system

Abstract

The system according to this embodiment aims to understand the usage status of the generation AI tool and identify prompts that require priority improvement. [Solution] The system according to the embodiment comprises a questionnaire transmission unit, a questionnaire result analysis unit, and an identification unit. The questionnaire transmission unit transmits questionnaires to understand the usage status of prompts. The questionnaire result analysis unit analyzes the results of the questionnaires transmitted by the questionnaire transmission unit. The identification unit identifies prompts that require priority improvement based on the results obtained by the questionnaire result analysis unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to grasp the usage situation of a generation AI tool and identify prompts that need to be improved preferentially.

[0005] The system according to the embodiment aims to grasp the usage situation of a generation AI tool and identify prompts that need to be improved preferentially.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a questionnaire transmission unit, a questionnaire result analysis unit, and an identification unit. The questionnaire transmission unit transmits questionnaires to understand the usage status of prompts. The questionnaire result analysis unit analyzes the results of the questionnaires transmitted by the questionnaire transmission unit. The identification unit identifies prompts that require priority improvement based on the results obtained by the questionnaire result analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can understand the usage status of the generation AI tool and identify prompts that require priority improvement. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0028] (Example of form 1) The management platform according to an embodiment of the present invention is a system for improving the current situation where not all employees are able to use generation AI tools at the same level. While it is common practice to assign evangelists or AI utilization promoters to each team or department, listen to their needs, and provide appropriate AI tools (such as prompts), it is difficult to verify how much the provided prompts are being used, updated, and how useful they are for work. Therefore, we propose an idea to introduce a management platform into the company's generation AI tool usage environment to make it easier to understand the status of prompts created by AI utilization promoters. Specifically, a simple questionnaire is sent periodically to the people using the prompts, and prompts requiring priority improvement are identified based on the results. This mechanism can achieve both increased efficiency and an overall improvement in AI tool usage. First, evangelists or AI utilization promoters are assigned to each team or department, listen to their needs, and provide appropriate AI tools (such as prompts). Next, a management platform is introduced into the company's generation AI tool usage environment to verify how much the provided prompts are being used, updated, and how useful they are for work. This management platform makes it easier to understand the status of prompts created by AI utilization promoters. Furthermore, short surveys are regularly sent to the field users who use the prompts, and the results are used to identify prompts that require priority improvement. For example, the surveys include questions such as, "How often is this prompt used?", "How often is this prompt updated?", and "How helpful is this prompt in your work?". Based on the results of these surveys, AI utilization promoters identify prompts that require priority improvement and make those improvements. This system enables increased efficiency and overall improvement of AI tools. For example, by understanding prompt usage, it is possible to identify which prompts are effective and distribute effective prompts to other teams and departments. Also, by understanding prompt update status, outdated prompts can be updated in a timely manner to provide the latest information.Furthermore, by understanding how useful prompts are to business operations, it becomes possible to prioritize improving prompts that are directly related to those operations, thereby improving operational efficiency. In this way, by introducing a management platform into the internal environment for using generation AI tools, it becomes easier to understand the status of prompts created by AI utilization promoters, enabling the efficiency of AI tools and an overall improvement in performance. As a result, the management platform can efficiently grasp the usage status of generation AI tools and identify prompts that require priority improvement.

[0029] The management platform according to this embodiment comprises a survey transmission unit, a survey result analysis unit, and an identification unit. The survey transmission unit transmits surveys to understand the usage status of prompts. The survey transmission unit has a function to automatically transmit surveys periodically, for example. The survey transmission unit can also optimize the timing of survey transmission using AI. For example, the survey transmission unit transmits surveys at the optimal timing based on the user's work situation and emotional state. The survey result analysis unit analyzes the results of surveys transmitted by the survey transmission unit. The survey result analysis unit has a function to automatically aggregate and analyze survey results using AI, for example. The survey result analysis unit can understand the usage status of prompts in detail using statistical analysis of survey results and data mining techniques. For example, the survey result analysis unit evaluates the frequency and effectiveness of prompt usage based on the survey response data. The identification unit identifies prompts that require priority improvement based on the results obtained by the survey result analysis unit. The identification unit has a function to automatically identify prompts that require improvement by analyzing survey results using AI, for example. The identification unit can determine the priority order for prompt improvement based on the analysis data of the survey results. For example, the identification unit evaluates user dissatisfaction and low usage frequency from the survey results and identifies prompts that require improvement. This allows the management platform according to the embodiment to efficiently grasp the usage status of prompts and identify prompts that require priority improvement. Some or all of the above processing in the survey transmission unit, survey result analysis unit, and identification unit may be performed using AI or not. For example, the survey transmission unit may use AI to optimize the timing of survey transmission, the survey result analysis unit may use AI to automatically aggregate survey results, and the identification unit may use AI to identify prompts that require improvement.

[0030] The survey sending unit sends surveys to understand how prompts are being used. Specifically, the survey sending unit has the function to send surveys at the optimal time, taking into account the user's work situation and emotional state. For example, sending surveys after the peak of work or during relaxed times can improve the response rate. The survey sending unit uses AI to analyze the user's behavior patterns and past survey response history and automatically calculates the optimal sending timing. Furthermore, the survey sending unit can customize the content and format of surveys for each user. For example, different questions can be set according to the user's work content and position to obtain more specific feedback. The survey sending unit sends surveys using multiple communication methods such as email, push notifications, and SMS, allowing users to respond in the way that is most convenient for them. The survey sending unit also has the function to monitor the survey sending history and response status in real time and send reminders to users who have not responded. This allows the survey sending unit to send surveys efficiently and effectively and collect data to accurately understand how prompts are being used.

[0031] The Survey Results Analysis Department analyzes the results of surveys sent by the Survey Transmission Department. Specifically, the Survey Results Analysis Department uses AI to automatically aggregate survey results and utilizes statistical analysis and data mining techniques to gain a detailed understanding of prompt usage. For example, based on the response data, the Survey Results Analysis Department evaluates the frequency and effectiveness of prompt usage and clarifies user satisfaction and dissatisfaction. The AI ​​can analyze free-response answers using natural language processing technology and extract common themes and keywords. This makes it possible to efficiently collect user opinions and requests and identify specific areas for improvement. Furthermore, by comparing current survey data with past survey data, the Survey Results Analysis Department can grasp changes and trends in prompt usage and conduct long-term evaluations. For example, it can analyze increases and decreases in prompt usage frequency and fluctuations in user satisfaction over a specific period to evaluate the effectiveness of improvements. In addition, the Survey Results Analysis Department can use anomaly detection algorithms to detect unusual patterns and abnormal data early and respond quickly. As a result, the Survey Results Analysis Department can analyze prompt usage from multiple perspectives and provide valuable insights to improve the overall system performance.

[0032] The Specialist Unit identifies prompts that require priority improvement based on the results obtained by the Survey Results Analysis Unit. Specifically, the Specialist Unit has the functionality to automatically identify prompts that need improvement by analyzing survey results using AI and evaluating user dissatisfaction levels and low usage frequency. For example, the Specialist Unit lists prompts that users are particularly dissatisfied with or that are used infrequently, based on keywords and themes extracted from the survey results. Furthermore, the Specialist Unit can use multiple evaluation criteria to determine the priority of prompt improvements. For example, it comprehensively evaluates user dissatisfaction levels, usage frequency, and impact on work to identify the prompts that require the most improvement. The Specialist Unit can also predict the effectiveness of improvements and propose optimal improvement measures by considering past improvement history and feedback from other users. The Specialist Unit presents specific improvement plans for the identified prompts and instructs the development and operations teams to implement them. In this way, the Specialist Unit can efficiently grasp the usage status of prompts and improve the overall user experience of the system by identifying prompts that require priority improvement.

