social media activity and collect relevant opinions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned opinion analysis unit, We estimate the user's emotions and adjust the opinion analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned opinion analysis unit, When analyzing opinions, different analysis algorithms are applied depending on the employee's position and department. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned opinion analysis unit, When analyzing opinions, we improve the accuracy of the analysis by referring to the employee's past opinion submission history. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned opinion analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned opinion analysis unit, When analyzing opinions, the analysis will take into account the geographical location information of the employees. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned opinion analysis unit, When analyzing opinions, we improve the accuracy of the analysis by referring to relevant literature from employees. The system described in Appendix 1, characterized by the features described herein. (Note 25) The results aggregation unit, We estimate the user's emotions and adjust the aggregation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The results aggregation unit, When compiling results, different aggregation algorithms are applied depending on the employee's position and department. The system described in Appendix 1, characterized by the features described herein. (Note 27) The results aggregation unit, When compiling results, we improve the accuracy of the compilation by referring to employees' past feedback submission history. The system described in Appendix 1, characterized by the features described herein. (Note 28) The results aggregation unit, It estimates the user's emotions and adjusts how the aggregated results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The results aggregation unit, When compiling the results, the geographical location information of employees will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 30) The results aggregation unit, When compiling results, we improve the accuracy of the compilation by referring to relevant literature related to employees. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned solution presentation unit, It estimates the user's emotions and adjusts how solutions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned solution presentation unit, When presenting solutions, offer different solutions depending on the employee's position and department. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned solution presentation unit, When proposing solutions, we refer to employees' past feedback history to improve the accuracy of the solutions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned solution presentation unit, It estimates the user's emotions and determines the priority of solutions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned solution presentation unit, When proposing solutions, consider the geographical location of employees to present the most suitable solution. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned solution presentation unit, When proposing solutions, we analyze employees' social media activity and suggest solutions based on that analysis. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A section for adding written response questions, The opinion gathering department collects employee opinions, An opinion analysis unit analyzes the opinions collected by the opinion collection unit, A results aggregation unit aggregates the results based on the opinions analyzed by the opinion analysis unit, The system includes a solution presentation unit that presents solutions based on the results compiled by the results compilation unit. A system characterized by the following features.

2. The aforementioned opinion collection department, We will install an anonymous suggestion box so that employees can submit their opinions anonymously. The system according to feature 1.

3. The results aggregation unit, The results are compiled based on opinions collected through an annual survey and suggestion box. The system according to feature 1.

4. The aforementioned solution presentation unit, Based on opinions collected using AI, we propose improvement measures. The system according to feature 1.

5. The aforementioned opinion analysis unit, Classify employee complaints and requests to identify frequently occurring problems. The system according to feature 1.

6. The results aggregation unit, Automatically generate reports for reporting purposes. The system according to feature 1.

7. The aforementioned section for adding questions is, The system estimates the user's emotions and adjusts the content and format of the questions based on those estimated emotions. The system according to feature 1.

8. The aforementioned section for adding questions is, Analyze past survey results and dynamically generate questions based on frequently occurring problems. The system according to feature 1.

9. The aforementioned section for adding questions is, When adding questions, different questions will be presented depending on the employee's position and department. The system according to feature 1.

10. The aforementioned section for adding questions is, The system estimates the user's emotions and adjusts the order of the questions based on those emotions. The system according to feature 1.

Images