System

Abstract

An object of a system according to an embodiment is to grasp detailed emotions and specific positive / negative points of employees.SOLUTION: A system according to an embodiment includes a generation AI, a scenario generation unit, an emotion analysis unit, and a feedback unit. The generating AI conducts an engagement survey in a chat format using the generating AI. The scenario generation unit performs a dialogue based on the scenario. The emotion analysis unit analyzes an emotion of the employee. The feedback unit performs feedback of a result and an improvement proposal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, engagement surveys based on score evaluations had the problem that it was difficult to grasp employees' detailed feelings or specific positive and negative points.

[0005] The system according to the embodiment aims to grasp detailed emotions of employees and specific positive and negative points. [Means for solving the problem]

[0006] The system according to the embodiment includes a generation AI, a scenario generation unit, an emotion analysis unit, and a feedback unit. The generation AI uses the generation AI to conduct an engagement survey in chat format. The scenario generation unit conducts a dialogue based on the scenario. The emotion analysis unit analyzes the emotions of employees. The feedback unit provides feedback on the results and suggests improvements. [Effects of the Invention]

[0007] The system according to the embodiment can grasp detailed emotions of employees and specific positive and negative points. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The engagement survey system according to the embodiment of the present invention is a system that grasps the emotions and opinions of employees in detail and extracts specific positive and negative points. As a result, the engagement survey system can gain a deeper understanding of the emotions and opinions of employees and make specific improvement proposals.

[0029] An engagement survey system according to an embodiment includes a generation AI, a scenario generation unit, an emotion analysis unit, and a feedback unit. The generation AI elicits emotions and opinions through dialogue with employees. For example, the generation AI asks employees, "How do you feel about the recent project?" and collects their responses. The generation AI then proceeds with the dialogue based on the employees' responses. The scenario generation unit conducts a dialogue based on the scenario. For example, the scenario generation unit presents a specific business scenario and asks employees about their emotions and opinions regarding the scenario. The emotion analysis unit analyzes employees' emotions. For example, the emotion analysis unit analyzes employees' responses and extracts positive and negative points. The feedback unit provides feedback on the results and makes improvement suggestions. For example, the feedback unit makes specific improvement suggestions based on the collected emotions and opinions. This allows the engagement survey system according to an embodiment to gain a detailed understanding of employees' emotions and opinions and make specific improvement suggestions.

[0030] Generative AI can refer to an employee's past interaction history and generate questions optimized for that employee. For example, generative AI can analyze an employee's past interaction history and generate questions based on the employee's interests. For example, an employee who has previously asked many questions about projects can be asked detailed questions about the current project. Generative AI can also generate follow-up questions for concerns or issues previously expressed by the employee based on the employee's past interaction history. For example, an employee who previously pointed out communication problems can be asked questions about the current communication situation. Generative AI can also refer to an employee's past interaction history to generate questions related to topics that the employee is particularly interested in. For example, an employee who is interested in technical topics can be asked questions about the latest technology implementations. This allows for generating questions optimized for the employee, eliciting more detailed feelings and opinions.

[0031] The generation AI can provide instant feedback to employees' answers and generate follow-up questions to deepen the dialogue. For example, the generation AI analyzes employees' answers and provides instant feedback. For example, if an employee answers, "The project is going well," the generation AI generates a follow-up question such as, "In what specific areas is it going well?" The generation AI also generates follow-up questions to deepen the dialogue based on the employee's answers. For example, if the question is, "How do you feel about the introduction of the new system?" and the employee answers, "It's easy to use," the generation AI asks a follow-up question such as, "Which features do you find particularly easy to use?" The generation AI also provides instant feedback to employees' answers and generates specific questions to deepen the dialogue. For example, if an employee answers, "The team atmosphere is good," the generation AI asks a follow-up question such as, "What specifically do you find good about it?" This allows for instant feedback and deeper dialogue, making it possible to understand employees' feelings and opinions in more detail.