[0033] The survey sending unit includes an automatic survey sending function. For example, the survey sending unit includes a function to automatically send surveys periodically. The survey sending unit can also optimize the timing of survey sending using AI. For example, the survey sending unit sends surveys at the optimal time based on the user's work situation and emotional state. This allows for efficient survey sending through automatic transmission. Some or all of the above-described processes in the survey sending unit may be performed using AI or not. For example, the survey sending unit can use AI to optimize the timing of survey sending, sending surveys at the optimal time based on the user's work situation and emotional state.

[0034] The survey results analysis unit is equipped with an automatic aggregation function for survey results. For example, the survey results analysis unit can automatically aggregate and analyze survey results using AI. The survey results analysis unit can gain a detailed understanding of prompt usage using statistical analysis and data mining techniques for survey results. For example, the survey results analysis unit evaluates the frequency and effectiveness of prompt usage based on survey response data. This allows for rapid analysis of results through automatic aggregation of survey results. Some or all of the above-described processes in the survey results analysis unit may be performed using AI or not. For example, the survey results analysis unit can automatically aggregate survey results using AI and evaluate the frequency and effectiveness of prompt usage based on survey response data.

[0035] The identification unit identifies prompts that require priority improvement based on the survey results. The identification unit includes a function to automatically identify prompts that require improvement by analyzing the survey results using AI, for example. The identification unit can determine the priority order for improving prompts based on the analysis data of the survey results. For example, the identification unit evaluates user dissatisfaction levels and low usage frequency from the survey results and identifies prompts that require improvement. This makes it possible to identify prompts that require priority improvement based on the survey results. Some or all of the above processing in the identification unit may be performed using AI or not. For example, the identification unit can automatically identify prompts that require improvement by analyzing the survey results using AI.

[0036] The usage monitoring unit monitors the usage status of prompts in real time. The usage monitoring unit includes a function to monitor prompt usage status in real time, for example, using AI. The usage monitoring unit can monitor the frequency and duration of prompt usage in real time and detect abnormal usage patterns. For example, the usage monitoring unit issues an alert if the frequency of prompt usage drops sharply. This allows for a quick response by monitoring prompt usage status in real time. Some or all of the above processing in the usage monitoring unit may be performed using AI or not. For example, the usage monitoring unit can use AI to monitor prompt usage status in real time and detect abnormal usage patterns.

[0037] The update history management unit manages the update history of prompts. The update history management unit has a function to manage the update history of prompts using, for example, AI. The update history management unit can record the update date and time and update content of prompts and provide the latest information. For example, the update history management unit can automatically detect outdated prompts and notify prompts that need updating. In this way, the latest information can be provided by managing the update history of prompts. Some or all of the above processing in the update history management unit may be performed using AI or not using AI. For example, the update history management unit can use AI to manage the update history of prompts and automatically detect outdated prompts.

[0038] The survey sending unit analyzes past survey response history and selects the optimal survey format. For example, the survey sending unit can use AI to analyze past survey response history and prioritize selecting formats that users have preferred in the past (multiple-choice, open-ended, etc.). The survey sending unit can also create surveys based on formats in which users have shown high response rates in the past. Furthermore, the survey sending unit can identify formats that are easy for users to answer based on their past response history and send surveys in those formats. By selecting the optimal survey format based on past survey response history, the response rate is improved. Some or all of the above processing in the survey sending unit may be performed using AI or not. For example, the survey sending unit can use AI to analyze past survey response history and select the optimal survey format.

[0039] The survey sending unit filters surveys based on the user's current work status. For example, the survey sending unit may use AI to analyze the user's work status and temporarily withhold sending the survey if the user is in a meeting. It may also postpone sending the survey if the user is working on an important project. Furthermore, it may prioritize sending the survey if the user is on a break. This adjusts the timing of survey sending according to the user's work status, ensuring that it does not disrupt their work. Some or all of the above processing in the survey sending unit may be performed using AI or not. For example, the survey sending unit may use AI to analyze the user's work status and adjust the timing of survey sending.

[0040] The survey sending unit prioritizes sending surveys that are highly relevant to the user, taking into account the user's geographical location. For example, the survey sending unit can use AI to analyze the user's geographical location and, if the user is in a specific office, prioritize sending surveys related to that office. Furthermore, if the user is on a business trip, the survey sending unit can send surveys related to their business trip destination. Additionally, if the user is working from home, the survey sending unit can send surveys related to working from home. This allows for more appropriate feedback by sending surveys that are highly relevant based on the user's geographical location. Some or all of the above processing in the survey sending unit may be performed using AI or not. For example, the survey sending unit can use AI to analyze the user's geographical location and send highly relevant surveys.

[0041] The survey sending unit analyzes the user's social media activity and sends relevant surveys when sending surveys. For example, the survey sending unit may use AI to analyze the user's social media activity and, if the user mentions a specific topic on social media, send a survey related to that topic. The survey sending unit can also send surveys during times when the user is most active on social media. Furthermore, if the survey sending unit is seeking feedback on social media, it can send a survey related to that feedback. This allows for more appropriate feedback to be obtained by sending relevant surveys based on the user's social media activity. Some or all of the above processing in the survey sending unit may be performed using AI or not. For example, the survey sending unit can use AI to analyze the user's social media activity and send relevant surveys.

[0042] The survey results analysis department adjusts the level of detail of the analysis based on the importance of the responses during the analysis of survey results. For example, the survey results analysis department uses AI to evaluate the importance of responses and performs detailed analysis on highly important responses. The survey results analysis department can also perform a concise analysis on less important responses. Furthermore, the survey results analysis department can perform analysis with a moderate level of detail on responses of moderate importance. In this way, efficient analysis can be performed by adjusting the level of detail of the analysis based on the importance of the responses. Some or all of the above processes in the survey results analysis department may be performed using AI or not. For example, the survey results analysis department can use AI to evaluate the importance of responses and adjust the level of detail of the analysis.

[0043] The survey results analysis department applies different analysis algorithms depending on the category of the responses when analyzing survey results. For example, the survey results analysis department may use AI to classify the categories of responses and apply a technical analysis algorithm to responses to technical questions. Furthermore, the survey results analysis department may apply a business process analysis algorithm to responses to questions about business processes. In addition, the survey results analysis department may apply a satisfaction analysis algorithm to responses to questions about user satisfaction. By applying different analysis algorithms depending on the category of responses, more appropriate analysis can be performed. Some or all of the above processing in the survey results analysis department may be performed using AI or not. For example, the survey results analysis department may use AI to classify the categories of responses and apply different analysis algorithms.

[0044] The survey results analysis department determines the priority of analysis based on the submission date of responses. For example, the survey results analysis department may use AI to evaluate the submission date of responses and prioritize the analysis of recently submitted responses. The survey results analysis department may also postpone the analysis of older responses. Furthermore, the survey results analysis department may perform analysis with a moderate priority on responses submitted at a moderate time. This allows for efficient analysis by determining the priority of analysis based on the submission date of responses. Some or all of the above processes in the survey results analysis department may be performed using AI or not. For example, the survey results analysis department may use AI to evaluate the submission date of responses and determine the priority of analysis.

