system

Abstract

The system according to this embodiment aims to efficiently collect employee feedback and obtain insights that are useful for improving business operations. [Solution] The system according to the embodiment comprises an analysis unit, an extraction unit, a generation unit, and a provision unit. The analysis unit analyzes employee feedback documents. The extraction unit extracts questions from the documents analyzed by the analysis unit. The generation unit automatically generates questionnaires based on the questions extracted by the extraction unit. The provision unit distributes the questionnaires generated by the generation unit to employees and analyzes and provides the collected data in real time.

Description

Technical Field

[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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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 conventional technology, it is laborious to collect feedback from employees, and there is a risk that the results will be insufficient.

[0005] The system according to the embodiment aims to efficiently collect feedback from employees and obtain insights useful for business improvement.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, an extraction unit, a generation unit, and a provision unit. The analysis unit analyzes employee feedback documents. The extraction unit extracts questions from the documents analyzed by the analysis unit. The generation unit automatically generates questionnaires based on the questions extracted by the extraction unit. The provision unit distributes the questionnaires generated by the generation unit to employees and analyzes and provides the collected data in real time. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently collect employee feedback and obtain insights that are useful for improving business operations. [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, etc. The communication I / F controls communication between a plurality of computers. Examples of communication standards applicable 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 automated questionnaire generation system according to an embodiment of the present invention is a system for streamlining the collection of employee feedback and obtaining insights that directly lead to business improvement. This automated questionnaire generation system analyzes employee feedback documents, extracts necessary questions using natural language processing technology, and automatically designs an effective questionnaire format. Furthermore, it distributes the generated questionnaires to employees and analyzes and provides the collected data in real time. This mechanism makes it easier to reflect employee opinions and obtains insights that directly lead to business improvement. First, the automated questionnaire generation system analyzes employee feedback documents. In this process, it uses natural language processing technology to extract necessary questions from the document. For example, if an employee provides feedback such as "What challenges did you experience in recent projects?", the automated questionnaire generation system analyzes this document and extracts relevant questions. Next, the automated questionnaire generation system automatically designs an effective questionnaire format based on the extracted questions. Based on the extracted questions, the automated questionnaire generation system optimizes the structure and order of the questions in the questionnaire. For example, based on employee feedback, it designs a questionnaire that combines multiple-choice questions and open-ended questions. Furthermore, the automated survey generation system distributes the generated surveys to employees and analyzes and provides the collected data in real time. The automated survey generation system analyzes the collected data and provides insights to management. For example, based on employee feedback, it identifies areas for improvement in specific business processes and reports them to management. This mechanism makes it easier to reflect employee opinions and provides insights that directly lead to business improvement. Employees become more engaged and their work efficiency improves when their opinions are reflected. Management can also analyze the data in real time and make quick decisions. For example, by identifying areas for improvement in specific business processes based on employee feedback and taking quick action, work efficiency and management efficiency improve. Thus, the automated survey generation system is an effective means of streamlining the collection of employee feedback and obtaining insights that directly lead to business improvement.This allows the automated survey generation system to efficiently collect employee feedback and gain insights that directly lead to business improvements.

[0029] The automated questionnaire generation system according to this embodiment comprises an analysis unit, an extraction unit, a generation unit, and a provision unit. The analysis unit analyzes employee feedback documents. The analysis unit analyzes feedback documents using, for example, natural language processing technology. The analysis unit can extract words in the document using morphological analysis and analyze sentence structure using grammatical analysis. The analysis unit can also understand the meaning of the document using semantic analysis and extract important information. The extraction unit extracts questions from the document analyzed by the analysis unit. The extraction unit extracts important keywords in the document using, for example, keyword extraction technology and generates questions based on them. The extraction unit can also understand the context of the document using contextual analysis technology and extract relevant questions. The extraction unit can also identify frequently occurring questions and generate questions based on them. The generation unit automatically generates questionnaires based on the questions extracted by the extraction unit. The generation unit determines the structure of the questionnaire based on question selection criteria and optimizes the order of the questions. The generation unit can generate questionnaires that combine multiple-choice questions and open-ended questions. The generation unit can optimize the design of the questionnaire and generate it in a format that is easy for respondents to answer. The distribution unit distributes the questionnaires generated by the generation unit to employees and analyzes and provides the collected data in real time. The distribution unit distributes the questionnaires to employees, for example, via email or web application. The distribution unit analyzes the collected data in real time and provides insights to management. The distribution unit can analyze the data based on the data collection frequency and the type of analysis algorithm and extract important information. The distribution unit can also identify areas for improvement in specific business processes based on the collected data and report them to management. As a result, the automated questionnaire generation system according to this embodiment can efficiently collect employee feedback and obtain insights that directly lead to business improvement.

[0030] The analysis unit analyzes employee feedback documents. For example, the analysis unit uses natural language processing techniques to analyze feedback documents. Specifically, it can extract words from documents using morphological analysis and analyze sentence structure using grammatical analysis. Morphological analysis divides the document into word units and identifies the part of speech and meaning of each word. This allows for the extraction of important keywords and phrases within the document. Grammatical analysis analyzes sentence structure and identifies sentence elements such as subject, predicate, and object. This allows for a deeper understanding of the document's meaning. Furthermore, the analysis unit can also understand the meaning of the document and extract important information using semantic analysis. Semantic analysis considers the context of the entire document and identifies the meaning of words and phrases. This allows for the extraction of important information and opinions within the document, enabling effective analysis of employee feedback. By combining these techniques, the analysis unit can analyze employee feedback documents from multiple perspectives and extract important information. For example, it can identify improvements and problems suggested by employees and formulate specific countermeasures based on them. The analysis department can share the results of its feedback document analysis with other departments and systems to help improve operations. This allows the analysis department to efficiently analyze employee feedback and provide insights directly relevant to business improvement.

[0031] The extraction unit extracts questions from documents analyzed by the analysis unit. For example, the extraction unit uses keyword extraction techniques to extract important keywords from documents and generates questions based on them. Specifically, the extraction unit identifies important keywords and phrases within documents based on the results of morphological and semantic analysis. This allows for the extraction of highly relevant questions from employee feedback documents. Furthermore, the extraction unit can also understand the context of a document using contextual analysis techniques and extract relevant questions. Contextual analysis considers the overall flow and meaning of the document and evaluates the relevance of questions. This allows for the extraction of appropriate questions based on important information and opinions within the document. The extraction unit can also identify frequently occurring questions and generate questions based on them. For example, it can identify keywords and phrases common to multiple feedback documents and generate general questions based on them. This allows for the effective collection of employee feedback and its use in business improvement. The extraction unit can share the extracted questions with other departments and systems to facilitate the generation and distribution of questionnaires. This enables the extraction unit to efficiently extract questions from employee feedback documents and improve the quality of questionnaires.

[0032] The generation unit automatically generates questionnaires based on questions extracted by the extraction unit. For example, the generation unit determines the questionnaire's structure based on question selection criteria and optimizes the question order. Specifically, the generation unit evaluates the extracted questions and selects appropriate questions according to the questionnaire's purpose and target audience. This improves the quality of the questionnaire and generates it in a format that is easy for respondents to answer. The generation unit can generate questionnaires that combine multiple-choice questions and open-ended questions. Multiple-choice questions allow respondents to choose the appropriate answer from several options. Open-ended questions allow respondents to freely write their opinions and impressions. This ensures diversity in the questionnaire and allows for effective collection of employee feedback. The generation unit can also optimize the questionnaire design and generate it in a format that is easy for respondents to answer. For example, it can adjust the layout, font, and colors of the questionnaire to create a visually appealing design. This reduces the burden on respondents and improves the response rate. The generation unit can share the generated questionnaires with other departments and systems for distribution and analysis. This allows the generation unit to efficiently and effectively automatically generate questionnaires and collect employee feedback.