[0032] The scenario generation unit can refer to an employee's work history and generate a scenario optimized for that employee. For example, the scenario generation unit uses a generation AI to analyze an employee's work history and generate a scenario based on the employee's work content and experience. For example, a project manager is presented with a scenario related to project management. The scenario generation unit also generates scenarios related to the challenges and issues the employee is facing based on the employee's work history. For example, an engineer is presented with a scenario related to technical problem solving. The scenario generation unit also uses a generation AI to refer to an employee's work history and generate a scenario based on the employee's skills and knowledge. For example, a new employee is presented with a scenario related to the onboarding process. This makes it possible to elicit more specific emotions and opinions by generating an optimized scenario based on the employee's work history.

[0033] When conducting a dialogue based on a scenario, the scenario generation unit can dynamically change the scenario depending on the employee's responses. In the scenario generation unit, for example, the generation AI analyzes the employee's responses and dynamically changes the scenario. For example, if an employee responds that "the new system is easy to use," the generation AI adds questions about the system's specific functions. In addition, the scenario generation unit adjusts the scenario in real time based on the employee's responses. For example, if an employee responds that "there are problems with the progress of the project," the generation AI adds questions about the details of the problem. In addition, the scenario generation unit dynamically changes the scenario based on the employee's responses to deepen the dialogue. For example, if an employee responds that "there is a lack of communication in the team," the generation AI adds questions asking for specific suggestions for improving communication. In this way, the dialogue can be deepened by dynamically changing the scenario depending on the employee's responses.

[0034] The scenario generation unit can expand the dialogue format of the scenario into a game format, allowing employees to participate in the survey while having fun. The scenario generation unit, for example, expands the dialogue format of the scenario into a game format, allowing employees to participate in the survey while having fun. For example, quiz-style questions can be introduced so that points can be earned for each correct answer. The scenario generation unit can also introduce a game-style scenario, creating a system in which employees level up as they progress through the dialogue. For example, answering a specific question can allow them to advance to the next level. The scenario generation unit can also gamify the dialogue format of the scenario, allowing employees to participate in the survey while having fun. For example, mission-style questions can be introduced so that rewards can be earned for each mission completed. In this way, by expanding the dialogue format into a game format, employees can participate in the survey while having fun.

[0035] The scenario generation unit extends the scenario-based dialogue format to a virtual reality format, allowing employees to respond while experiencing the scenario in a virtual environment. The scenario generation unit, for example, extends the scenario-based dialogue format to a virtual reality format, allowing employees to respond while experiencing the scenario in a virtual environment. For example, employees answer questions while experiencing a work scenario in a virtual office. The scenario generation unit also introduces a VR-format scenario, allowing employees to respond while experiencing a specific situation in the virtual environment. For example, employees may express their feelings and opinions while checking the progress of a virtual project. The scenario generation unit also uses virtual reality technology to build a system in which employees respond while experiencing a scenario in a virtual environment. For example, employees may answer questions while experiencing a discussion in a virtual conference room. By extending the format to virtual reality, employees can respond while experiencing a specific situation.

[0036] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0037] The engagement survey system can monitor employees' health status and provide feedback based on health data. For example, it can collect employees' heart rate and sleep data and evaluate their stress levels. It can also provide employees with advice on relaxation methods and stress management based on their health data. It can also adjust workloads and suggest breaks based on employees' health status. This makes it possible to provide feedback that takes into account employees' health status, thereby improving employee engagement.

[0038] The engagement survey system can provide feedback based on employees' skills and career goals. For example, it can analyze an employee's skill set and provide specific advice for improving their skills. It can also suggest training programs and career paths based on the employee's career goals. It can also adjust project assignments and work content based on the employee's skills and career goals. This makes it possible to improve employee motivation by providing feedback based on the employee's skills and career goals.