[0045] The Survey Results Analysis Department adjusts the order of analysis based on the relevance of the responses during the analysis of survey results. For example, the Survey Results Analysis Department uses AI to evaluate the relevance of responses and prioritizes the analysis of responses directly related to business operations. The Survey Results Analysis Department can also postpone the analysis of responses with low relevance. Furthermore, the Survey Results Analysis Department can analyze responses with moderate relevance with a moderate priority. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the responses. Some or all of the above processes in the Survey Results Analysis Department may be performed using AI or not. For example, the Survey Results Analysis Department can use AI to evaluate the relevance of responses and adjust the order of analysis.

[0046] The identification unit improves the accuracy of identification by considering the interrelationships of the survey results during the identification process. For example, the identification unit may use AI to evaluate the interrelationships of the survey results, integrate multiple survey results, and analyze the interrelationships to improve the accuracy of identification. The identification unit can also identify relevant prompts based on the interrelationships of the survey results. Furthermore, the identification unit may apply algorithms to improve the accuracy of identification by considering the interrelationships of the survey results. This improves the accuracy of identification by considering the interrelationships of the survey results. Some or all of the above processing in the identification unit may be performed using AI or not. For example, the identification unit may use AI to evaluate the interrelationships of the survey results and improve the accuracy of identification.

[0047] The identification unit considers the attribute information of the survey respondents when making identifications. For example, the identification unit may use AI to evaluate the attribute information of survey respondents and make identifications based on the job description of the survey respondents. The identification unit may also make identifications based on the survey respondents' years of experience. Furthermore, the identification unit may also make identifications based on the department to which the survey respondents belong. This allows for more appropriate identifications by considering the attribute information of the survey respondents. Some or all of the above processing in the identification unit may be performed using AI or not. For example, the identification unit may use AI to evaluate the attribute information of survey respondents and make identifications.

[0048] The identification unit performs identification while considering the geographical distribution of the survey results. For example, the identification unit uses AI to evaluate the geographical distribution of the survey results and prioritizes the identification of survey results related to a specific region. The identification unit can also perform identification on a region-by-region basis based on the geographical distribution. Furthermore, the identification unit can apply algorithms to improve the accuracy of identification by considering the geographical distribution. This allows for more appropriate identification by considering the geographical distribution of the survey results. Some or all of the above processing in the identification unit may be performed using AI or not. For example, the identification unit can use AI to evaluate the geographical distribution of the survey results and perform identification.

[0049] The identification unit improves the accuracy of identification by referring to relevant literature for the survey results at the time of identification. The identification unit can, for example, use AI to refer to relevant literature and apply an algorithm to improve the accuracy of identification. The identification unit can also improve the accuracy of identification based on the relevant literature. Furthermore, the identification unit can collect data to improve the accuracy of identification based on the relevant literature. As a result, the accuracy of identification is improved by referring to relevant literature for the survey results. Some or all of the above processing in the identification unit may be performed using AI or not using AI. For example, the identification unit can use AI to refer to relevant literature and improve the accuracy of identification.

[0050] The usage monitoring unit optimizes its monitoring algorithm by referring to past usage data when monitoring usage. For example, the usage monitoring unit can use AI to analyze past usage data and strengthen monitoring during periods of high usage frequency. The usage monitoring unit can also adjust its monitoring algorithm based on usage patterns using past usage data. Furthermore, the usage monitoring unit can optimize its algorithm for detecting abnormal usage patterns by referring to past usage data. In this way, the monitoring algorithm can be optimized by referring to past usage data. Some or all of the above processes in the usage monitoring unit may be performed using AI or not. For example, the usage monitoring unit can use AI to analyze past usage data and optimize its monitoring algorithm.

[0051] The usage monitoring unit determines the monitoring priority based on the submission date of usage data when monitoring usage status. For example, the usage monitoring unit may use AI to evaluate the submission date of usage data and prioritize monitoring of recently submitted usage data. The usage monitoring unit may also postpone monitoring older usage data. Furthermore, the usage monitoring unit may monitor usage data with a moderate submission date with a moderate priority. This allows for efficient monitoring by determining the monitoring priority based on the submission date of usage data. Some or all of the above processing in the usage monitoring unit may be performed using AI or not. For example, the usage monitoring unit may use AI to evaluate the submission date of usage data and determine the monitoring priority.

[0052] The update history management unit optimizes its management algorithm by referring to past update data when managing the update history. For example, the update history management unit uses AI to analyze past update data and prioritize the management of frequently updated prompts. The update history management unit can also adjust its management algorithm based on update patterns using past update data. Furthermore, the update history management unit can also optimize its algorithm for detecting abnormal update patterns by referring to past update data. In this way, the management algorithm can be optimized by referring to past update data. Some or all of the above processes in the update history management unit may be performed using AI or not. For example, the update history management unit can use AI to analyze past update data and optimize its management algorithm.

[0053] The update history management unit determines management priorities based on the submission date of update data when managing update history. For example, the update history management unit uses AI to evaluate the submission date of update data and prioritizes the management of recently submitted update data. The update history management unit can also postpone the management of older update data. Furthermore, the update history management unit can manage update data with a moderate level of priority. This allows for efficient management by determining management priorities based on the submission date of update data. Some or all of the above processes in the update history management unit may be performed using AI or not. For example, the update history management unit can use AI to evaluate the submission date of update data and determine management priorities.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The management platform can provide a dashboard that visualizes prompt usage in real time. For example, it can display the frequency and effectiveness of each prompt in a graph, allowing users to see at a glance which prompts are most effective. It can also simultaneously display the prompt update history and user feedback, enabling quick identification of areas for improvement. Furthermore, the dashboard is customizable, allowing it to display information tailored to user needs. This enables efficient monitoring of prompt usage and appropriate improvements.

[0056] The management platform can analyze prompt usage and automatically delete infrequently used prompts. For example, it can automatically detect and delete prompts that haven't been used for a certain period. It can also request confirmation before deleting infrequently used but important prompts for specific users. Furthermore, it can save a history of deleted prompts and restore them as needed. This streamlines prompt management and prevents unnecessary prompts from cluttering the system.

[0057] The management platform can have a function to automatically recommend the most suitable prompts based on their usage. For example, it can recommend prompts that have proven highly effective in specific tasks to other users. It can also prioritize the recommendation of frequently used prompts. Furthermore, it can analyze a user's past usage history and recommend prompts that are best suited to each individual user. This allows users to quickly find effective prompts, improving work efficiency.

[0058] The management platform can include features to evaluate the effectiveness of prompts based on their usage. For example, it can score prompts based on their frequency of use and contribution to business operations to identify high-performing prompts. It can also evaluate prompt effectiveness based on user feedback. Furthermore, it can periodically review prompt effectiveness and make improvements as needed. This allows for objective evaluation of prompt effectiveness and promotes the effective use of prompts.

[0059] The management platform can have a function to automatically adjust the update frequency of prompts based on their usage. For example, frequently used prompts will be updated more often to provide the latest information. Conversely, less frequently used prompts will be updated less frequently, allowing for more efficient use of resources. Furthermore, it is possible to adjust the prompt update frequency based on user feedback. This ensures that prompts are updated efficiently and always provide the latest information.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The survey sending unit sends surveys to understand the usage of prompts. The survey sending unit has a function to automatically send surveys periodically, for example. It can also use AI to optimize the timing of survey sending. For example, it can send surveys at the optimal time based on the user's work situation and emotional state. Step 2: The Survey Results Analysis Unit analyzes the results of the surveys sent by the Survey Transmission Unit. The Survey Results Analysis Unit has functions to automatically aggregate and analyze survey results, for example, using AI. By using statistical analysis and data mining techniques of the survey results, it is possible to understand the usage of prompts in detail. For example, the frequency and effectiveness of prompt usage can be evaluated based on the survey response data. Step 3: The identification unit identifies prompts that require priority improvement based on the results obtained by the survey results analysis unit. The identification unit has a function that automatically identifies prompts that require improvement by analyzing survey results using AI, for example. Based on the analysis data of the survey results, it can determine the priority order for improving prompts. For example, it can evaluate the level of user dissatisfaction and low usage frequency from the survey results and identify prompts that require improvement.