[0033] The distribution department distributes questionnaires generated by the generation department to employees and analyzes and provides the collected data in real time. For example, the distribution department distributes questionnaires to employees via email or web applications. Specifically, the distribution department manages employee email addresses and web application account information to distribute questionnaires quickly and reliably. This allows employees to easily access and respond to questionnaires. The distribution department analyzes the collected data in real time and provides insights to management. For example, the distribution department analyzes data based on data collection frequency and the type of analysis algorithm to extract important information. This allows management to quickly grasp employee feedback and use it to improve operations. The distribution department can also identify areas for improvement in specific business processes based on the collected data and report them to management. For example, it can identify problems in specific business processes from employee feedback and propose concrete improvement measures based on that. This allows management to take concrete actions based on employee feedback. The distribution department can share the collected data with other departments and systems to help improve operations. This allows the service provider to efficiently collect employee feedback and provide insights that directly lead to business improvement.

[0034] The analysis unit can analyze the feedback document using natural language processing techniques. For example, the analysis unit can extract words from the document using morphological analysis. The analysis unit can also analyze the structure of sentences using grammatical analysis. The analysis unit can also understand the meaning of the document and extract important information using semantic analysis. This improves the accuracy of the analysis of the feedback document by using natural language processing techniques. Natural language processing techniques include, but are not limited to, morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the feedback document into a generative AI, which can perform morphological analysis, grammatical analysis, and semantic analysis, and output the analysis results.

[0035] The extraction unit can extract necessary questions from the analyzed document. For example, the extraction unit can use keyword extraction techniques to extract important keywords from the document and generate questions based on them. The extraction unit can also use contextual analysis techniques to understand the context of the document and extract relevant questions. The extraction unit can also identify frequently occurring questions and generate questions based on them. In this way, an effective questionnaire can be generated by extracting the necessary questions. The extraction of necessary questions includes, but is not limited to, keyword extraction, contextual analysis, and identification of frequently occurring questions. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the extraction unit can input the analyzed document into a generative AI, which can perform keyword extraction, contextual analysis, identification of frequently occurring questions, and extract questions.

[0036] The generation unit can optimize the structure and order of questions in a questionnaire based on the extracted questions. For example, the generation unit can determine the structure of the questionnaire and optimize the order of questions based on question selection criteria. The generation unit can generate a questionnaire that combines multiple-choice questions and open-ended questions. The generation unit can also optimize the design of the questionnaire and generate it in a format that is easy for respondents to answer. By optimizing the structure and order of questions in the questionnaire, an effective questionnaire can be generated. Optimization of the structure and order of questions in the questionnaire includes, but is not limited to, optimizing the importance of questions, the flow of responses, and the design. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not. For example, the generation unit can input the extracted questions into a generation AI, which can then optimize the structure and order of questions in the questionnaire and generate the questionnaire.

[0037] The service provider can analyze the collected data in real time and provide insights to management. For example, the service provider can distribute questionnaires to employees via email or web applications. The service provider can analyze the collected data in real time and provide insights to management. The service provider can analyze the data based on the frequency of data collection and the type of analysis algorithm, and extract important information. The service provider can also identify areas for improvement in specific business processes based on the collected data and report them to management. This enables rapid decision-making by analyzing the collected data in real time. Real-time data analysis includes, but is not limited to, the frequency of data collection, the type of analysis algorithm, and the extraction of important information. Some or all of the above processes in the service provider may be performed, for example, using generative AI, or not using generative AI. For example, the service provider can input the collected data into a generative AI, which can analyze the data in real time and provide insights.

[0038] The service provider can identify areas for improvement in specific business processes based on collected data and report them to management. For example, the service provider can analyze the collected data to identify areas for improvement in specific business processes. The service provider can analyze business flows and identify bottlenecks to extract areas for improvement. The service provider can report the identified areas for improvement to management to encourage prompt action. This improves operational efficiency by identifying areas for improvement in specific business processes. Identifying areas for improvement in business processes includes, but is not limited to, analyzing business flows, identifying bottlenecks, and extracting areas for improvement. Some or all of the above processes performed by the service provider may be performed using, for example, generative AI, or not using generative AI. For example, the service provider can input collected data into generative AI, which can then analyze business flows, identify bottlenecks, and extract areas for improvement.

[0039] The analysis unit can improve the accuracy of its analysis by referring to the employee's past feedback history when analyzing feedback documents. For example, the analysis unit can refer to the employee's past feedback history to identify similar feedback patterns. The analysis unit can analyze trends in the employee's opinions from the past feedback history to improve the accuracy of its analysis. The analysis unit can also track changes in the employee's opinions based on the past feedback history and reflect these changes in the analysis. This improves the accuracy of the analysis by referring to the past feedback history. Past feedback history includes, but is not limited to, past survey results and the timing of feedback. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input the employee's past feedback history into a generative AI, which can then identify similar feedback patterns and improve the accuracy of the analysis.

[0040] The analysis unit can customize the analysis algorithm based on the employee's job description and position when analyzing feedback documents. For example, the analysis unit can apply an analysis algorithm that takes into account specialized terminology and job content depending on the employee's job description. The analysis unit can also perform the analysis with an emphasis on position-specific feedback based on the employee's position. The analysis unit can also combine and apply different analysis algorithms depending on the job description and position. This improves the accuracy of the analysis by applying an analysis algorithm that is appropriate for the job description and position. Job description and position include, but are not limited to, job categories and positional hierarchies. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input information about the employee's job description and position into a generative AI, which can then customize the analysis algorithm.

[0041] The analysis unit can perform analysis of feedback documents while considering the geographical location information of employees. For example, the analysis unit can analyze region-specific issues based on the geographical location information of employees. The analysis unit can compare and analyze feedback from different regions while considering geographical location information. The analysis unit can also analyze feedback trends for each region based on geographical location information. This allows for the analysis of region-specific issues by considering geographical location information. Geographical location information includes, but is not limited to, employee work locations and region-specific issues. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the geographical location information of employees into a generative AI, and the generative AI can analyze region-specific issues.

[0042] The analysis unit can analyze employees' social media activity and supplement relevant information when analyzing feedback documents. For example, the analysis unit can analyze employees' social media activity to supplement the content of feedback documents. The analysis unit can estimate employees' opinions and feelings from social media activity and reflect them in the analysis. The analysis unit can also evaluate the credibility of feedback documents based on social media activity. In this way, the content of feedback documents can be supplemented by analyzing social media activity. Social media activity includes, but is not limited to, posts, number of followers, and engagement rate. Some or all of the above processing in the analysis unit may be performed using, for example, generative AI, or not using generative AI. For example, the analysis unit can input employees' social media activity into generative AI, and the generative AI can supplement relevant information.

[0043] The extraction unit can adjust the level of detail of the questions based on the importance of the feedback documents during the extraction process. For example, the extraction unit can extract detailed questions from high-importance feedback documents. The extraction unit can extract concise questions from low-importance feedback documents. The extraction unit can also adjust the level of detail of the questions according to the importance of the feedback documents. This allows for the extraction of effective questions by adjusting the level of detail based on the importance of the feedback documents. The importance of the feedback documents includes, but is not limited to, the content of the feedback and the position of the submitter. Some or all of the above processing in the extraction unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the extraction unit can input the importance of the feedback documents into a generating AI, and the generating AI can adjust the level of detail of the questions.