[0039] The engagement survey system can analyze employees' internal networks and make suggestions for improving internal communication. For example, it can analyze employees' email and chat history to evaluate the frequency and quality of communication. It can also suggest areas for improving communication or the introduction of new communication tools based on the results of analyzing the internal network. It can also suggest workshops and training programs to promote collaboration between employees. This can improve employee engagement through improved internal communication.

[0040] The engagement survey system can evaluate employees' work-life balance and suggest ways to achieve a balanced work style. For example, it can analyze employees' working hours and vacation status to evaluate their work-life balance. It can also suggest flexible working hours and remote work based on the employee's work-life balance. It can also suggest welfare programs and support services to improve employees' work-life balance. This makes it possible to improve employee engagement by making suggestions that take into account employees' work-life balance.

[0041] The engagement survey system can analyze employees' work performance without using employee emotion estimation functions and provide specific advice to improve performance. For example, it can analyze employees' work data and suggest efficient work methods and tools. It can also provide training programs and resources for skill development based on the results of the work performance analysis. It can also adjust work content and project assignments according to employees' work performance. This makes it possible to improve employee engagement by providing specific advice to improve employees' work performance.

[0042] The processing flow of the first embodiment will be briefly explained below.

[0043] Step 1: The generative AI elicits emotions and opinions through dialogue with employees. For example, the generative AI asks employees, "How do you feel about the recent project?" and collects their responses. The generative AI then proceeds with the dialogue based on the employees' responses. Step 2: The scenario generator conducts a dialogue based on the scenario. For example, the scenario generator presents a specific business scenario and asks for feelings and opinions about the scenario. Step 3: The sentiment analysis unit analyzes the employee's emotions. For example, the sentiment analysis unit analyzes the employee's responses and extracts positive and negative points. Step 4: The feedback department provides feedback on the results and makes suggestions for improvement. For example, the feedback department makes specific suggestions for improvement based on the collected emotions and opinions.

[0044] (Example 2) The engagement survey system according to the embodiment of the present invention is a system that grasps the emotions and opinions of employees in detail and extracts specific positive and negative points. As a result, the engagement survey system can gain a deeper understanding of the emotions and opinions of employees and make specific improvement proposals.

[0045] An engagement survey system according to an embodiment includes a generation AI, a scenario generation unit, an emotion analysis unit, and a feedback unit. The generation AI elicits emotions and opinions through dialogue with employees. For example, the generation AI asks employees, "How do you feel about the recent project?" and collects their responses. The generation AI then proceeds with the dialogue based on the employees' responses. The scenario generation unit conducts a dialogue based on the scenario. For example, the scenario generation unit presents a specific business scenario and asks employees about their emotions and opinions regarding the scenario. The emotion analysis unit analyzes employees' emotions. For example, the emotion analysis unit analyzes employees' responses and extracts positive and negative points. The feedback unit provides feedback on the results and makes improvement suggestions. For example, the feedback unit makes specific improvement suggestions based on the collected emotions and opinions. This allows the engagement survey system according to an embodiment to gain a detailed understanding of employees' emotions and opinions and make specific improvement suggestions.

[0046] Generative AI can refer to an employee's past interaction history and generate questions optimized for that employee. For example, generative AI can analyze an employee's past interaction history and generate questions based on the employee's interests. For example, an employee who has previously asked many questions about projects can be asked detailed questions about the current project. Generative AI can also generate follow-up questions for concerns or issues previously expressed by the employee based on the employee's past interaction history. For example, an employee who previously pointed out communication problems can be asked questions about the current communication situation. Generative AI can also refer to an employee's past interaction history to generate questions related to topics that the employee is particularly interested in. For example, an employee who is interested in technical topics can be asked questions about the latest technology implementations. This allows for generating questions optimized for the employee, eliciting more detailed feelings and opinions.

