system

Abstract

The system according to this embodiment aims to analyze VOC data, efficiently propose improvements, and automatically share them with relevant parties. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a proposal unit, and a sharing unit. The collection unit collects VOC data. The analysis unit analyzes the VOC data collected by the collection unit. The proposal unit makes improvement proposals based on the data analyzed by the analysis unit. The sharing unit automatically shares the improvement proposal document created by the proposal unit with relevant parties.

Description

Technical Field

[0006] , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the process of efficiently extracting useful improvement proposals from VOC data and sharing them with relevant parties is complicated.

[0005] The system according to the embodiment aims to analyze VOC data, efficiently make improvement proposals, and automatically share them with relevant parties.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an analysis unit, a proposal unit, and a sharing unit. The collection unit collects VOC data. The analysis unit analyzes the VOC data collected by the collection unit. The proposal unit makes improvement proposals based on the data analyzed by the analysis unit. The sharing unit automatically shares the improvement proposal document created by the proposal unit with relevant parties. [Effects of the Invention]

[0007] The system according to this embodiment can analyze VOC data, efficiently propose improvements, and automatically share them with relevant parties. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applicable to the communication I / F include wireless communication standards including 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 AI ​​agent system according to an embodiment of the present invention is a system for improving services by utilizing customer feedback (VOC) in service operations. This AI agent system is a mechanism in which an AI agent, including a generation AI, reads VOC and makes improvement suggestions from various angles. As a result, people are freed from sorting through noisy minorities and creating proposals, and can easily request improvement suggestions repeatedly through dialogue with the AI ​​agent. As a result, the improvement cycle is dramatically improved, service quality is enhanced, and user satisfaction is increased. For example, since VOC contains suggestions of different levels of detail and requests that do not align with the purpose of the service, it is necessary to select them based on basic service knowledge in order to actually implement improvements. Therefore, the AI ​​agent, including a generation AI, is fed VOC and makes improvement suggestions from various angles. For example, by having the AI ​​read records of inquiry emails and calls, and further training it on service functions, it can think of ways to improve. A dialogue UI is provided, allowing planning staff to implement improvement measures through dialogue with the AI. Specifically, it consists of the following steps. First, VOC data is collected. For example, data such as email inquiry texts and call handling records are collected. Next, the collected VOC data is fed into an AI agent, including a generating AI. The AI ​​agent analyzes the collected data and identifies noisy minorities. Furthermore, it learns basic service knowledge and devises improvement measures by comparing it with the VOC data. For example, it learns from documentation, specifications, requirements definitions, and help pages related to service functions. Next, the AI ​​agent makes improvement suggestions. For example, based on the VOC data, it determines which voices are useful and which requests are realistic, and makes improvement suggestions. Furthermore, through a conversational UI, planners can implement improvement measures by interacting with the AI ​​agent. For example, they can give instructions to the AI ​​agent such as "this voice is noise" or "this voice is important," and the AI ​​agent will make improvement suggestions based on that. Finally, the AI ​​agent creates an improvement proposal document and automatically shares it with relevant parties. For example, it creates a document summarizing this month's VOC topics and improvement suggestions and shares them with relevant parties.This dramatically improves the improvement cycle in service operations, enhances service quality, and increases user satisfaction. As a result, the AI ​​agent system can dramatically improve the improvement cycle in service operations, enhance service quality, and increase user satisfaction.

[0029] The AI ​​agent system according to this embodiment comprises a collection unit, an analysis unit, a proposal unit, and a sharing unit. The collection unit collects VOC data. VOC data includes, but is not limited to, customer feedback, complaints, and inquiries. The collection unit collects VOC data such as email inquiry texts and call handling records. The collection unit can also automatically collect VOC data using AI. The analysis unit analyzes the VOC data collected by the collection unit. The analysis unit analyzes the collected VOC data and sorts out noisy minorities, for example. Noisy minorities include, for example, data sorted based on data reliability and importance. The analysis unit can also analyze VOC data using AI. The proposal unit makes improvement suggestions based on the data analyzed by the analysis unit. The proposal unit learns basic service knowledge and devise improvement measures in comparison with VOC data, for example. Basic service knowledge includes, for example, basic service functions and basic customer service. The proposal unit can also make improvement suggestions using AI. The sharing unit automatically shares improvement proposals created by the proposal unit with relevant parties. For example, the sharing unit creates this month's VOC topics and improvement proposals and shares them with relevant parties. The sharing unit can also automatically create and share improvement proposals using AI. This enables the AI ​​agent system according to the embodiment to efficiently collect, analyze, propose improvements to, and share VOC data.