[0044] The extraction unit can apply different extraction algorithms depending on the category of the feedback document during extraction. For example, the extraction unit can apply an extraction algorithm that takes into account technical terms and business content depending on the category of the feedback document. The extraction unit can combine and apply different extraction algorithms for each category. The extraction unit can also select the optimal extraction algorithm based on the category of the feedback document. This allows for the extraction of effective questions by applying an extraction algorithm appropriate to the category of the feedback document. The categories of feedback documents include, but are not limited to, technical feedback and business improvement feedback. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the extraction unit can input the category of the feedback document into a generative AI, which can then apply the optimal extraction algorithm.

[0045] The extraction unit can prioritize questions based on the submission date of the feedback documents during the extraction process. For example, the extraction unit may prioritize questions from recently submitted feedback documents. The extraction unit may also postpone questions from older feedback documents. The extraction unit can also adjust the priority of questions based on the submission date of the feedback documents. This ensures that the most recent feedback is reflected first by prioritizing questions based on the submission date of the feedback documents. The submission date of the feedback documents includes, but is not limited to, recent feedback or feedback within a specific period. Some or all of the above processing in the extraction unit may be performed, for example, using a generating AI, or not using a generating AI. For example, the extraction unit may input the submission date of the feedback documents into a generating AI, which can then determine the priority of the questions.

[0046] The extraction unit can adjust the order of questions based on the relevance of the feedback documents during extraction. For example, the extraction unit can prioritize extracting questions that are highly relevant to the feedback documents. The extraction unit can postpone questions that are less relevant. The extraction unit can also adjust the order of questions based on the relevance of the feedback documents. This allows for the generation of an effective questionnaire by adjusting the order of questions based on the relevance of the feedback documents. Relevance of the feedback documents includes, but is not limited to, similarity of content and related topics. Some or all of the above processing in the extraction unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the extraction unit can input the relevance of the feedback documents into a generating AI, and the generating AI can adjust the order of the questions.

[0047] The generation unit can adjust the level of detail of a questionnaire based on the importance of the extracted questions during questionnaire generation. For example, the generation unit can generate a questionnaire with detailed descriptions of high-importance questions. The generation unit can also generate a questionnaire with concise descriptions of low-importance questions. The generation unit can also adjust the level of detail of the questionnaire according to the importance of the extracted questions. This allows for the generation of effective questionnaires by adjusting the level of detail based on the importance of the extracted questions. Question importance includes, but is not limited to, the impact of the answer and the frequency of the question. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the importance of the extracted questions into the generation AI, and the generation AI can adjust the level of detail of the questionnaire.

[0048] The generation unit can apply different survey structuring algorithms depending on the question category when generating a survey. For example, the generation unit can apply a survey structuring algorithm that takes into account technical terms and business content depending on the question category. The generation unit can combine and apply different survey structuring algorithms for each category. The generation unit can also select the optimal survey structuring algorithm based on the question category. This allows for the generation of effective surveys by applying a survey structuring algorithm appropriate to the question category. Question categories include, but are not limited to, technical questions and business improvement questions. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the question category into a generation AI, which can then apply the optimal survey structuring algorithm.

[0049] The generation unit can determine the priority of the questionnaire based on when the questions were submitted when generating the questionnaire. For example, the generation unit can prioritize the inclusion of recently submitted questions in the questionnaire. The generation unit can also postpone older questions. The generation unit can also adjust the priority of the questionnaire based on when the questions were submitted. This allows the most recent questions to be reflected first by determining the priority of the questionnaire based on when the questions were submitted. The submission time of the questions includes, but is not limited to, recent questions or questions within a specific period. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the generation unit can input the submission time of the questions into the generation AI, and the generation AI can determine the priority of the questionnaire.

[0050] The generation unit can adjust the order of questions based on their relevance when generating a questionnaire. For example, the generation unit can prioritize including questions with high relevance in the questionnaire. The generation unit can postpone questions with low relevance. The generation unit can also adjust the order of questions based on their relevance. This allows for the generation of an effective questionnaire by adjusting the order of questions based on their relevance. The relevance of questions includes, but is not limited to, similarity of content and related topics. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the generation unit can input the relevance of questions into a generation AI, which can then adjust the order of the questionnaire.

[0051] The data provider can adjust the content of the data provided based on the importance of the collected data. For example, the provider can prioritize providing data of high importance. The provider can postpone providing data of low importance. The provider can also adjust the content of the data provided based on the importance of the collected data. This allows for the priority provision of important data by adjusting the content of the data provided based on the importance of the collected data. The importance of the collected data includes, but is not limited to, the impact of the data and the frequency of the data. Some or all of the above processing in the data provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the data provider can input the importance of the collected data into a generative AI, and the generative AI can adjust the content of the data provided.

[0052] The data provider can apply different analysis algorithms depending on the category of the collected data when providing the data. For example, the data provider can apply an analysis algorithm that takes into account technical terms and business content depending on the data category. The data provider can combine and apply different analysis algorithms for each category. The data provider can also select the optimal analysis algorithm based on the data category. This enables effective data analysis by applying an analysis algorithm appropriate to the data category. The categories of collected data include, but are not limited to, technical data and business improvement data. Some or all of the above processing in the data provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the data provider can input the categories of the collected data into a generative AI, and the generative AI can apply the optimal analysis algorithm.

[0053] The data provider can prioritize the content of the data provided based on when the collected data was submitted. For example, the provider may prioritize recently submitted data. The provider may postpone the provision of older data. The provider can also adjust the priority of the content of the data provided based on when the collected data was submitted. This allows for the provision of the most recent data by prioritizing the content of the data based on when the collected data was submitted. The submission time of the collected data includes, but is not limited to, recent data or data within a specific period. Some or all of the above processing in the data provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the data provider can input the submission time of the collected data into a generative AI, which can then determine the priority of the content of the data provided.

[0054] The data provider can adjust the order of the data provided based on the relevance of the collected data. For example, the provider can prioritize providing highly relevant data. The provider can postpone providing less relevant data. The provider can also adjust the order of the data provided based on the relevance of the collected data. This allows for effective data provision by adjusting the order of the data provided based on the relevance of the collected data. The relevance of the collected data includes, but is not limited to, similarity of content and related topics. Some or all of the processing described above in the data provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the data provider can input the relevance of the collected data into a generative AI, which can then adjust the order of the data provided.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The automated survey generation system can adjust the timing of survey distribution to account for employees' work schedules when collecting employee feedback. For example, surveys can be distributed at night to night shift employees and during the day to day shift employees. The frequency of survey distribution can also be adjusted based on employee work shifts. This allows for surveys to be distributed at appropriate times according to employees' work situations, potentially improving response rates. Furthermore, adjusting the timing of survey distribution can reduce employee stress and lead to more accurate feedback.

[0057] An automated survey generation system can adjust the difficulty of questions based on employee skill levels when collecting employee feedback. For example, it can generate surveys with basic questions for new employees and advanced questions for experienced employees. It can also change the format of questions according to the employee's skill level. This allows for the provision of appropriate questions tailored to the employee's skill level, resulting in more valuable feedback. Furthermore, adjusting the difficulty of questions makes it easier for employees to answer, which can lead to an improved response rate.

[0058] The automated survey generation system can customize questions when collecting employee feedback, taking into account each employee's individual goals and evaluation criteria. For example, when requesting feedback on a specific project, it can generate questions based on that project's goals and evaluation criteria. It can also adjust the content of the feedback according to each employee's individual goals. This allows for obtaining specific feedback based on employees' goal achievement and evaluation criteria, which can be used to improve work processes. Furthermore, customizing questions makes it easier for employees to provide more specific feedback, improving the quality of responses.

[0059] An automated survey generation system can optimize questions by referencing employees' past survey responses when collecting employee feedback. For example, it can add questions from a new perspective to employees who have consistently answered similar questions in the past. It can also identify employees' interests and concerns based on their past responses and generate questions accordingly. This allows for the creation of more effective surveys by leveraging employees' past responses. Furthermore, by referring to past responses, it is possible to track changes in employee opinions and use this information to improve business operations.