[0047] The generation AI can provide instant feedback to employees' answers and generate follow-up questions to deepen the dialogue. For example, the generation AI analyzes employees' answers and provides instant feedback. For example, if an employee answers, "The project is going well," the generation AI generates a follow-up question such as, "In what specific areas is it going well?" The generation AI also generates follow-up questions to deepen the dialogue based on the employee's answers. For example, if the question is, "How do you feel about the introduction of the new system?" and the employee answers, "It's easy to use," the generation AI asks a follow-up question such as, "Which features do you find particularly easy to use?" The generation AI also provides instant feedback to employees' answers and generates specific questions to deepen the dialogue. For example, if an employee answers, "The team atmosphere is good," the generation AI asks a follow-up question such as, "What specifically do you find good about it?" This allows for instant feedback and deeper dialogue, making it possible to understand employees' feelings and opinions in more detail.

[0048] The generative AI can use its emotion estimation function to generate questions based on an employee's emotional state and engage in dialogue that elicits positive emotions. For example, the generative AI uses its emotion estimation function to analyze an employee's emotional state in real time and generate questions that elicit positive emotions. For example, if an employee is feeling stressed, it can ask a question such as, "What are you particularly satisfied with in your recent project?" The generative AI can also analyze an employee's emotional state and generate specific questions to elicit positive emotions. For example, if an employee is tired, it can ask a question such as, "When did you feel a particular sense of accomplishment in your recent work?" The generative AI can also use its emotion estimation function to generate questions based on an employee's emotional state and engage in dialogue that elicits positive emotions. For example, if an employee is feeling anxious, it can ask a question such as, "What are you particularly proud of in your recent project?" This allows the system to generate questions based on an employee's emotional state and elicit positive emotions, thereby improving employee engagement.

[0049] Generative AI can expand chat-style surveys to voice dialogue and use voice recognition technology to analyze employee emotions. For example, generative AI expands chat-style surveys to voice dialogue and uses voice recognition technology to analyze employee emotions. For example, it analyzes the tone and speed of employees' voice responses to estimate their emotional state. Generative AI can also introduce voice dialogue-style surveys and analyze employees' voice data to grasp changes in emotions in real time. For example, it analyzes the intonation and strength of the employee's voice when they respond to measure the intensity of their emotions. Generative AI can also use voice recognition technology to analyze emotions from employees' voice data and adjust the content of the survey questions. For example, if an employee is tired, it can ask questions to help them relax. By expanding the survey to voice dialogue, it is possible to analyze employees' emotions in more detail.

[0050] Generative AI can extend chat-style surveys to video interactive formats and use facial expression recognition technology to analyze employee emotions. For example, generative AI extends chat-style surveys to video interactive formats and uses facial expression recognition technology to analyze employee emotions. For example, it analyzes the facial expressions of employees when they answer questions via video calls to estimate their emotional state. Generative AI also introduces video interactive surveys and analyzes employees' facial expression data to grasp changes in emotions in real time. For example, it analyzes the facial movements and changes in expressions when employees answer questions to measure the intensity of their emotions. Generative AI also uses facial expression recognition technology to analyze emotions from employees' facial expression data and adjust the content of the survey questions. For example, if an employee is nervous, it asks questions that will help them relax. By extending the survey to a video interactive format, it is possible to analyze employees' emotions in more detail.

[0051] The generation AI can use the emotion estimation function to generate questions that are appropriate for the environment in which employees are taking the chat-style survey. For example, the generation AI uses the emotion estimation function to generate questions that are appropriate for the environment in which employees are taking the chat-style survey. For example, employees working remotely are asked questions about the benefits and challenges of remote work. The generation AI also analyzes employees' work environments and generates questions that are appropriate for that environment. For example, employees working in an office are asked questions about areas for improvement in the office environment. The generation AI also uses the emotion estimation function to generate questions that are appropriate for employees' work environments, thereby improving the effectiveness of the survey. For example, employees working remotely are asked questions about the stress factors of remote work. This allows for generating questions that are appropriate for the employee's environment, thereby obtaining more appropriate feedback.