[0030] The collection unit collects VOC data. VOC data includes, but is not limited to, customer feedback, complaints, and inquiries. The collection unit collects VOC data such as email inquiry texts and call handling records. The collection unit can also automatically collect VOC data using AI. Specifically, the collection unit has an interface for automatically collecting emails, chat messages, and telephone recordings from customers. This data is converted into text data using natural language processing (NLP) technology and stored in a database. For example, email inquiry texts are automatically retrieved from the mail server and their content is analyzed by a text analysis engine. Call handling records are converted into text using speech recognition technology, and the content and tone of customer statements are analyzed. Furthermore, the collection unit can also collect VOC data from public platforms such as social networking services (SNS) and online forums. This makes it possible to collect a wide range of customer voices and build a comprehensive database. The collection unit collects this data in real time and provides it to the analysis unit, enabling a rapid response. The collection unit also has a filtering function to remove data duplication and noise, maintaining the quality of the collected data. This allows the data collection unit to efficiently and accurately collect VOC data, improving the overall system performance.

[0031] The analysis unit analyzes the VOC data collected by the collection unit. For example, the analysis unit analyzes the collected VOC data and sorts out noisy minorities. Noisy minorities include data that can be sorted out based on reliability and importance, for example. The analysis unit can also analyze VOC data using AI. Specifically, the analysis unit uses natural language processing (NLP) technology to analyze text data and extract customer opinions and sentiments. For example, it classifies positive and negative opinions from customer feedback and identifies frequently occurring keywords and phrases. It also analyzes complaints and inquiries to extract common problems and areas for improvement. Furthermore, the analysis unit can learn data patterns using machine learning algorithms and automatically sort out noisy minorities. For example, based on past data, it can identify unreliable or unimportant data and exclude it from the analysis results. This allows the analysis unit to provide accurate analysis results based on reliable data. The analysis unit analyzes data in real time, enabling rapid responses. Furthermore, the analysis unit can utilize historical data and statistical information to evaluate long-term trends and risks. This allows the analysis unit to efficiently and accurately analyze VOC data, improving the reliability and safety of the entire system.

[0032] The Proposal Department makes improvement suggestions based on data analyzed by the Analysis Department. For example, the Proposal Department learns fundamental service knowledge and devise improvement measures by comparing it with VOC data. Fundamental service knowledge includes, for example, basic service functions and basic customer service. The Proposal Department can also make improvement suggestions using AI. Specifically, the Proposal Department uses machine learning algorithms to integrate analysis results and fundamental service knowledge and automatically generate optimal improvement measures. For example, if customer feedback indicates many complaints about a particular service function, it will propose improvements to that function. Also, if the content of complaints indicates problems in the customer service process, it will propose a review and improvement of that process. The Proposal Department provides these improvement measures as concrete action plans and presents them in a way that is easy for stakeholders to implement. Furthermore, the Proposal Department can evaluate the effectiveness of past improvement measures and continuously optimize them. For example, it can analyze the results of past improvement measures and prioritize proposing measures that were highly effective. In addition, the Proposal Department can use AI to automatically generate new improvement measures, improving the diversity and accuracy of the proposed content. This allows the proposal department to quickly provide effective improvement suggestions based on analysis results, supporting improvements in service quality and customer satisfaction.

[0033] The sharing department automatically shares improvement proposals created by the proposal department with relevant parties. For example, the sharing department creates and shares this month's VOC topics and improvement proposals with relevant parties. The sharing department can also automatically create and share improvement proposals using AI. Specifically, the sharing department automatically generates reports for relevant parties based on the improvement proposals provided by the proposal department. These reports include an overview of this month's VOC data, key topics, and proposed improvement measures. These reports are visually represented using graphs and charts so that relevant parties can easily understand them. Furthermore, the sharing department has a function to automatically distribute reports to relevant parties. For example, it can distribute reports regularly via email or the company's information sharing system. The sharing department can also collect feedback from relevant parties and use it to improve the report content and the accuracy of the proposals. Through these functions, the sharing department facilitates information sharing among relevant parties and promotes the implementation of improvement proposals. In addition, the sharing department can monitor the distribution status of reports and the viewing status of relevant parties, and send reminders as needed. This allows the shared section to support the reliable sharing and implementation of proposals, maximizing the overall effectiveness of the system.

[0034] The collection unit can collect VOC data such as email inquiry texts and call handling records. For example, the collection unit can collect email inquiry texts that include questions and complaints from customers. The collection unit can also collect call handling records that include the content of conversations with customers and summaries of those conversations. For example, the collection unit can automatically collect inquiry emails from customers and save them as VOC data. The collection unit can also record conversations with customers and automatically create summaries of those conversations. This allows the collection unit to broaden the scope of VOC data collection and obtain more information. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input inquiry emails from customers into a generating AI and have the generating AI perform the VOC data collection.