[0060] An automated survey generation system can generate different questions for each employee's team or department when collecting employee feedback. For example, it can generate surveys with questions about sales activities for the sales department and questions about the development process for the development department. It can also adjust the content and format of questions according to the characteristics and challenges of each team or department. This allows for obtaining specific feedback from each team or department, which can be used to improve operations in each department. Furthermore, customizing questions for each team or department makes it easier for employees to provide more specific feedback, improving the quality of responses.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The analysis unit analyzes employee feedback documents. The analysis unit uses natural language processing technology to analyze the feedback documents, extracts words from the documents using morphological analysis, and analyzes the sentence structure using grammatical analysis. Furthermore, it can understand the meaning of the documents using semantic analysis and extract important information. Step 2: The extraction unit extracts questions from the document analyzed by the analysis unit. The extraction unit uses keyword extraction technology to extract important keywords from the document and generates questions based on them. Furthermore, it can also use contextual analysis technology to understand the context of the document and extract relevant questions. It can also identify frequently occurring questions and generate questions based on them. Step 3: The generation unit automatically generates a questionnaire based on the questions extracted by the extraction unit. The generation unit determines the structure of the questionnaire based on the question selection criteria and optimizes the order of the questions. It can generate questionnaires that combine multiple-choice questions and open-ended questions, and optimize the questionnaire design to create a questionnaire in a format that is easy for respondents to answer. Step 4: The distribution department distributes the questionnaires generated by the generation department to employees and analyzes and provides the collected data in real time. The distribution department distributes the questionnaires to employees via email or web application and analyzes the collected data in real time to provide insights to management. Based on the data collection frequency and the type of analysis algorithm, the data can be analyzed to extract important information. Based on the collected data, it is also possible to identify areas for improvement in specific business processes and report them to management.

[0063] (Example of form 2) The automated questionnaire generation system according to an embodiment of the present invention is a system for streamlining the collection of employee feedback and obtaining insights that directly lead to business improvement. This automated questionnaire generation system analyzes employee feedback documents, extracts necessary questions using natural language processing technology, and automatically designs an effective questionnaire format. Furthermore, it distributes the generated questionnaires to employees and analyzes and provides the collected data in real time. This mechanism makes it easier to reflect employee opinions and obtains insights that directly lead to business improvement. First, the automated questionnaire generation system analyzes employee feedback documents. In this process, it uses natural language processing technology to extract necessary questions from the document. For example, if an employee provides feedback such as "What challenges did you experience in recent projects?", the automated questionnaire generation system analyzes this document and extracts relevant questions. Next, the automated questionnaire generation system automatically designs an effective questionnaire format based on the extracted questions. Based on the extracted questions, the automated questionnaire generation system optimizes the structure and order of the questions in the questionnaire. For example, based on employee feedback, it designs a questionnaire that combines multiple-choice questions and open-ended questions. Furthermore, the automated survey generation system distributes the generated surveys to employees and analyzes and provides the collected data in real time. The automated survey generation system analyzes the collected data and provides insights to management. For example, based on employee feedback, it identifies areas for improvement in specific business processes and reports them to management. This mechanism makes it easier to reflect employee opinions and provides insights that directly lead to business improvement. Employees become more engaged and their work efficiency improves when their opinions are reflected. Management can also analyze the data in real time and make quick decisions. For example, by identifying areas for improvement in specific business processes based on employee feedback and taking quick action, work efficiency and management efficiency improve. Thus, the automated survey generation system is an effective means of streamlining the collection of employee feedback and obtaining insights that directly lead to business improvement.This allows the automated survey generation system to efficiently collect employee feedback and gain insights that directly lead to business improvements.

[0064] The automated questionnaire generation system according to this embodiment comprises an analysis unit, an extraction unit, a generation unit, and a provision unit. The analysis unit analyzes employee feedback documents. The analysis unit analyzes feedback documents using, for example, natural language processing technology. The analysis unit can extract words in the document using morphological analysis and analyze sentence structure using grammatical analysis. The analysis unit can also understand the meaning of the document using semantic analysis and extract important information. The extraction unit extracts questions from the document analyzed by the analysis unit. The extraction unit extracts important keywords in the document using, for example, keyword extraction technology and generates questions based on them. The extraction unit can also understand the context of the document using contextual analysis technology and extract relevant questions. The extraction unit can also identify frequently occurring questions and generate questions based on them. The generation unit automatically generates questionnaires based on the questions extracted by the extraction unit. The generation unit determines the structure of the questionnaire based on question selection criteria and optimizes the order of the questions. The generation unit can generate questionnaires that combine multiple-choice questions and open-ended questions. The generation unit can optimize the design of the questionnaire and generate it in a format that is easy for respondents to answer. The distribution unit distributes the questionnaires generated by the generation unit to employees and analyzes and provides the collected data in real time. The distribution unit distributes the questionnaires to employees, for example, via email or web application. The distribution unit analyzes the collected data in real time and provides insights to management. The distribution unit can analyze the data based on the data collection frequency and the type of analysis algorithm and extract important information. The distribution unit can also identify areas for improvement in specific business processes based on the collected data and report them to management. As a result, the automated questionnaire generation system according to this embodiment can efficiently collect employee feedback and obtain insights that directly lead to business improvement.

[0065] The analysis unit analyzes employee feedback documents. For example, the analysis unit uses natural language processing techniques to analyze feedback documents. Specifically, it can extract words from documents using morphological analysis and analyze sentence structure using grammatical analysis. Morphological analysis divides the document into word units and identifies the part of speech and meaning of each word. This allows for the extraction of important keywords and phrases within the document. Grammatical analysis analyzes sentence structure and identifies sentence elements such as subject, predicate, and object. This allows for a deeper understanding of the document's meaning. Furthermore, the analysis unit can also understand the meaning of the document and extract important information using semantic analysis. Semantic analysis considers the context of the entire document and identifies the meaning of words and phrases. This allows for the extraction of important information and opinions within the document, enabling effective analysis of employee feedback. By combining these techniques, the analysis unit can analyze employee feedback documents from multiple perspectives and extract important information. For example, it can identify improvements and problems suggested by employees and formulate specific countermeasures based on them. The analysis department can share the results of its feedback document analysis with other departments and systems to help improve operations. This allows the analysis department to efficiently analyze employee feedback and provide insights directly relevant to business improvement.

[0066] The extraction unit extracts questions from documents analyzed by the analysis unit. For example, the extraction unit uses keyword extraction techniques to extract important keywords from documents and generates questions based on them. Specifically, the extraction unit identifies important keywords and phrases within documents based on the results of morphological and semantic analysis. This allows for the extraction of highly relevant questions from employee feedback documents. Furthermore, the extraction unit can also understand the context of a document using contextual analysis techniques and extract relevant questions. Contextual analysis considers the overall flow and meaning of the document and evaluates the relevance of questions. This allows for the extraction of appropriate questions based on important information and opinions within the document. The extraction unit can also identify frequently occurring questions and generate questions based on them. For example, it can identify keywords and phrases common to multiple feedback documents and generate general questions based on them. This allows for the effective collection of employee feedback and its use in business improvement. The extraction unit can share the extracted questions with other departments and systems to facilitate the generation and distribution of questionnaires. This enables the extraction unit to efficiently extract questions from employee feedback documents and improve the quality of questionnaires.