[0062] (Example of form 2) The management platform according to an embodiment of the present invention is a system for improving the current situation where not all employees are able to use generation AI tools at the same level. While it is common practice to assign evangelists or AI utilization promoters to each team or department, listen to their needs, and provide appropriate AI tools (such as prompts), it is difficult to verify how much the provided prompts are being used, updated, and how useful they are for work. Therefore, we propose an idea to introduce a management platform into the company's generation AI tool usage environment to make it easier to understand the status of prompts created by AI utilization promoters. Specifically, a simple questionnaire is sent periodically to the people using the prompts, and prompts requiring priority improvement are identified based on the results. This mechanism can achieve both increased efficiency and an overall improvement in AI tool usage. First, evangelists or AI utilization promoters are assigned to each team or department, listen to their needs, and provide appropriate AI tools (such as prompts). Next, a management platform is introduced into the company's generation AI tool usage environment to verify how much the provided prompts are being used, updated, and how useful they are for work. This management platform makes it easier to understand the status of prompts created by AI utilization promoters. Furthermore, short surveys are regularly sent to the field users who use the prompts, and the results are used to identify prompts that require priority improvement. For example, the surveys include questions such as, "How often is this prompt used?", "How often is this prompt updated?", and "How helpful is this prompt in your work?". Based on the results of these surveys, AI utilization promoters identify prompts that require priority improvement and make those improvements. This system enables increased efficiency and overall improvement of AI tools. For example, by understanding prompt usage, it is possible to identify which prompts are effective and distribute effective prompts to other teams and departments. Also, by understanding prompt update status, outdated prompts can be updated in a timely manner to provide the latest information.Furthermore, by understanding how useful prompts are to business operations, it becomes possible to prioritize improving prompts that are directly related to those operations, thereby improving operational efficiency. In this way, by introducing a management platform into the internal environment for using generation AI tools, it becomes easier to understand the status of prompts created by AI utilization promoters, enabling the efficiency of AI tools and an overall improvement in performance. As a result, the management platform can efficiently grasp the usage status of generation AI tools and identify prompts that require priority improvement.

[0063] The management platform according to this embodiment comprises a survey transmission unit, a survey result analysis unit, and an identification unit. The survey transmission unit transmits surveys to understand the usage status of prompts. The survey transmission unit has a function to automatically transmit surveys periodically, for example. The survey transmission unit can also optimize the timing of survey transmission using AI. For example, the survey transmission unit transmits surveys at the optimal timing based on the user's work situation and emotional state. The survey result analysis unit analyzes the results of surveys transmitted by the survey transmission unit. The survey result analysis unit has a function to automatically aggregate and analyze survey results using AI, for example. The survey result analysis unit can understand the usage status of prompts in detail using statistical analysis of survey results and data mining techniques. For example, the survey result analysis unit evaluates the frequency and effectiveness of prompt usage based on the survey response data. The identification unit identifies prompts that require priority improvement based on the results obtained by the survey result analysis unit. The identification unit has a function to automatically identify prompts that require improvement by analyzing survey results using AI, for example. The identification unit can determine the priority order for prompt improvement based on the analysis data of the survey results. For example, the identification unit evaluates user dissatisfaction and low usage frequency from the survey results and identifies prompts that require improvement. This allows the management platform according to the embodiment to efficiently grasp the usage status of prompts and identify prompts that require priority improvement. Some or all of the above processing in the survey transmission unit, survey result analysis unit, and identification unit may be performed using AI or not. For example, the survey transmission unit may use AI to optimize the timing of survey transmission, the survey result analysis unit may use AI to automatically aggregate survey results, and the identification unit may use AI to identify prompts that require improvement.

[0064] The survey sending unit sends surveys to understand how prompts are being used. Specifically, the survey sending unit has the function to send surveys at the optimal time, taking into account the user's work situation and emotional state. For example, sending surveys after the peak of work or during relaxed times can improve the response rate. The survey sending unit uses AI to analyze the user's behavior patterns and past survey response history and automatically calculates the optimal sending timing. Furthermore, the survey sending unit can customize the content and format of surveys for each user. For example, different questions can be set according to the user's work content and position to obtain more specific feedback. The survey sending unit sends surveys using multiple communication methods such as email, push notifications, and SMS, allowing users to respond in the way that is most convenient for them. The survey sending unit also has the function to monitor the survey sending history and response status in real time and send reminders to users who have not responded. This allows the survey sending unit to send surveys efficiently and effectively and collect data to accurately understand how prompts are being used.

[0065] The Survey Results Analysis Department analyzes the results of surveys sent by the Survey Transmission Department. Specifically, the Survey Results Analysis Department uses AI to automatically aggregate survey results and utilizes statistical analysis and data mining techniques to gain a detailed understanding of prompt usage. For example, based on the response data, the Survey Results Analysis Department evaluates the frequency and effectiveness of prompt usage and clarifies user satisfaction and dissatisfaction. The AI ​​can analyze free-response answers using natural language processing technology and extract common themes and keywords. This makes it possible to efficiently collect user opinions and requests and identify specific areas for improvement. Furthermore, by comparing current survey data with past survey data, the Survey Results Analysis Department can grasp changes and trends in prompt usage and conduct long-term evaluations. For example, it can analyze increases and decreases in prompt usage frequency and fluctuations in user satisfaction over a specific period to evaluate the effectiveness of improvements. In addition, the Survey Results Analysis Department can use anomaly detection algorithms to detect unusual patterns and abnormal data early and respond quickly. As a result, the Survey Results Analysis Department can analyze prompt usage from multiple perspectives and provide valuable insights to improve the overall system performance.

[0066] The Specialist Unit identifies prompts that require priority improvement based on the results obtained by the Survey Results Analysis Unit. Specifically, the Specialist Unit has the functionality to automatically identify prompts that need improvement by analyzing survey results using AI and evaluating user dissatisfaction levels and low usage frequency. For example, the Specialist Unit lists prompts that users are particularly dissatisfied with or that are used infrequently, based on keywords and themes extracted from the survey results. Furthermore, the Specialist Unit can use multiple evaluation criteria to determine the priority of prompt improvements. For example, it comprehensively evaluates user dissatisfaction levels, usage frequency, and impact on work to identify the prompts that require the most improvement. The Specialist Unit can also predict the effectiveness of improvements and propose optimal improvement measures by considering past improvement history and feedback from other users. The Specialist Unit presents specific improvement plans for the identified prompts and instructs the development and operations teams to implement them. In this way, the Specialist Unit can efficiently grasp the usage status of prompts and improve the overall user experience of the system by identifying prompts that require priority improvement.

[0067] The survey sending unit includes an automatic survey sending function. For example, the survey sending unit includes a function to automatically send surveys periodically. The survey sending unit can also optimize the timing of survey sending using AI. For example, the survey sending unit sends surveys at the optimal time based on the user's work situation and emotional state. This allows for efficient survey sending through automatic transmission. Some or all of the above-described processes in the survey sending unit may be performed using AI or not. For example, the survey sending unit can use AI to optimize the timing of survey sending, sending surveys at the optimal time based on the user's work situation and emotional state.