[0052] The scenario generation unit can refer to an employee's work history and generate a scenario optimized for that employee. For example, the scenario generation unit uses a generation AI to analyze an employee's work history and generate a scenario based on the employee's work content and experience. For example, a project manager is presented with a scenario related to project management. The scenario generation unit also generates scenarios related to the challenges and issues the employee is facing based on the employee's work history. For example, an engineer is presented with a scenario related to technical problem solving. The scenario generation unit also uses a generation AI to refer to an employee's work history and generate a scenario based on the employee's skills and knowledge. For example, a new employee is presented with a scenario related to the onboarding process. This makes it possible to elicit more specific emotions and opinions by generating an optimized scenario based on the employee's work history.

[0053] When conducting a dialogue based on a scenario, the scenario generation unit can dynamically change the scenario depending on the employee's responses. In the scenario generation unit, for example, the generation AI analyzes the employee's responses and dynamically changes the scenario. For example, if an employee responds that "the new system is easy to use," the generation AI adds questions about the system's specific functions. In addition, the scenario generation unit adjusts the scenario in real time based on the employee's responses. For example, if an employee responds that "there are problems with the progress of the project," the generation AI adds questions about the details of the problem. In addition, the scenario generation unit dynamically changes the scenario based on the employee's responses to deepen the dialogue. For example, if an employee responds that "there is a lack of communication in the team," the generation AI adds questions asking for specific suggestions for improving communication. In this way, the dialogue can be deepened by dynamically changing the scenario depending on the employee's responses.

[0054] The scenario generation unit can expand the dialogue format of the scenario into a game format, allowing employees to participate in the survey while having fun. The scenario generation unit, for example, expands the dialogue format of the scenario into a game format, allowing employees to participate in the survey while having fun. For example, quiz-style questions can be introduced so that points can be earned for each correct answer. The scenario generation unit can also introduce a game-style scenario, creating a system in which employees level up as they progress through the dialogue. For example, answering a specific question can allow them to advance to the next level. The scenario generation unit can also gamify the dialogue format of the scenario, allowing employees to participate in the survey while having fun. For example, mission-style questions can be introduced so that rewards can be earned for each mission completed. In this way, by expanding the dialogue format into a game format, employees can participate in the survey while having fun.

[0055] The scenario generation unit extends the scenario-based dialogue format to a virtual reality format, allowing employees to respond while experiencing the scenario in a virtual environment. The scenario generation unit, for example, extends the scenario-based dialogue format to a virtual reality format, allowing employees to respond while experiencing the scenario in a virtual environment. For example, employees answer questions while experiencing a work scenario in a virtual office. The scenario generation unit also introduces a VR-format scenario, allowing employees to respond while experiencing a specific situation in the virtual environment. For example, employees may express their feelings and opinions while checking the progress of a virtual project. The scenario generation unit also uses virtual reality technology to build a system in which employees respond while experiencing a scenario in a virtual environment. For example, employees may answer questions while experiencing a discussion in a virtual conference room. By extending the format to virtual reality, employees can respond while experiencing a specific situation.

[0056] The scenario generation unit can use the emotion estimation function to generate a scenario according to the time of day when an employee will have a conversation based on the scenario. For example, the scenario generation unit uses the emotion estimation function to generate a scenario according to the time of day when an employee will have a conversation based on the scenario. For example, it presents a work-related scenario during working hours and a relaxing scenario during break time. The scenario generation unit also uses the generation AI to analyze the employee's emotional state and time of day and generate a scenario according to the situation. For example, it presents a scenario that increases motivation in the morning and a scenario that encourages reflection in the evening. The scenario generation unit also uses the emotion estimation function to generate a scenario according to the employee's emotional state and time of day to effectively advance the conversation. For example, it presents a scenario that involves reflecting on the day before the end of work. In this way, by generating scenarios according to the time of day, it is possible to have a conversation according to the employee's situation.