[0067] The generation unit automatically generates questionnaires based on questions extracted by the extraction unit. For example, the generation unit determines the questionnaire's structure based on question selection criteria and optimizes the question order. Specifically, the generation unit evaluates the extracted questions and selects appropriate questions according to the questionnaire's purpose and target audience. This improves the quality of the questionnaire and generates it in a format that is easy for respondents to answer. The generation unit can generate questionnaires that combine multiple-choice questions and open-ended questions. Multiple-choice questions allow respondents to choose the appropriate answer from several options. Open-ended questions allow respondents to freely write their opinions and impressions. This ensures diversity in the questionnaire and allows for effective collection of employee feedback. The generation unit can also optimize the questionnaire design and generate it in a format that is easy for respondents to answer. For example, it can adjust the layout, font, and colors of the questionnaire to create a visually appealing design. This reduces the burden on respondents and improves the response rate. The generation unit can share the generated questionnaires with other departments and systems for distribution and analysis. This allows the generation unit to efficiently and effectively automatically generate questionnaires and collect employee feedback.

[0068] The distribution department distributes questionnaires generated by the generation department to employees and analyzes and provides the collected data in real time. For example, the distribution department distributes questionnaires to employees via email or web applications. Specifically, the distribution department manages employee email addresses and web application account information to distribute questionnaires quickly and reliably. This allows employees to easily access and respond to questionnaires. The distribution department analyzes the collected data in real time and provides insights to management. For example, the distribution department analyzes data based on data collection frequency and the type of analysis algorithm to extract important information. This allows management to quickly grasp employee feedback and use it to improve operations. The distribution department can also identify areas for improvement in specific business processes based on the collected data and report them to management. For example, it can identify problems in specific business processes from employee feedback and propose concrete improvement measures based on that. This allows management to take concrete actions based on employee feedback. The distribution department can share the collected data with other departments and systems to help improve operations. This allows the service provider to efficiently collect employee feedback and provide insights that directly lead to business improvement.

[0069] The analysis unit can analyze the feedback document using natural language processing techniques. For example, the analysis unit can extract words from the document using morphological analysis. The analysis unit can also analyze the structure of sentences using grammatical analysis. The analysis unit can also understand the meaning of the document and extract important information using semantic analysis. This improves the accuracy of the analysis of the feedback document by using natural language processing techniques. Natural language processing techniques include, but are not limited to, morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the feedback document into a generative AI, which can perform morphological analysis, grammatical analysis, and semantic analysis, and output the analysis results.

[0070] The extraction unit can extract necessary questions from the analyzed document. For example, the extraction unit can use keyword extraction techniques to extract important keywords from the document and generate questions based on them. The extraction unit can also use contextual analysis techniques to understand the context of the document and extract relevant questions. The extraction unit can also identify frequently occurring questions and generate questions based on them. In this way, an effective questionnaire can be generated by extracting the necessary questions. The extraction of necessary questions includes, but is not limited to, keyword extraction, contextual analysis, and identification of frequently occurring questions. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the extraction unit can input the analyzed document into a generative AI, which can perform keyword extraction, contextual analysis, identification of frequently occurring questions, and extract questions.

[0071] The generation unit can optimize the structure and order of questions in a questionnaire based on the extracted questions. For example, the generation unit can determine the structure of the questionnaire and optimize the order of questions based on question selection criteria. The generation unit can generate a questionnaire that combines multiple-choice questions and open-ended questions. The generation unit can also optimize the design of the questionnaire and generate it in a format that is easy for respondents to answer. By optimizing the structure and order of questions in the questionnaire, an effective questionnaire can be generated. Optimization of the structure and order of questions in the questionnaire includes, but is not limited to, optimizing the importance of questions, the flow of responses, and the design. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not. For example, the generation unit can input the extracted questions into a generation AI, which can then optimize the structure and order of questions in the questionnaire and generate the questionnaire.

[0072] The service provider can analyze the collected data in real time and provide insights to management. For example, the service provider can distribute questionnaires to employees via email or web applications. The service provider can analyze the collected data in real time and provide insights to management. The service provider can analyze the data based on the frequency of data collection and the type of analysis algorithm, and extract important information. The service provider can also identify areas for improvement in specific business processes based on the collected data and report them to management. This enables rapid decision-making by analyzing the collected data in real time. Real-time data analysis includes, but is not limited to, the frequency of data collection, the type of analysis algorithm, and the extraction of important information. Some or all of the above processes in the service provider may be performed, for example, using generative AI, or not using generative AI. For example, the service provider can input the collected data into a generative AI, which can analyze the data in real time and provide insights.

[0073] The service provider can identify areas for improvement in specific business processes based on collected data and report them to management. For example, the service provider can analyze the collected data to identify areas for improvement in specific business processes. The service provider can analyze business flows and identify bottlenecks to extract areas for improvement. The service provider can report the identified areas for improvement to management to encourage prompt action. This improves operational efficiency by identifying areas for improvement in specific business processes. Identifying areas for improvement in business processes includes, but is not limited to, analyzing business flows, identifying bottlenecks, and extracting areas for improvement. Some or all of the above processes performed by the service provider may be performed using, for example, generative AI, or not using generative AI. For example, the service provider can input collected data into generative AI, which can then analyze business flows, identify bottlenecks, and extract areas for improvement.

[0074] The analysis unit can estimate an employee's emotions and adjust the analysis method of the feedback document based on the estimated emotions. For example, if an employee is stressed, the analysis unit can apply a concise and clear analysis method. If an employee is relaxed, the analysis unit can apply a detailed analysis method to gain deeper insights. If an employee is dissatisfied, the analysis unit can also focus on emotional expression in the analysis. This allows for more appropriate analysis by adjusting the analysis method according to the employee's emotions. The estimation of an employee's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using or without the generative AI. For example, the analysis unit can input an employee's feedback document into the generative AI, which can estimate the employee's emotions and adjust the analysis method.

[0075] The analysis unit can improve the accuracy of its analysis by referring to the employee's past feedback history when analyzing feedback documents. For example, the analysis unit can refer to the employee's past feedback history to identify similar feedback patterns. The analysis unit can analyze trends in the employee's opinions from the past feedback history to improve the accuracy of its analysis. The analysis unit can also track changes in the employee's opinions based on the past feedback history and reflect these changes in the analysis. This improves the accuracy of the analysis by referring to the past feedback history. Past feedback history includes, but is not limited to, past survey results and the timing of feedback. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input the employee's past feedback history into a generative AI, which can then identify similar feedback patterns and improve the accuracy of the analysis.

[0076] The analysis unit can customize the analysis algorithm based on the employee's job description and position when analyzing feedback documents. For example, the analysis unit can apply an analysis algorithm that takes into account specialized terminology and job content depending on the employee's job description. The analysis unit can also perform the analysis with an emphasis on position-specific feedback based on the employee's position. The analysis unit can also combine and apply different analysis algorithms depending on the job description and position. This improves the accuracy of the analysis by applying an analysis algorithm that is appropriate for the job description and position. Job description and position include, but are not limited to, job categories and positional hierarchies. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input information about the employee's job description and position into a generative AI, which can then customize the analysis algorithm.

[0077] The analysis unit can estimate employee emotions and prioritize analysis results based on the estimated employee emotions. For example, if an employee has strong dissatisfaction, the analysis unit will prioritize analyzing that feedback. If an employee has positive emotions, the analysis unit can postpone analyzing that feedback. The analysis unit can also adjust the importance of analysis results based on employee emotions. This allows important feedback to be prioritized by determining the priority of analysis results based on employee emotions. The determination of the priority of analysis results includes, but is not limited to, high-importance feedback and high-urgency feedback. Estimation of employee emotions is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using, for example, generative AI, or without generative AI. For example, the analysis unit can input employee feedback documents into a generating AI, which can then estimate the employee's emotions and determine the priority of the analysis results.