[0035] The analysis unit can analyze the collected VOC data and separate out noisy minorities. For example, the analysis unit can analyze the collected VOC data and separate out noisy minorities based on the reliability and importance of the data. Noisy minorities include, for example, data with low reliability or low importance. The analysis unit can also analyze VOC data using AI. For example, the analysis unit can input the collected VOC data into a generating AI and have the generating AI perform the sorting out of noisy minorities. This allows the analysis unit to efficiently extract important VOC data.

[0036] The proposal department can learn fundamental service knowledge and devise improvement measures by comparing it with VOC data. For example, the proposal department can learn fundamental service knowledge such as the basic functions of the service and the basics of customer service. Fundamental service knowledge includes, for example, documentation, specifications, requirements definitions, and help pages related to service functions. The proposal department can also use AI to learn fundamental service knowledge and devise improvement measures by comparing it with VOC data. For example, the proposal department can input documentation related to service functions into a generating AI and have the generating AI perform the learning of fundamental service knowledge. As a result, the proposal department can devise more appropriate improvement measures by learning fundamental service knowledge.

[0037] The proposal department can implement improvement measures through dialogue with project managers via a conversational UI. For example, the proposal department can have project managers give instructions through the conversational UI, such as "This voice is noise" or "This voice is important," and an AI agent will make improvement suggestions based on those instructions. The conversational UI includes, for example, the dialogue interface and the flow of the dialogue. The proposal department can also implement improvement measures through the conversational UI using AI. For example, the proposal department can input the conversational UI into a generating AI and have the generating AI execute a dialogue with the project manager. This allows the proposal department to implement improvement measures through the conversational UI while project managers interact with an AI agent.

[0038] The shared department can create this month's VOC topics and improvement proposals and share them with stakeholders. For example, the shared department can create this month's VOC topics and improvement proposals. This month's VOC topics may include frequently occurring issues or customer concerns. The shared department can also use AI to automatically create this month's VOC topics and improvement proposals and share them with stakeholders. For example, the shared department can input this month's VOC topics into a generation AI and have the generation AI create improvement proposals. This streamlines information sharing by allowing the shared department to automatically create and share this month's VOC topics and improvement proposals with stakeholders.

[0039] The data collection unit can analyze a user's past inquiry history and select the optimal data collection method. For example, if a user has previously made an inquiry via email, the data collection unit will collect VOC data via email. If a user has previously made an inquiry via telephone, the data collection unit can prioritize collecting VOC data via telephone. If a user has previously made an inquiry via chat, the data collection unit can also collect VOC data via chat. In this way, the data collection unit can select the optimal data collection method by analyzing a user's past inquiry history. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input a user's past inquiry history into a generating AI and have the generating AI select the optimal data collection method.

[0040] The data collection unit can filter VOC data based on the user's current service usage and areas of interest. For example, if a user frequently uses a particular service, the data collection unit will prioritize collecting VOC data related to that service. If a user has a specific area of ​​interest, the data collection unit can also collect VOC data related to that area. If a user is trying a new service, the data collection unit can also collect initial feedback on that service. This allows the data collection unit to collect highly relevant data by filtering based on the user's current service usage and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on the user's current service usage and areas of interest into a generating AI and have the generating AI perform the filtering.

[0041] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location when collecting VOC data. For example, if the user is in a specific region, the data collection unit will prioritize the collection of VOC data related to that region. If the user is traveling, the data collection unit can also collect VOC data related to the travel destination. If the user is at home, the data collection unit can also collect VOC data related to services around their home. In this way, the data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's geographical location information into a generating AI and have the generating AI perform the collection of VOC data.

[0042] The data collection unit can analyze a user's social media activity and collect relevant data when collecting VOC data. For example, if a user mentions a particular service on social media, the data collection unit can collect VOC data related to that service. If a user discusses a particular issue on social media, the data collection unit can also collect VOC data related to that issue. If a user posts about a particular event on social media, the data collection unit can also collect VOC data related to that event. In this way, the data collection unit can collect relevant data by analyzing a user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on a user's social media activity into a generating AI and have the generating AI perform the collection of VOC data.