[0068] The survey results analysis unit is equipped with an automatic aggregation function for survey results. For example, the survey results analysis unit can automatically aggregate and analyze survey results using AI. The survey results analysis unit can gain a detailed understanding of prompt usage using statistical analysis and data mining techniques for survey results. For example, the survey results analysis unit evaluates the frequency and effectiveness of prompt usage based on survey response data. This allows for rapid analysis of results through automatic aggregation of survey results. Some or all of the above-described processes in the survey results analysis unit may be performed using AI or not. For example, the survey results analysis unit can automatically aggregate survey results using AI and evaluate the frequency and effectiveness of prompt usage based on survey response data.

[0069] The identification unit identifies prompts that require priority improvement based on the survey results. The identification unit includes a function to automatically identify prompts that require improvement by analyzing the survey results using AI, for example. The identification unit can determine the priority order for improving prompts based on the analysis data of the survey results. For example, the identification unit evaluates user dissatisfaction levels and low usage frequency from the survey results and identifies prompts that require improvement. This makes it possible to identify prompts that require priority improvement based on the survey results. Some or all of the above processing in the identification unit may be performed using AI or not. For example, the identification unit can automatically identify prompts that require improvement by analyzing the survey results using AI.

[0070] The usage monitoring unit monitors the usage status of prompts in real time. The usage monitoring unit includes a function to monitor prompt usage status in real time, for example, using AI. The usage monitoring unit can monitor the frequency and duration of prompt usage in real time and detect abnormal usage patterns. For example, the usage monitoring unit issues an alert if the frequency of prompt usage drops sharply. This allows for a quick response by monitoring prompt usage status in real time. Some or all of the above processing in the usage monitoring unit may be performed using AI or not. For example, the usage monitoring unit can use AI to monitor prompt usage status in real time and detect abnormal usage patterns.

[0071] The update history management unit manages the update history of prompts. The update history management unit has a function to manage the update history of prompts using, for example, AI. The update history management unit can record the update date and time and update content of prompts and provide the latest information. For example, the update history management unit can automatically detect outdated prompts and notify prompts that need updating. In this way, the latest information can be provided by managing the update history of prompts. Some or all of the above processing in the update history management unit may be performed using AI or not using AI. For example, the update history management unit can use AI to manage the update history of prompts and automatically detect outdated prompts.

[0072] The survey sending unit estimates the user's emotions and adjusts the timing of survey submission based on the estimated emotions. For example, the survey sending unit estimates the user's emotions using an emotion engine or generative AI, and if the user is stressed, it delays sending the survey until the user is relaxed. Conversely, if the user is relaxed, the survey sending unit can send the survey immediately to obtain quick feedback. Furthermore, if the user is busy, the survey sending unit can send the survey when their work is finished. In this way, by adjusting the timing of survey submission according to the user's emotions, the survey can be sent at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the survey sending unit may be performed using AI or not. For example, the survey sending unit can estimate the user's emotions using an emotion engine and adjust the timing of survey submission.

[0073] The survey sending unit analyzes past survey response history and selects the optimal survey format. For example, the survey sending unit can use AI to analyze past survey response history and prioritize selecting formats that users have preferred in the past (multiple-choice, open-ended, etc.). The survey sending unit can also create surveys based on formats in which users have shown high response rates in the past. Furthermore, the survey sending unit can identify formats that are easy for users to answer based on their past response history and send surveys in those formats. By selecting the optimal survey format based on past survey response history, the response rate is improved. Some or all of the above processing in the survey sending unit may be performed using AI or not. For example, the survey sending unit can use AI to analyze past survey response history and select the optimal survey format.

[0074] The survey sending unit filters surveys based on the user's current work status. For example, the survey sending unit may use AI to analyze the user's work status and temporarily withhold sending the survey if the user is in a meeting. It may also postpone sending the survey if the user is working on an important project. Furthermore, it may prioritize sending the survey if the user is on a break. This adjusts the timing of survey sending according to the user's work status, ensuring that it does not disrupt their work. Some or all of the above processing in the survey sending unit may be performed using AI or not. For example, the survey sending unit may use AI to analyze the user's work status and adjust the timing of survey sending.

[0075] The survey sending unit estimates the user's emotions and determines the priority of surveys based on the estimated emotions. For example, the survey sending unit might use an emotion engine or generative AI to estimate the user's emotions and, if the user is stressed, postpone less important surveys. Conversely, if the user is relaxed, the survey sending unit can prioritize sending more important surveys. Furthermore, if the user is busy, the survey sending unit can postpone less urgent surveys. This allows for the priority of important surveys by determining the priority of surveys according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the survey sending unit may be performed using AI or not. For example, the survey sending unit can use an emotion engine to estimate the user's emotions and determine the priority of surveys.

[0076] The survey sending unit prioritizes sending surveys that are highly relevant to the user, taking into account the user's geographical location. For example, the survey sending unit can use AI to analyze the user's geographical location and, if the user is in a specific office, prioritize sending surveys related to that office. Furthermore, if the user is on a business trip, the survey sending unit can send surveys related to their business trip destination. Additionally, if the user is working from home, the survey sending unit can send surveys related to working from home. This allows for more appropriate feedback by sending surveys that are highly relevant based on the user's geographical location. Some or all of the above processing in the survey sending unit may be performed using AI or not. For example, the survey sending unit can use AI to analyze the user's geographical location and send highly relevant surveys.

[0077] The survey sending unit analyzes the user's social media activity and sends relevant surveys when sending surveys. For example, the survey sending unit may use AI to analyze the user's social media activity and, if the user mentions a specific topic on social media, send a survey related to that topic. The survey sending unit can also send surveys during times when the user is most active on social media. Furthermore, if the survey sending unit is seeking feedback on social media, it can send a survey related to that feedback. This allows for more appropriate feedback to be obtained by sending relevant surveys based on the user's social media activity. Some or all of the above processing in the survey sending unit may be performed using AI or not. For example, the survey sending unit can use AI to analyze the user's social media activity and send relevant surveys.

[0078] The survey results analysis unit estimates the user's emotions and adjusts the analysis method of the survey results based on the estimated user emotions. For example, the survey results analysis unit estimates the user's emotions using an emotion engine or generative AI, and if the user is feeling stressed, it adopts a concise analysis method. If the user is relaxed, the survey results analysis unit can adopt a detailed analysis method. Furthermore, if the user is busy, the survey results analysis unit can adopt a rapid analysis method. By adjusting the analysis method of the survey results according to the user's emotions, a more appropriate analysis can be performed. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the survey results analysis unit may be performed using AI or not. For example, the survey results analysis unit can estimate the user's emotions using an emotion engine and adjust the analysis method of the survey results.

[0079] The survey results analysis department adjusts the level of detail of the analysis based on the importance of the responses during the analysis of survey results. For example, the survey results analysis department uses AI to evaluate the importance of responses and performs detailed analysis on highly important responses. The survey results analysis department can also perform a concise analysis on less important responses. Furthermore, the survey results analysis department can perform analysis with a moderate level of detail on responses of moderate importance. In this way, efficient analysis can be performed by adjusting the level of detail of the analysis based on the importance of the responses. Some or all of the above processes in the survey results analysis department may be performed using AI or not. For example, the survey results analysis department can use AI to evaluate the importance of responses and adjust the level of detail of the analysis.