[0078] The analysis unit can perform analysis of feedback documents while considering the geographical location information of employees. For example, the analysis unit can analyze region-specific issues based on the geographical location information of employees. The analysis unit can compare and analyze feedback from different regions while considering geographical location information. The analysis unit can also analyze feedback trends for each region based on geographical location information. This allows for the analysis of region-specific issues by considering geographical location information. Geographical location information includes, but is not limited to, employee work locations and region-specific issues. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the geographical location information of employees into a generative AI, and the generative AI can analyze region-specific issues.

[0079] The analysis unit can analyze employees' social media activity and supplement relevant information when analyzing feedback documents. For example, the analysis unit can analyze employees' social media activity to supplement the content of feedback documents. The analysis unit can estimate employees' opinions and feelings from social media activity and reflect them in the analysis. The analysis unit can also evaluate the credibility of feedback documents based on social media activity. In this way, the content of feedback documents can be supplemented by analyzing social media activity. Social media activity includes, but is not limited to, posts, number of followers, and engagement rate. Some or all of the above processing in the analysis unit may be performed using, for example, generative AI, or not using generative AI. For example, the analysis unit can input employees' social media activity into generative AI, and the generative AI can supplement relevant information.

[0080] The extraction unit can estimate an employee's emotions and adjust the content of the questions extracted based on the estimated emotions. For example, if an employee is stressed, the extraction unit can extract concise and clear questions. If an employee is relaxed, the extraction unit can extract detailed questions. If an employee is dissatisfied, the extraction unit can also extract questions that include emotional expressions. This allows for the extraction of more appropriate questions by adjusting the content of the questions based on the employee's emotions. Adjustment of question content includes, but is not limited to, changing questions according to emotions or adjusting the difficulty level of questions. Estimation of employee emotions is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the extraction unit can input employee emotions into a generative AI, which can then adjust the content of the questions.

[0081] The extraction unit can adjust the level of detail of the questions based on the importance of the feedback documents during the extraction process. For example, the extraction unit can extract detailed questions from high-importance feedback documents. The extraction unit can extract concise questions from low-importance feedback documents. The extraction unit can also adjust the level of detail of the questions according to the importance of the feedback documents. This allows for the extraction of effective questions by adjusting the level of detail based on the importance of the feedback documents. The importance of the feedback documents includes, but is not limited to, the content of the feedback and the position of the submitter. Some or all of the above processing in the extraction unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the extraction unit can input the importance of the feedback documents into a generating AI, and the generating AI can adjust the level of detail of the questions.

[0082] The extraction unit can apply different extraction algorithms depending on the category of the feedback document during extraction. For example, the extraction unit can apply an extraction algorithm that takes into account technical terms and business content depending on the category of the feedback document. The extraction unit can combine and apply different extraction algorithms for each category. The extraction unit can also select the optimal extraction algorithm based on the category of the feedback document. This allows for the extraction of effective questions by applying an extraction algorithm appropriate to the category of the feedback document. The categories of feedback documents include, but are not limited to, technical feedback and business improvement feedback. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the extraction unit can input the category of the feedback document into a generative AI, which can then apply the optimal extraction algorithm.

[0083] The extraction unit can estimate an employee's emotions and determine the priority of questions to extract based on the estimated employee's emotions. For example, if an employee is strongly dissatisfied, the extraction unit will prioritize extracting that question. If an employee has positive emotions, the extraction unit can postpone extracting that question. The extraction unit can also adjust the priority of questions based on the employee's emotions. This allows important questions to be extracted preferentially by determining the priority of questions based on the employee's emotions. The determination of question priority includes, but is not limited to, questions of high importance or urgency. Estimation of employee emotions is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the extraction unit can input employee emotions into a generative AI, which can then determine the priority of questions.

[0084] The extraction unit can prioritize questions based on the submission date of the feedback documents during the extraction process. For example, the extraction unit may prioritize questions from recently submitted feedback documents. The extraction unit may also postpone questions from older feedback documents. The extraction unit can also adjust the priority of questions based on the submission date of the feedback documents. This ensures that the most recent feedback is reflected first by prioritizing questions based on the submission date of the feedback documents. The submission date of the feedback documents includes, but is not limited to, recent feedback or feedback within a specific period. Some or all of the above processing in the extraction unit may be performed, for example, using a generating AI, or not using a generating AI. For example, the extraction unit may input the submission date of the feedback documents into a generating AI, which can then determine the priority of the questions.

[0085] The extraction unit can adjust the order of questions based on the relevance of the feedback documents during extraction. For example, the extraction unit can prioritize extracting questions that are highly relevant to the feedback documents. The extraction unit can postpone questions that are less relevant. The extraction unit can also adjust the order of questions based on the relevance of the feedback documents. This allows for the generation of an effective questionnaire by adjusting the order of questions based on the relevance of the feedback documents. Relevance of the feedback documents includes, but is not limited to, similarity of content and related topics. Some or all of the above processing in the extraction unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the extraction unit can input the relevance of the feedback documents into a generating AI, and the generating AI can adjust the order of the questions.

[0086] The generation unit can estimate employees' emotions and adjust the wording of the questionnaire based on the estimated emotions. For example, if an employee is stressed, the generation unit can apply concise and clear wording. If an employee is relaxed, the generation unit can apply detailed wording. If an employee is dissatisfied, the generation unit can also generate a questionnaire that includes emotional expressions. This allows for the generation of more appropriate questionnaires by adjusting the wording based on employees' emotions. Adjustments to the wording of the questionnaire include, but are not limited to, adjusting wording or changing the question format. Estimation of employee emotions is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the generation unit can input employee emotions into a generative AI, which can then adjust the wording of the questionnaire.

[0087] The generation unit can adjust the level of detail of a questionnaire based on the importance of the extracted questions during questionnaire generation. For example, the generation unit can generate a questionnaire with detailed descriptions of high-importance questions. The generation unit can also generate a questionnaire with concise descriptions of low-importance questions. The generation unit can also adjust the level of detail of the questionnaire according to the importance of the extracted questions. This allows for the generation of effective questionnaires by adjusting the level of detail based on the importance of the extracted questions. Question importance includes, but is not limited to, the impact of the answer and the frequency of the question. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the importance of the extracted questions into the generation AI, and the generation AI can adjust the level of detail of the questionnaire.

[0088] The generation unit can apply different survey structuring algorithms depending on the question category when generating a survey. For example, the generation unit can apply a survey structuring algorithm that takes into account technical terms and business content depending on the question category. The generation unit can combine and apply different survey structuring algorithms for each category. The generation unit can also select the optimal survey structuring algorithm based on the question category. This allows for the generation of effective surveys by applying a survey structuring algorithm appropriate to the question category. Question categories include, but are not limited to, technical questions and business improvement questions. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the question category into a generation AI, which can then apply the optimal survey structuring algorithm.

[0089] The generation unit can estimate the employee's emotions and adjust the length of the questionnaire based on the estimated emotions. For example, if an employee is stressed, the generation unit can generate a short and concise questionnaire. If an employee is relaxed, the generation unit can generate a detailed questionnaire. If an employee is dissatisfied, the generation unit can also generate a questionnaire that includes emotional expressions. This allows for the generation of more appropriate questionnaires by adjusting the length based on the employee's emotions. Adjusting the length of the questionnaire includes, but is not limited to, adjusting the number of questions or providing an estimated response time. Estimation of employee emotions is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the generation unit can input employee emotions into a generation AI, which can then adjust the length of the questionnaire.

[0090] The generation unit can determine the priority of the questionnaire based on when the questions were submitted when generating the questionnaire. For example, the generation unit can prioritize the inclusion of recently submitted questions in the questionnaire. The generation unit can also postpone older questions. The generation unit can also adjust the priority of the questionnaire based on when the questions were submitted. This allows the most recent questions to be reflected first by determining the priority of the questionnaire based on when the questions were submitted. The submission time of the questions includes, but is not limited to, recent questions or questions within a specific period. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the generation unit can input the submission time of the questions into the generation AI, and the generation AI can determine the priority of the questionnaire.