[0043] The analysis unit can adjust the level of detail of the analysis based on the importance of the VOC data during the analysis. For example, the analysis unit can perform a detailed analysis on highly important VOC data to identify specific areas for improvement. For less important VOC data, the analysis unit can perform an analysis to grasp the overall trend. For moderately important VOC data, the analysis unit can apply normal analysis criteria. In this way, the analysis unit can perform a detailed analysis on important data by adjusting the level of detail of the analysis based on the importance of the VOC data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the importance of the VOC data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0044] The analysis unit can apply different analysis algorithms depending on the category of the VOC data during analysis. For example, the analysis unit can apply an analysis algorithm specialized for service improvement to VOC data related to services. The analysis unit can also apply an analysis algorithm specialized for product improvement to VOC data related to products. The analysis unit can also apply an analysis algorithm specialized for support improvement to VOC data related to support. In this way, the analysis unit can perform more appropriate analysis by applying different analysis algorithms depending on the category of the VOC data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the categories of the VOC data into a generating AI and have the generating AI execute the application of the analysis algorithm.

[0045] The analysis unit can determine the priority of analysis based on the submission timing of VOC data during the analysis process. For example, the analysis unit can prioritize the analysis of recently submitted VOC data to ensure a quick response. The analysis unit can also periodically analyze previously submitted VOC data to grasp long-term trends. The analysis unit can also prioritize the analysis of VOC data submitted after a specific event to evaluate the impact of the event. This allows the analysis unit to respond quickly by determining the priority of analysis based on the submission timing of VOC data. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input the submission timing of VOC data into a generating AI and have the generating AI determine the priority of analysis.

[0046] The analysis unit can adjust the order of analysis based on the relevance of the VOC data during the analysis. For example, the analysis unit may prioritize the analysis of highly relevant VOC data to identify important areas for improvement. The analysis unit may also analyze VOC data with a moderate level of relevance in the normal order. The analysis unit may also postpone the analysis of VOC data with a low level of relevance. In this way, the analysis unit can prioritize the analysis of important data by adjusting the order of analysis based on the relevance of the VOC data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit may input the relevance of the VOC data into a generating AI and have the generating AI perform the adjustment of the analysis order.

[0047] The proposal unit can adjust the level of detail of a proposal based on its importance when it makes a proposal. For example, for high-importance improvement proposals, the proposal unit will provide a detailed proposal outlining specific areas for improvement. For low-importance improvement proposals, the proposal unit may provide a proposal that shows the overall trend. For medium-importance improvement proposals, the proposal unit may apply the normal level of detail. In this way, the proposal unit can provide detailed proposals for important proposals by adjusting the level of detail based on the importance of the improvement proposal. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input the importance of the improvement proposal into a generating AI and have the generating AI perform the adjustment of the level of detail of the proposal.

[0048] The proposal unit can apply different proposal algorithms depending on the category of the improvement suggestion when making a proposal. For example, for a service improvement suggestion, the proposal unit can apply a proposal algorithm specialized in service improvement. For a product improvement suggestion, the proposal unit can also apply a proposal algorithm specialized in product improvement. For a support improvement suggestion, the proposal unit can also apply a proposal algorithm specialized in support improvement. In this way, the proposal unit can make more appropriate suggestions by applying different proposal algorithms depending on the category of the improvement suggestion. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input the category of the improvement suggestion into a generation AI and have the generation AI execute the application of the proposal algorithm.

[0049] The proposal department can prioritize proposals based on when they are submitted. For example, the proposal department can prioritize recently submitted proposals to ensure a quick response. The proposal department can also periodically submit previously submitted proposals to understand long-term trends. The proposal department can also prioritize proposals submitted after a specific event to evaluate the impact of that event. This allows the proposal department to respond quickly by prioritizing proposals based on when they are submitted. Some or all of the above processes in the proposal department may be performed using AI or not. For example, the proposal department can input the submission dates of improvement proposals into a generating AI and have the generating AI determine the priority of the proposals.

[0050] The proposal unit can adjust the order of improvement suggestions based on their relevance when making a proposal. For example, the proposal unit can prioritize highly relevant improvement suggestions to identify important areas for improvement. The proposal unit can also propose moderately relevant improvement suggestions in the usual order. The proposal unit can also postpone proposing less relevant improvement suggestions. In this way, the proposal unit can prioritize important suggestions by adjusting the order of suggestions based on their relevance. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input the relevance of improvement suggestions into a generating AI and have the generating AI perform the adjustment of the order of suggestions.

[0051] The sharing function can adjust the level of detail of information shared based on the roles and responsibilities of the stakeholders. For example, the sharing function can share overall trends and key areas for improvement concisely with management. It can also share specific areas for improvement and detailed information with field staff. It can also share overall trends and specific areas for improvement in a balanced way with middle management. In this way, the sharing function can share information appropriately by adjusting the level of detail based on the roles and responsibilities of the stakeholders. Some or all of the above processing in the sharing function may be performed using AI or not. For example, the sharing function can input data on the roles and responsibilities of stakeholders into a generating AI and have the generating AI perform the adjustment of the level of detail of the information.