[0080] The survey results analysis department applies different analysis algorithms depending on the category of the responses when analyzing survey results. For example, the survey results analysis department may use AI to classify the categories of responses and apply a technical analysis algorithm to responses to technical questions. Furthermore, the survey results analysis department may apply a business process analysis algorithm to responses to questions about business processes. In addition, the survey results analysis department may apply a satisfaction analysis algorithm to responses to questions about user satisfaction. By applying different analysis algorithms depending on the category of responses, more appropriate analysis can be performed. Some or all of the above processing in the survey results analysis department may be performed using AI or not. For example, the survey results analysis department may use AI to classify the categories of responses and apply different analysis algorithms.

[0081] The survey results analysis unit estimates the user's emotions and adjusts the display method of the survey results based on the estimated user emotions. For example, the survey results analysis unit estimates the user's emotions using an emotion engine or generative AI, and if the user is stressed, it provides a concise and highly visible display method. If the user is relaxed, the survey results analysis unit can provide a display method that includes detailed information. Furthermore, if the user is busy, the survey results analysis unit can provide a display method that gets straight to the point. In this way, by adjusting the display method of the survey results according to the user's emotions, a more appropriate display can be achieved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the survey results analysis unit may be performed using AI or not using AI. For example, the survey results analysis unit can estimate the user's emotions using an emotion engine and adjust the display method of the survey results.

[0082] The survey results analysis department determines the priority of analysis based on the submission date of responses. For example, the survey results analysis department may use AI to evaluate the submission date of responses and prioritize the analysis of recently submitted responses. The survey results analysis department may also postpone the analysis of older responses. Furthermore, the survey results analysis department may perform analysis with a moderate priority on responses submitted at a moderate time. This allows for efficient analysis by determining the priority of analysis based on the submission date of responses. Some or all of the above processes in the survey results analysis department may be performed using AI or not. For example, the survey results analysis department may use AI to evaluate the submission date of responses and determine the priority of analysis.

[0083] The Survey Results Analysis Department adjusts the order of analysis based on the relevance of the responses during the analysis of survey results. For example, the Survey Results Analysis Department uses AI to evaluate the relevance of responses and prioritizes the analysis of responses directly related to business operations. The Survey Results Analysis Department can also postpone the analysis of responses with low relevance. Furthermore, the Survey Results Analysis Department can analyze responses with moderate relevance with a moderate priority. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the responses. Some or all of the above processes in the Survey Results Analysis Department may be performed using AI or not. For example, the Survey Results Analysis Department can use AI to evaluate the relevance of responses and adjust the order of analysis.

[0084] The identification unit estimates the user's emotions and determines the priority of prompts to identify based on the estimated emotions. For example, the identification unit estimates the user's emotions using an emotion engine or generative AI, and if the user is stressed, it postpones less important prompts. Conversely, if the user is relaxed, the identification unit can prioritize identifying more important prompts. Furthermore, if the user is busy, the identification unit can postpone less urgent prompts. In this way, by determining the priority of prompts according to the user's emotions, important prompts can be identified preferentially. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the identification unit may be performed using AI or not. For example, the identification unit can estimate the user's emotions using an emotion engine and determine the priority of prompts.

[0085] The identification unit improves the accuracy of identification by considering the interrelationships of the survey results during the identification process. For example, the identification unit may use AI to evaluate the interrelationships of the survey results, integrate multiple survey results, and analyze the interrelationships to improve the accuracy of identification. The identification unit can also identify relevant prompts based on the interrelationships of the survey results. Furthermore, the identification unit may apply algorithms to improve the accuracy of identification by considering the interrelationships of the survey results. This improves the accuracy of identification by considering the interrelationships of the survey results. Some or all of the above processing in the identification unit may be performed using AI or not. For example, the identification unit may use AI to evaluate the interrelationships of the survey results and improve the accuracy of identification.

[0086] The identification unit considers the attribute information of the survey respondents when making identifications. For example, the identification unit may use AI to evaluate the attribute information of survey respondents and make identifications based on the job description of the survey respondents. The identification unit may also make identifications based on the survey respondents' years of experience. Furthermore, the identification unit may also make identifications based on the department to which the survey respondents belong. This allows for more appropriate identifications by considering the attribute information of the survey respondents. Some or all of the above processing in the identification unit may be performed using AI or not. For example, the identification unit may use AI to evaluate the attribute information of survey respondents and make identifications.

[0087] The identification unit estimates the user's emotions and adjusts the display method of the identified prompt based on the estimated user emotions. For example, the identification unit estimates the user's emotions using an emotion engine or generative AI and provides a simple and highly visible display method if the user is stressed. The identification unit can also provide a display method that includes detailed information if the user is relaxed. Furthermore, the identification unit can provide a concise display method if the user is busy. By adjusting the display method of the prompt according to the user's emotions, more appropriate displays can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the identification unit may be performed using AI or not. For example, the identification unit can estimate the user's emotions using an emotion engine and adjust the display method of the prompt.

[0088] The identification unit performs identification while considering the geographical distribution of the survey results. For example, the identification unit uses AI to evaluate the geographical distribution of the survey results and prioritizes the identification of survey results related to a specific region. The identification unit can also perform identification on a region-by-region basis based on the geographical distribution. Furthermore, the identification unit can apply algorithms to improve the accuracy of identification by considering the geographical distribution. This allows for more appropriate identification by considering the geographical distribution of the survey results. Some or all of the above processing in the identification unit may be performed using AI or not. For example, the identification unit can use AI to evaluate the geographical distribution of the survey results and perform identification.

[0089] The identification unit improves the accuracy of identification by referring to relevant literature for the survey results at the time of identification. The identification unit can, for example, use AI to refer to relevant literature and apply an algorithm to improve the accuracy of identification. The identification unit can also improve the accuracy of identification based on the relevant literature. Furthermore, the identification unit can collect data to improve the accuracy of identification based on the relevant literature. As a result, the accuracy of identification is improved by referring to relevant literature for the survey results. Some or all of the above processing in the identification unit may be performed using AI or not using AI. For example, the identification unit can use AI to refer to relevant literature and improve the accuracy of identification.

[0090] The usage monitoring unit estimates the user's emotions and adjusts the usage monitoring method based on the estimated user emotions. For example, the usage monitoring unit estimates the user's emotions using an emotion engine or generative AI, and reduces the monitoring frequency if the user is stressed. Conversely, the usage monitoring unit can increase the monitoring frequency if the user is relaxed. Furthermore, the usage monitoring unit can adjust the monitoring frequency if the user is busy. This allows for more appropriate monitoring by adjusting the usage monitoring method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the usage monitoring unit may be performed using AI or not. For example, the usage monitoring unit can estimate the user's emotions using an emotion engine and adjust the monitoring method.

[0091] The usage monitoring unit optimizes its monitoring algorithm by referring to past usage data when monitoring usage. For example, the usage monitoring unit can use AI to analyze past usage data and strengthen monitoring during periods of high usage frequency. The usage monitoring unit can also adjust its monitoring algorithm based on usage patterns using past usage data. Furthermore, the usage monitoring unit can optimize its algorithm for detecting abnormal usage patterns by referring to past usage data. In this way, the monitoring algorithm can be optimized by referring to past usage data. Some or all of the above processes in the usage monitoring unit may be performed using AI or not. For example, the usage monitoring unit can use AI to analyze past usage data and optimize its monitoring algorithm.

[0092] The usage monitoring unit estimates the user's emotions and adjusts the display method of usage status based on the estimated user emotions. For example, the usage monitoring unit estimates the user's emotions using an emotion engine or generative AI, and if the user is stressed, it provides a concise and highly visible display method. Furthermore, if the user is relaxed, the usage monitoring unit can provide a display method that includes detailed information. In addition, if the user is busy, the usage monitoring unit can provide a concise display method. This allows for more appropriate display by adjusting the usage status display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the usage monitoring unit may be performed using AI or not. For example, the usage monitoring unit can estimate the user's emotions using an emotion engine and adjust the display method accordingly.