[0091] The generation unit can adjust the order of questions based on their relevance when generating a questionnaire. For example, the generation unit can prioritize including questions with high relevance in the questionnaire. The generation unit can postpone questions with low relevance. The generation unit can also adjust the order of questions based on their relevance. This allows for the generation of an effective questionnaire by adjusting the order of questions based on their relevance. The relevance of questions includes, but is not limited to, similarity of content and related topics. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the generation unit can input the relevance of questions into a generation AI, which can then adjust the order of the questionnaire.

[0092] The service provider can estimate employees' emotions and adjust the data analysis method based on the estimated emotions. For example, if an employee is stressed, the service provider can apply a concise and clear analysis method. If an employee is relaxed, the service provider can apply a detailed analysis method. If an employee is dissatisfied, the service provider can also analyze with an emphasis on emotional expression. This allows for more appropriate analysis by adjusting the data analysis method based on employees' emotions. Adjusting the data analysis method includes, but is not limited to, changing the analysis algorithm according to emotions or adjusting the depth of the analysis. Estimation of employees' emotions is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the service provider can input employee emotions into a generative AI, and the generative AI can adjust the data analysis method.

[0093] The data provider can adjust the content of the data provided based on the importance of the collected data. For example, the provider can prioritize providing data of high importance. The provider can postpone providing data of low importance. The provider can also adjust the content of the data provided based on the importance of the collected data. This allows for the priority provision of important data by adjusting the content of the data provided based on the importance of the collected data. The importance of the collected data includes, but is not limited to, the impact of the data and the frequency of the data. Some or all of the above processing in the data provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the data provider can input the importance of the collected data into a generative AI, and the generative AI can adjust the content of the data provided.

[0094] The data provider can apply different analysis algorithms depending on the category of the collected data when providing the data. For example, the data provider can apply an analysis algorithm that takes into account technical terms and business content depending on the data category. The data provider can combine and apply different analysis algorithms for each category. The data provider can also select the optimal analysis algorithm based on the data category. This enables effective data analysis by applying an analysis algorithm appropriate to the data category. The categories of collected data include, but are not limited to, technical data and business improvement data. Some or all of the above processing in the data provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the data provider can input the categories of the collected data into a generative AI, and the generative AI can apply the optimal analysis algorithm.

[0095] The data provider can estimate an employee's emotions and adjust how the data is displayed based on the estimated emotions. For example, if an employee is stressed, the provider can apply a concise and clear display method. If an employee is relaxed, the provider can apply a detailed display method. If an employee is dissatisfied, the provider can also apply a display method that includes emotional expressions. This allows for more appropriate data display by adjusting how the data is displayed based on the employee's emotions. Adjusting how the data is displayed includes, but is not limited to, changing the display format or adjusting the display content according to the emotions. Estimation of employee emotions is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the data provider can input employee emotions into a generative AI, which can then adjust how the data is displayed.

[0096] The data provider can prioritize the content of the data provided based on when the collected data was submitted. For example, the provider may prioritize recently submitted data. The provider may postpone the provision of older data. The provider can also adjust the priority of the content of the data provided based on when the collected data was submitted. This allows for the provision of the most recent data by prioritizing the content of the data based on when the collected data was submitted. The submission time of the collected data includes, but is not limited to, recent data or data within a specific period. Some or all of the above processing in the data provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the data provider can input the submission time of the collected data into a generative AI, which can then determine the priority of the content of the data provided.

[0097] The data provider can adjust the order of the data provided based on the relevance of the collected data. For example, the provider can prioritize providing highly relevant data. The provider can postpone providing less relevant data. The provider can also adjust the order of the data provided based on the relevance of the collected data. This allows for effective data provision by adjusting the order of the data provided based on the relevance of the collected data. The relevance of the collected data includes, but is not limited to, similarity of content and related topics. Some or all of the processing described above in the data provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the data provider can input the relevance of the collected data into a generative AI, which can then adjust the order of the data provided.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The automated survey generation system can adjust the timing of survey distribution to account for employees' work schedules when collecting employee feedback. For example, surveys can be distributed at night to night shift employees and during the day to day shift employees. The frequency of survey distribution can also be adjusted based on employee work shifts. This allows for surveys to be distributed at appropriate times according to employees' work situations, potentially improving response rates. Furthermore, adjusting the timing of survey distribution can reduce employee stress and lead to more accurate feedback.

[0100] An automated survey generation system can adjust the difficulty of questions based on employee skill levels when collecting employee feedback. For example, it can generate surveys with basic questions for new employees and advanced questions for experienced employees. It can also change the format of questions according to the employee's skill level. This allows for the provision of appropriate questions tailored to the employee's skill level, resulting in more valuable feedback. Furthermore, adjusting the difficulty of questions makes it easier for employees to answer, which can lead to an improved response rate.

[0101] The automated survey generation system can customize questions when collecting employee feedback, taking into account each employee's individual goals and evaluation criteria. For example, when requesting feedback on a specific project, it can generate questions based on that project's goals and evaluation criteria. It can also adjust the content of the feedback according to each employee's individual goals. This allows for obtaining specific feedback based on employees' goal achievement and evaluation criteria, which can be used to improve work processes. Furthermore, customizing questions makes it easier for employees to provide more specific feedback, improving the quality of responses.

[0102] An automated survey generation system can optimize questions by referencing employees' past survey responses when collecting employee feedback. For example, it can add questions from a new perspective to employees who have consistently answered similar questions in the past. It can also identify employees' interests and concerns based on their past responses and generate questions accordingly. This allows for the creation of more effective surveys by leveraging employees' past responses. Furthermore, by referring to past responses, it is possible to track changes in employee opinions and use this information to improve business operations.

[0103] An automated survey generation system can generate different questions for each employee's team or department when collecting employee feedback. For example, it can generate surveys with questions about sales activities for the sales department and questions about the development process for the development department. It can also adjust the content and format of questions according to the characteristics and challenges of each team or department. This allows for obtaining specific feedback from each team or department, which can be used to improve operations in each department. Furthermore, customizing questions for each team or department makes it easier for employees to provide more specific feedback, improving the quality of responses.

[0104] An automated survey generation system can estimate employees' emotions and adjust the survey questions based on those estimates. For example, if an employee is stressed, it can prioritize including concise and easy-to-answer questions. If an employee is relaxed, it can add questions that request more detailed feedback. Furthermore, if an employee is dissatisfied, it can include questions to identify the cause of that dissatisfaction. This allows for the provision of appropriate questions tailored to employees' emotions, resulting in more accurate feedback. By using the emotion estimation function, it is possible to generate surveys that take employees' psychological states into consideration, which is expected to improve response rates.

[0105] The automated survey generation system can estimate employees' emotions and adjust the timing of survey distribution based on those estimates. For example, if an employee is stressed, the survey can be distributed when their workload has calmed down. Conversely, if an employee is relaxed, the survey can be distributed immediately to collect feedback. Furthermore, if an employee is dissatisfied, the survey can be distributed after their dissatisfaction has been resolved. This allows for the distribution of surveys at the appropriate time according to employees' emotions, which is expected to improve response rates. By using the emotion estimation function, it becomes possible to distribute surveys that take into account employees' psychological states, leading to more accurate feedback.

[0106] The automated survey generation system can estimate employees' emotions and adjust the order of survey questions based on those estimates. For example, if an employee is stressed, the system can start with simple questions and gradually move to more detailed ones. Conversely, if an employee is relaxed, important questions can be placed first. Furthermore, if an employee is dissatisfied, questions related to that dissatisfaction can be prioritized. This allows for an appropriate question order tailored to the employee's emotions, leading to more accurate feedback. By using the emotion estimation function, it is possible to generate surveys that take employees' psychological states into consideration, which is expected to improve response rates.