[0057] When analyzing employee responses, the emotion analysis unit can classify the intensity and type of emotions in detail and track changes in emotions. For example, the emotion analysis unit uses a generation AI to analyze employee responses and classify the intensity and type of emotions in detail. For example, emotions such as joy, sadness, and surprise are quantified and changes in emotions are tracked. The emotion analysis unit also analyzes employee responses and builds a system that classifies the intensity and type of emotions in detail. For example, positive emotions and negative emotions are quantified and changes in emotions are displayed in a graph. The emotion analysis unit also analyzes employee responses using a generation AI and classifies the intensity and type of emotions in detail to track changes in emotions. For example, it calculates an emotion score for each response and visualizes changes in emotions over time. This allows for detailed classification of the intensity and type of emotions and tracking changes in emotions, making it possible to understand employee emotions in more detail.

[0058] The emotion analysis unit can identify the factors behind the emotions when analyzing employee responses. For example, the emotion analysis unit uses a generation AI to analyze employee responses and identify the factors behind the emotions. For example, it extracts keywords related to work content and interpersonal relationships to clarify the causes of the emotions. The emotion analysis unit also builds a system that analyzes employee responses and identifies the factors behind the emotions. For example, it analyzes emotions related to specific work or projects to identify the causes of the emotions. The emotion analysis unit also analyzes employee responses using a generation AI to identify the factors behind the emotions, thereby gaining a detailed understanding of the emotions. For example, it extracts work-related stress factors and interpersonal problems from the content of the responses. This allows for a more detailed understanding of employee emotions by identifying the factors behind the emotions.

[0059] The emotion analysis unit can use the emotion estimation function to analyze subtle emotional nuances contained in the employee's answers and generate a detailed emotion profile. The emotion analysis unit, for example, uses the emotion estimation function to analyze subtle emotional nuances contained in the employee's answers. For example, it analyzes the tone and wording of the answers and generates a detailed emotion profile. The emotion analysis unit also builds a system that analyzes subtle emotional nuances contained in the employee's answers. For example, it analyzes the subtle differences between positive emotions and negative emotions and generates an emotion profile. The emotion analysis unit also uses the emotion estimation function to analyze subtle emotional nuances contained in the employee's answers and generate a detailed emotion profile. For example, it analyzes the context of the answers and the choice of words to create a detailed emotion profile. In this way, by analyzing subtle emotional nuances and generating a detailed emotion profile, it is possible to understand the employee's emotions in more detail.

[0060] The emotion analysis unit can grasp emotions in detail by combining not only text analysis but also voice analysis and facial expression analysis. For example, the emotion analysis unit builds a system that grasps emotions in detail by combining not only text analysis but also voice analysis and facial expression analysis. For example, it analyzes an employee's voice data and facial expression data to generate a detailed emotional profile. The emotion analysis unit also grasps emotions in detail by combining voice analysis and facial expression analysis in addition to text analysis. For example, it analyzes the content of an employee's answers, their voice tone, and changes in their facial expressions to classify the intensity and type of emotions in detail. The emotion analysis unit also develops a system that grasps emotions in detail by combining text analysis, voice analysis, and facial expression analysis. For example, it comprehensively analyzes the content of an employee's answers, their voice tone, and changes in their facial expressions to generate a detailed emotional profile. As a result, it becomes possible to grasp emotions in detail by combining text analysis, voice analysis, and facial expression analysis.

[0061] The emotion analysis unit can grasp emotions in detail using the physiological data of employees. The emotion analysis unit, for example, builds a system that grasps emotions in detail using the physiological data of employees. For example, it analyzes heart rate and electrodermal activity to classify the intensity and type of emotion in detail. The emotion analysis unit also analyzes the physiological data of employees to grasp emotions in detail. For example, it analyzes fluctuations in heart rate and changes in electrodermal activity to identify the intensity and type of emotion. The emotion analysis unit also develops a system that grasps emotions in detail using the physiological data of employees. For example, it monitors heart rate and electrodermal activity in real time to grasp changes in emotions in detail. In this way, it becomes possible to grasp emotions in detail using physiological data.