[0093] The usage monitoring unit determines the monitoring priority based on the submission date of usage data when monitoring usage status. For example, the usage monitoring unit may use AI to evaluate the submission date of usage data and prioritize monitoring of recently submitted usage data. The usage monitoring unit may also postpone monitoring older usage data. Furthermore, the usage monitoring unit may monitor usage data with a moderate submission date with a moderate priority. This allows for efficient monitoring by determining the monitoring priority based on the submission date of usage data. Some or all of the above processing in the usage monitoring unit may be performed using AI or not. For example, the usage monitoring unit may use AI to evaluate the submission date of usage data and determine the monitoring priority.

[0094] The update history management unit estimates the user's emotions and adjusts the update history management method based on the estimated user emotions. For example, the update history management unit can estimate the user's emotions using an emotion engine or generative AI and provide a concise management method if the user is stressed. It can also provide a detailed management method if the user is relaxed. Furthermore, it can provide a quick management method if the user is busy. This allows for more appropriate management by adjusting the update history management method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the update history management unit may be performed using AI or not. For example, the update history management unit can estimate the user's emotions using an emotion engine and adjust the management method accordingly.

[0095] The update history management unit optimizes its management algorithm by referring to past update data when managing the update history. For example, the update history management unit uses AI to analyze past update data and prioritize the management of frequently updated prompts. The update history management unit can also adjust its management algorithm based on update patterns using past update data. Furthermore, the update history management unit can also optimize its algorithm for detecting abnormal update patterns by referring to past update data. In this way, the management algorithm can be optimized by referring to past update data. Some or all of the above processes in the update history management unit may be performed using AI or not. For example, the update history management unit can use AI to analyze past update data and optimize its management algorithm.

[0096] The update history management unit estimates the user's emotions and adjusts the display method of the update history based on the estimated emotions. For example, the update history management unit can estimate the user's emotions using an emotion engine or generative AI, and if the user is stressed, it provides a concise and highly visible display method. If the user is relaxed, the update history management unit can provide a display method that includes detailed information. Furthermore, if the user is busy, the update history management unit can provide a concise display method. In this way, by adjusting the display method of the update history according to the user's emotions, a more appropriate display can be achieved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the update history management unit may be performed using AI or not. For example, the update history management unit can estimate the user's emotions using an emotion engine and adjust the display method.

[0097] The update history management unit determines management priorities based on the submission date of update data when managing update history. For example, the update history management unit uses AI to evaluate the submission date of update data and prioritizes the management of recently submitted update data. The update history management unit can also postpone the management of older update data. Furthermore, the update history management unit can manage update data with a moderate level of priority. This allows for efficient management by determining management priorities based on the submission date of update data. Some or all of the above processes in the update history management unit may be performed using AI or not. For example, the update history management unit can use AI to evaluate the submission date of update data and determine management priorities.

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

[0099] The management platform can estimate the user's emotions and suggest improvements to prompts based on those estimates. For example, if a user is stressed, the system will prioritize suggesting prompts that help reduce stress. If the user is relaxed, it can suggest prompts that stimulate creativity. Furthermore, if the user is busy, it can suggest prompts that help them work more efficiently. This allows for suggesting improvements to prompts that are tailored to the user's emotions.

[0100] The management platform can provide a dashboard that visualizes prompt usage in real time. For example, it can display the frequency and effectiveness of each prompt in a graph, allowing users to see at a glance which prompts are most effective. It can also simultaneously display the prompt update history and user feedback, enabling quick identification of areas for improvement. Furthermore, the dashboard is customizable, allowing it to display information tailored to user needs. This enables efficient monitoring of prompt usage and appropriate improvements.

[0101] The management platform can estimate a user's emotions and adjust survey questions based on those estimates. For example, if a user is stressed, it can prioritize sending concise and easy-to-answer questions. Conversely, if a user is relaxed, it can send questions that request more detailed feedback. Furthermore, if a user is busy, it can send only the most important questions, postponing others. This adjusts survey questions to the user's emotions, leading to improved response rates.

[0102] The management platform can analyze prompt usage and automatically delete infrequently used prompts. For example, it can automatically detect and delete prompts that haven't been used for a certain period. It can also request confirmation before deleting infrequently used but important prompts for specific users. Furthermore, it can save a history of deleted prompts and restore them as needed. This streamlines prompt management and prevents unnecessary prompts from cluttering the system.

[0103] The management platform can estimate the user's emotions and adjust how prompts are displayed based on those estimates. For example, if a user is stressed, it can provide a simple and highly visible prompt. If the user is relaxed, it can provide a more detailed prompt. Furthermore, if the user is busy, it can provide a concise prompt. This allows prompts to be displayed in a way that suits the user's emotions, resulting in more relevant information being provided.

[0104] The management platform can have a function to automatically recommend the most suitable prompts based on their usage. For example, it can recommend prompts that have proven highly effective in specific tasks to other users. It can also prioritize the recommendation of frequently used prompts. Furthermore, it can analyze a user's past usage history and recommend prompts that are best suited to each individual user. This allows users to quickly find effective prompts, improving work efficiency.

[0105] The management platform can estimate the user's emotions and determine the priority for improving prompts based on those emotions. For example, if a user is stressed, prompts that alleviate that stress can be prioritized for improvement. If the user is relaxed, prompts that stimulate creativity can be prioritized for improvement. Furthermore, if the user is busy, prompts that help them work efficiently can be prioritized for improvement. This allows for prompt improvements that are tailored to the user's emotions.

[0106] The management platform can include features to evaluate the effectiveness of prompts based on their usage. For example, it can score prompts based on their frequency of use and contribution to business operations to identify high-performing prompts. It can also evaluate prompt effectiveness based on user feedback. Furthermore, it can periodically review prompt effectiveness and make improvements as needed. This allows for objective evaluation of prompt effectiveness and promotes the effective use of prompts.

[0107] The management platform can estimate the user's emotions and adjust the prompt's feedback method based on those estimates. For example, if the user is stressed, it can provide concise and positive feedback. If the user is relaxed, it can provide more detailed feedback. Furthermore, if the user is busy, it can provide concise feedback. This ensures that feedback is tailored to the user's emotions, promoting improvements to prompts.

[0108] The management platform can have a function to automatically adjust the update frequency of prompts based on their usage. For example, frequently used prompts will be updated more often to provide the latest information. Conversely, less frequently used prompts will be updated less frequently, allowing for more efficient use of resources. Furthermore, it is possible to adjust the prompt update frequency based on user feedback. This ensures that prompts are updated efficiently and always provide the latest information.