[0107] The automated survey generation system can estimate employees' emotions and adjust the survey question format based on those estimates. For example, if an employee is stressed, multiple-choice questions can be prioritized. If an employee is relaxed, open-ended questions can be added. Furthermore, if an employee is dissatisfied, questions that allow them to describe their dissatisfaction in detail can be included. This allows for the provision of appropriate question formats tailored to employees' emotions, resulting in more accurate feedback. By using the emotion estimation function, it is possible to generate surveys that take employees' psychological states into consideration, which is expected to improve response rates.

[0108] The automated survey generation system can estimate employees' emotions and adjust the survey design based on those estimates. For example, if an employee is stressed, a simple and easy-to-read design can be applied. If an employee is relaxed, a design with detailed information can be applied. Furthermore, if an employee is dissatisfied, a design emphasizing information to address that dissatisfaction can be applied. This allows for the provision of appropriate designs tailored to employees' emotions, leading to more accurate feedback. By using the emotion estimation function, it is possible to generate surveys that take employees' psychological states into consideration, which is expected to improve response rates.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The analysis unit analyzes employee feedback documents. The analysis unit uses natural language processing technology to analyze the feedback documents, extracts words from the documents using morphological analysis, and analyzes the sentence structure using grammatical analysis. Furthermore, it can understand the meaning of the documents using semantic analysis and extract important information. Step 2: The extraction unit extracts questions from the document analyzed by the analysis unit. The extraction unit uses keyword extraction technology to extract important keywords from the document and generates questions based on them. Furthermore, it can also use contextual analysis technology to understand the context of the document and extract relevant questions. It can also identify frequently occurring questions and generate questions based on them. Step 3: The generation unit automatically generates a questionnaire based on the questions extracted by the extraction unit. The generation unit determines the structure of the questionnaire based on the question selection criteria and optimizes the order of the questions. It can generate questionnaires that combine multiple-choice questions and open-ended questions, and optimize the questionnaire design to create a questionnaire in a format that is easy for respondents to answer. Step 4: The distribution department distributes the questionnaires generated by the generation department to employees and analyzes and provides the collected data in real time. The distribution department distributes the questionnaires to employees via email or web application and analyzes the collected data in real time to provide insights to management. Based on the data collection frequency and the type of analysis algorithm, the data can be analyzed to extract important information. Based on the collected data, it is also possible to identify areas for improvement in specific business processes and report them to management.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] Each of the multiple elements described above, including the analysis unit, extraction unit, generation unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing unit 12, and analyzes employee feedback documents. The extraction unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12, and extracts questions from the analyzed documents. The generation unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12, and automatically generates questionnaires based on the extracted questions. The provision unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12, and distributes the generated questionnaires to employees and analyzes and provides the collected data in real time. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] Each of the multiple elements described above, including the analysis unit, extraction unit, generation unit, and provision unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12, and analyzes employee feedback documents. The extraction unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12, and extracts questions from the analyzed documents. The generation unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12, and automatically generates questionnaires based on the extracted questions. The provision unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12, and distributes the generated questionnaires to employees and analyzes and provides the collected data in real time. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] Each of the multiple elements described above, including the analysis unit, extraction unit, generation unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12, and analyzes employee feedback documents. The extraction unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12, and extracts questions from the analyzed documents. The generation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12, and automatically generates questionnaires based on the extracted questions. The provision unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12, and distributes the generated questionnaires to employees and analyzes and provides the collected data in real time. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] Each of the multiple elements described above, including the analysis unit, extraction unit, generation unit, and provision unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing unit 12, and analyzes employee feedback documents. The extraction unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12, and extracts questions from the analyzed documents. The generation unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12, and automatically generates questionnaires based on the extracted questions. The provision unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12, and distributes the generated questionnaires to employees and analyzes and provides the collected data in real time. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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."

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] (Note 1) The analysis department analyzes employee feedback documents, An extraction unit extracts questions from the document analyzed by the aforementioned analysis unit, A generation unit that automatically generates a questionnaire based on the questions extracted by the extraction unit, The system includes a distribution unit that distributes questionnaires generated by the generation unit to employees and analyzes and provides the collected data in real time. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Analyze feedback documents using natural language processing techniques. The system described in Appendix 1, characterized by the features described herein. (Note 3) The extraction unit is Extract necessary questions from the analyzed document. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Optimize the structure and order of questions in the survey based on the extracted questions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, We analyze the collected data in real time and provide insights to business leaders. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned supply unit is, Based on the collected data, identify areas for improvement in specific business processes and report them to management. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, We estimate employee sentiment and adjust the analysis method of feedback documents based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When analyzing feedback documents, we improve the accuracy of the analysis by referring to the employee's past feedback history. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, When analyzing feedback documents, the analysis algorithm is customized based on the employee's job description and position. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, The system estimates employee emotions and prioritizes analysis results based on the estimated employee emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When analyzing feedback documents, 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 12) The aforementioned analysis unit, When analyzing feedback documents, analyze employees' social media activity to supplement relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The extraction unit is We estimate the emotions of our employees and adjust the content of the questions we extract based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The extraction unit is During extraction, adjust the level of detail of the questions based on the importance of the feedback document. The system described in Appendix 1, characterized by the features described herein. (Note 15) The extraction unit is During extraction, different extraction algorithms are applied depending on the category of the feedback document. The system described in Appendix 1, characterized by the features described herein. (Note 16) The extraction unit is Estimate employees' emotions and determine the priority of questions to extract based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The extraction unit is During the extraction process, prioritize questions based on when the feedback documents were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The extraction unit is During extraction, adjust the order of questions based on the relevance of the feedback documents. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is We estimate employees' emotions and adjust the wording of the questionnaire based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is When generating the survey, adjust the level of detail based on the importance of the extracted questions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating a survey, different survey structuring algorithms are applied depending on the question category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is Estimate employee sentiment and adjust the length of the questionnaire based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is When generating a survey, prioritize the survey questions based on when they were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is When generating a questionnaire, adjust the order of the questions based on their relevance. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, We estimate employee sentiment and adjust the data analysis method based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing data, we adjust the content provided based on the importance of the collected data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing data, different analysis algorithms are applied depending on the category of the collected data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, We estimate employee sentiment and adjust how data is displayed based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, When providing data, we prioritize the content of the data based on when the collected data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When providing data, the order of the data provided will be adjusted based on the relevance of the collected data. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0183] 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. The analysis department analyzes employee feedback documents, An extraction unit extracts questions from the document analyzed by the aforementioned analysis unit, A generation unit that automatically generates a questionnaire based on the questions extracted by the extraction unit, The system includes a distribution unit that distributes questionnaires generated by the generation unit to employees and analyzes and provides the collected data in real time. A system characterized by the following features.

2. The aforementioned analysis unit, Analyze feedback documents using natural language processing techniques. The system according to feature 1.

3. The extraction unit is Extract necessary questions from the analyzed document. The system according to feature 1.

4. The generating unit is Optimize the structure and order of questions in the survey based on the extracted questions. The system according to feature 1.

5. The aforementioned supply unit is, We analyze the collected data in real time and provide insights to management. The system according to feature 1.

6. The aforementioned supply unit is, Based on the collected data, identify areas for improvement in specific business processes and report them to management. The system according to feature 1.

7. The aforementioned analysis unit, We estimate employee sentiment and adjust the analysis method of feedback documents based on the estimated employee sentiment. The system according to feature 1.

8. The aforementioned analysis unit, When analyzing feedback documents, we improve the accuracy of the analysis by referring to the employee's past feedback history. The system according to feature 1.

Images