[0062] The emotion analysis unit can use the emotion estimation function to monitor the emotional state of employees in real time and provide feedback according to changes in their emotions. The emotion analysis unit, for example, uses the emotion estimation function to build a system that monitors the emotional state of employees in real time. For example, it analyzes the facial expressions and voice of employees and provides feedback according to changes in their emotions. The emotion analysis unit also develops a system that monitors the emotional state of employees in real time and provides feedback according to changes in their emotions. For example, if an employee is feeling stressed, it provides feedback to help them relax. The emotion analysis unit also uses the emotion estimation function to monitor the emotional state of employees in real time and provides feedback according to changes in their emotions. For example, if an employee is showing positive emotions, it provides feedback to further increase their motivation. In this way, by monitoring the emotional state in real time and providing feedback according to changes in their emotions, it is possible to grasp the emotions of employees in more detail.

[0063] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0064] The engagement survey system can monitor employees' health status and provide feedback based on health data. For example, it can collect employees' heart rate and sleep data and evaluate their stress levels. It can also provide employees with advice on relaxation methods and stress management based on their health data. It can also adjust workloads and suggest breaks based on employees' health status. This makes it possible to provide feedback that takes into account employees' health status, thereby improving employee engagement.

[0065] The engagement survey system can provide feedback based on employees' skills and career goals. For example, it can analyze an employee's skill set and provide specific advice for improving their skills. It can also suggest training programs and career paths based on the employee's career goals. It can also adjust project assignments and work content based on the employee's skills and career goals. This makes it possible to improve employee motivation by providing feedback based on the employee's skills and career goals.

[0066] The engagement survey system can analyze employees' internal networks and make suggestions for improving internal communication. For example, it can analyze employees' email and chat history to evaluate the frequency and quality of communication. It can also suggest areas for improving communication or the introduction of new communication tools based on the results of analyzing the internal network. It can also suggest workshops and training programs to promote collaboration between employees. This can improve employee engagement through improved internal communication.

[0067] The engagement survey system can evaluate employees' work-life balance and suggest ways to achieve a balanced work style. For example, it can analyze employees' working hours and vacation status to evaluate their work-life balance. It can also suggest flexible working hours and remote work based on the employee's work-life balance. It can also suggest welfare programs and support services to improve employees' work-life balance. This makes it possible to improve employee engagement by making suggestions that take into account employees' work-life balance.

[0068] The engagement survey system can use its employee emotion estimation function to suggest leadership styles that correspond to an employee's emotional state. For example, if an employee is feeling stressed, it can suggest supportive leadership. Alternatively, if an employee is highly motivated, it can suggest leadership that sets challenging goals. Furthermore, it can also provide training programs that enable employees to flexibly change their leadership style depending on their emotional state. This makes it possible to improve employee engagement by suggesting leadership styles that correspond to the employee's emotional state.

[0069] The engagement survey system can use its employee emotion estimation function to suggest team building activities that correspond to employees' emotional state. For example, if an employee is tired, it can suggest a relaxing activity. Alternatively, if an employee is showing positive emotions, it can suggest a challenging team building activity. Furthermore, it can adjust the content and frequency of team building activities according to the employee's emotional state. This makes it possible to improve employee engagement by suggesting team building activities that correspond to the employee's emotional state.

[0070] The engagement survey system uses an employee emotion estimation function to adjust the timing of feedback according to the employee's emotional state. For example, if an employee is feeling stressed, delaying feedback can reduce the employee's burden. Also, if an employee is showing positive emotions, providing immediate feedback can increase motivation. Furthermore, it is possible to adjust the content and method of feedback according to the employee's emotional state. This makes it possible to improve employee engagement by adjusting the timing of feedback according to the employee's emotional state.