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

[0110] Step 1: The survey sending unit sends surveys to understand the usage of prompts. The survey sending unit has a function to automatically send surveys periodically, for example. It can also use AI to optimize the timing of survey sending. For example, it can send surveys at the optimal time based on the user's work situation and emotional state. Step 2: The Survey Results Analysis Unit analyzes the results of the surveys sent by the Survey Transmission Unit. The Survey Results Analysis Unit has functions to automatically aggregate and analyze survey results, for example, using AI. By using statistical analysis and data mining techniques of the survey results, it is possible to understand the usage of prompts in detail. For example, the frequency and effectiveness of prompt usage can be evaluated based on the survey response data. Step 3: The identification unit identifies prompts that require priority improvement based on the results obtained by the survey results analysis unit. The identification unit has a function that automatically identifies prompts that require improvement by analyzing survey results using AI, for example. Based on the analysis data of the survey results, it can determine the priority order for improving prompts. For example, it can evaluate the level of user dissatisfaction and low usage frequency from the survey results and identify prompts that require improvement.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0113] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements described above, including the survey transmission unit, survey result analysis unit, identification unit, usage status monitoring unit, and update history management unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the survey transmission unit transmits the survey by the control unit 46A of the smart device 14 and optimizes the transmission timing by the identification processing unit 290 of the data processing unit 12. The survey result analysis unit automatically aggregates and analyzes the survey results by the identification processing unit 290 of the data processing unit 12. The identification unit identifies prompts that require priority improvement by the identification processing unit 290 of the data processing unit 12. The usage status monitoring unit monitors the usage status of prompts in real time by the control unit 46A of the smart device 14. The update history management unit manages the update history of prompts by the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

[0116] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0122] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0126] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the questionnaire transmission unit, questionnaire result analysis unit, identification unit, usage status monitoring unit, and update history management unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the questionnaire transmission unit transmits the questionnaire using the control unit 46A of the smart glasses 214 and optimizes the transmission timing using the identification processing unit 290 of the data processing unit 12. The questionnaire result analysis unit automatically aggregates and analyzes the questionnaire results using the identification processing unit 290 of the data processing unit 12. The identification unit identifies prompts that require priority improvement using the identification processing unit 290 of the data processing unit 12. The usage status monitoring unit monitors the usage status of prompts in real time using the control unit 46A of the smart glasses 214. The update history management unit manages the update history of prompts using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

[0132] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0139] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the questionnaire transmission unit, questionnaire result analysis unit, identification unit, usage status monitoring unit, and update history management unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the questionnaire transmission unit transmits the questionnaire using the control unit 46A of the headset terminal 314 and optimizes the transmission timing using the identification processing unit 290 of the data processing unit 12. The questionnaire result analysis unit automatically aggregates and analyzes the questionnaire results using the identification processing unit 290 of the data processing unit 12. The identification unit identifies prompts that require priority improvement using the identification processing unit 290 of the data processing unit 12. The usage status monitoring unit monitors the usage status of prompts in real time using the control unit 46A of the headset terminal 314. The update history management unit manages the update history of prompts using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

[0148] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0151] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0154] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0155] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0156] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements described above, including the questionnaire transmission unit, questionnaire result analysis unit, identification unit, usage status monitoring unit, and update history management unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the questionnaire transmission unit transmits questionnaires using the control unit 46A of the robot 414 and optimizes the transmission timing using the identification processing unit 290 of the data processing unit 12. The questionnaire result analysis unit automatically aggregates and analyzes questionnaire results using the identification processing unit 290 of the data processing unit 12. The identification unit identifies prompts that require priority improvement using the identification processing unit 290 of the data processing unit 12. The usage status monitoring unit monitors the usage status of prompts in real time using the control unit 46A of the robot 414. The update history management unit manages the update history of prompts using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0164] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0166] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0167] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0168] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0172] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0173] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0174] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0175] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0176] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0177] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0179] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0180] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0181] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0182] (Note 1) A survey sending unit that sends a survey to understand the usage status of prompts, A survey results analysis unit analyzes the results of the surveys sent by the aforementioned survey transmission unit, The system includes an identification unit that identifies prompts requiring priority improvement based on the results obtained by the aforementioned questionnaire result analysis unit. A system characterized by the following features. (Note 2) The aforementioned questionnaire transmission unit is: Features an automatic survey submission function. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned survey results analysis department, It includes a function for automatically aggregating survey results. The system described in Appendix 1, characterized by the features described herein. (Note 4) The specified part is, Based on the survey results, identify prompts that need priority improvement. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a usage monitoring unit that monitors prompt usage in real time. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes an update history management unit that manages the update history of the prompt. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned questionnaire transmission unit is: The system estimates the user's emotions and adjusts the timing of sending surveys based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned questionnaire transmission unit is: We analyze past survey response history to select the most suitable survey format. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned questionnaire transmission unit is: When submitting a survey, filtering is performed based on the user's current work situation. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned questionnaire transmission unit is: The system estimates user sentiment and prioritizes survey questions based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned questionnaire transmission unit is: When sending surveys, the system prioritizes sending surveys that are highly relevant to the user, taking into account their geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned questionnaire transmission unit is: When sending out surveys, we analyze the user's social media activity and send relevant surveys. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned survey results analysis department, We estimate the user's emotions and adjust the analysis method of the survey results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned survey results analysis department, When analyzing survey results, adjust the level of detail in the analysis based on the importance of the responses. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned survey results analysis department, When analyzing survey results, different analysis algorithms are applied depending on the category of the response. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned survey results analysis department, The system estimates the user's emotions and adjusts how survey results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned survey results analysis department, When analyzing survey results, prioritize the analysis based on when the responses were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned survey results analysis department, When analyzing survey results, adjust the order of analysis based on the relevance of the responses. The system described in Appendix 1, characterized by the features described herein. (Note 19) The specified part is, It estimates the user's emotions and determines the priority of specific prompts based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The specified part is, At specific times, improve the accuracy of specific tasks by considering the interrelationships of survey results. The system described in Appendix 1, characterized by the features described herein. (Note 21) The specified part is, When identifying individuals, the attribute information of the survey respondents is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The specified part is, We estimate the user's emotions and adjust how prompts are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The specified part is, When identifying individuals, the geographical distribution of the survey results should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The specified part is, When a specific situation arises, we refer to relevant literature related to the survey results to improve the accuracy of that specific situation. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned usage status monitoring unit, We estimate user sentiment and adjust usage monitoring methods based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned usage status monitoring unit, When monitoring usage, the monitoring algorithm is optimized by referring to past usage data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned usage status monitoring unit, The system estimates the user's emotions and adjusts how usage data is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned usage status monitoring unit, When monitoring usage, the monitoring priority is determined based on when the usage data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned update history management unit, We estimate user sentiment and adjust how update history is managed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned update history management unit, When managing the update history, the management algorithm is optimized by referring to past update data. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned update history management unit, It estimates the user's sentiment and adjusts how the update history is displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned update history management unit, When managing the update history, prioritize management based on when the update data was submitted. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A survey sending unit that sends a survey to understand the usage status of prompts, A survey results analysis unit analyzes the results of the surveys sent by the aforementioned survey transmission unit, The system includes an identification unit that identifies prompts requiring priority improvement based on the results obtained by the aforementioned questionnaire result analysis unit. A system characterized by the following features.

2. The aforementioned questionnaire transmission unit is: Features an automatic survey submission function. The system according to feature 1.

3. The aforementioned survey results analysis department, It includes a function for automatically aggregating survey results. The system according to feature 1.

4. The specified part is, Based on the survey results, identify prompts that need priority improvement. The system according to feature 1.

5. It includes a usage monitoring unit that monitors prompt usage in real time. The system according to feature 1.

6. It includes an update history management unit that manages the update history of the prompt. The system according to feature 1.

7. The aforementioned questionnaire transmission unit is: The system estimates the user's emotions and adjusts the timing of sending surveys based on those estimated emotions. The system according to feature 1.

8. The aforementioned questionnaire transmission unit is: We analyze past survey response history to select the most suitable survey format. The system according to feature 1.

9. The aforementioned questionnaire transmission unit is: When submitting a survey, filtering is performed based on the user's current work situation. The system according to feature 1.

10. The aforementioned questionnaire transmission unit is: The system estimates user sentiment and prioritizes survey questions based on the estimated sentiment. The system according to feature 1.

Images