[0071] The engagement survey system can use its employee emotion estimation function to provide mental health support according to the employee's emotional state. For example, if an employee is feeling stressed, it can suggest counseling or a relaxation program. If an employee is feeling anxious, it can also provide a stress management workshop. Furthermore, it can adjust the content and frequency of mental health support according to the employee's emotional state. This makes it possible to improve employee engagement by providing mental health support according to the employee's emotional state.

[0072] The engagement survey system uses an employee emotion estimation function to evaluate performance according to the employee's emotional state. For example, if an employee is feeling stressed, the evaluation criteria can be flexibly adjusted. Also, if an employee is showing positive emotions, challenging goals can be set. Furthermore, it is possible to adjust the content and method of performance evaluation feedback according to the employee's emotional state. This makes it possible to improve employee engagement by evaluating performance according to the employee's emotional state.

[0073] The engagement survey system can analyze employees' work performance without using employee emotion estimation functions and provide specific advice to improve performance. For example, it can analyze employees' work data and suggest efficient work methods and tools. It can also provide training programs and resources for skill development based on the results of the work performance analysis. It can also adjust work content and project assignments according to employees' work performance. This makes it possible to improve employee engagement by providing specific advice to improve employees' work performance.

[0074] The processing flow of the second embodiment will be briefly explained below.

[0075] Step 1: The generative AI elicits emotions and opinions through dialogue with employees. For example, the generative AI asks employees, "How do you feel about the recent project?" and collects their responses. The generative AI then proceeds with the dialogue based on the employees' responses. Step 2: The scenario generator conducts a dialogue based on the scenario. For example, the scenario generator presents a specific business scenario and asks for feelings and opinions about the scenario. Step 3: The sentiment analysis unit analyzes the employee's emotions. For example, the sentiment analysis unit analyzes the employee's responses and extracts positive and negative points. Step 4: The feedback department provides feedback on the results and makes suggestions for improvement. For example, the feedback department makes specific suggestions for improvement based on the collected emotions and opinions.

[0076] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0077] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0078] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0079] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0080] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0081] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0082] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0083] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0084] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0085] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0086] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0087] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0088] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0089] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0090] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0091] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0092] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0093] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0094] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0095] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0096] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0097] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0098] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0099] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0100] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0101] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0102] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0103] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0104] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0105] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0106] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0108] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0109] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0110] 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.

[0111] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0112] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0113] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0114] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0115] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0116] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0117] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0118] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0119] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0120] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0121] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0122] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0123] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0124] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0125] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0126] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0127] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0128] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0129] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0130] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0131] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0132] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0133] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0134] 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.

[0135] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0136] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0137] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0138] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0139] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0140] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0141] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0142] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0143] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A generation AI that conducts engagement surveys in chat format using generation AI, a scenario generation unit that performs a dialogue based on a scenario; An emotion analysis department that analyzes employee emotions; A feedback unit that provides feedback on the results and suggests improvements. A system characterized by:

2. The generated AI is Generate questions optimized for the employee by referring to the employee's past interaction history 2. The system of claim 1.

3. The generated AI is Provide immediate feedback on the employee's answers and generate follow-up questions to deepen the dialogue 2. The system of claim 1.

4. The generated AI is Generate questions according to the employee's emotional state and engage in dialogue that elicits positive emotions 2. The system of claim 1.

5. The generated AI is The chat-style survey is expanded to a voice dialogue format, and the employee's emotions are analyzed using voice recognition technology.

2. The system of claim 1.

6. The generated AI is The chat-style survey is expanded to a video dialogue format, and facial expression recognition technology is used to analyze the emotions of the employees.

2. The system of claim 1.

7. The generated AI is Generate questions that are appropriate for the environment in which the employee conducts the chat-style survey 2. The system of claim 1.

8. The scenario generation unit Refer to the work history of the employee and generate a scenario optimized for the employee.

2. The system of claim 1.

Images