[0052] The sharing unit can select the optimal sharing method by referring to past sharing history when sharing information. For example, the sharing unit may prioritize sharing via email based on information previously shared via email. It may also prioritize sharing in meetings based on information previously shared in meetings. It may also prioritize sharing via chat based on information previously shared via chat. In this way, the sharing unit can select the optimal sharing method by referring to past sharing history. Some or all of the above processing in the sharing unit may be performed using AI or not. For example, the sharing unit can input past sharing history into a generating AI and have the generating AI select the optimal sharing method.

[0053] The sharing function can select the optimal sharing method by considering the geographical location information of the stakeholders during the sharing process. For example, if stakeholders are in different regions, the sharing function may prioritize online sharing. If stakeholders are in the same office, the sharing function may also prioritize in-person sharing. If stakeholders are traveling, the sharing function may also share via mobile devices. This allows the sharing function to select the optimal sharing method by considering the geographical location information of the stakeholders. Some or all of the above processing in the sharing function may be performed using AI or not. For example, the sharing function can input the geographical location information of stakeholders into a generating AI and have the generating AI select the optimal sharing method.

[0054] The sharing unit can analyze the social media activity of stakeholders and share relevant information when sharing. For example, if a stakeholder mentions a specific topic on social media, the sharing unit can share information related to that topic. If a stakeholder discusses a specific issue on social media, the sharing unit can also share information related to that issue. If a stakeholder posts about a specific event on social media, the sharing unit can also share information related to that event. In this way, the sharing unit can share relevant information by analyzing the social media activity of stakeholders. Some or all of the above processing in the sharing unit may be performed using AI or not. For example, the sharing unit can input data on the stakeholders' social media activity into a generating AI and have the generating AI perform the information sharing.

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

[0056] The data collection unit can analyze a user's past inquiry history and select the most suitable collection method. For example, if a user has previously made an inquiry via email, VOC data can be collected via email. If a user has previously made an inquiry via telephone, priority can be given to collecting VOC data via telephone. If a user has previously made an inquiry via chat, VOC data can be collected via chat. In this way, the data collection unit can select the most suitable collection method by analyzing a user's past inquiry history.

[0057] The analysis unit can adjust the level of detail of the analysis based on the importance of the VOC data. For example, for highly important VOC data, a detailed analysis can be performed to identify specific areas for improvement. For less important VOC data, an analysis can be performed to grasp the overall trend. For VOC data of moderate importance, the normal analysis criteria can be applied. In this way, the analysis unit can adjust the level of detail of the analysis based on the importance of the VOC data.

[0058] The proposal department can adjust the level of detail in proposals based on the importance of each improvement suggestion. For example, for highly important improvement suggestions, a detailed proposal can be provided, outlining specific areas for improvement. For less important suggestions, a proposal outlining the overall trend can be provided. For moderately important suggestions, the standard level of detail can be applied. This allows the proposal department to adjust the level of detail in proposals based on their importance.

[0059] The shared information system can adjust the level of detail based on the roles and responsibilities of the stakeholders. For example, it can share overall trends and key areas for improvement concisely with management, specific areas for improvement and detailed information with frontline staff, and a balanced approach to sharing overall trends and specific areas for improvement with middle management. This allows the shared information system to adjust the level of detail based on the roles and responsibilities of the stakeholders.

[0060] The sharing department can select the optimal sharing method by referring to past sharing history. For example, it can prioritize sharing via email based on information previously shared via email. It can prioritize sharing in meetings based on information previously shared in meetings. It can prioritize sharing via chat based on information previously shared via chat. In this way, the sharing department can select the optimal sharing method by referring to past sharing history.

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

[0062] Step 1: The collection unit collects VOC data. VOC data includes customer feedback, complaints, and inquiries. The collection unit collects VOC data such as email inquiry texts and call handling records. The collection unit can also automatically collect VOC data using AI. Step 2: The analysis unit analyzes the VOC data collected by the collection unit. The analysis unit analyzes the collected VOC data and sorts out the noisy minority. The noisy minority includes data sorted based on data reliability and importance. The analysis unit can also analyze the VOC data using AI. Step 3: The proposal department makes improvement suggestions based on the data analyzed by the analysis department. The proposal department learns basic service knowledge and devise improvement measures by comparing them with VOC data. Basic service knowledge includes the basic functions of the service and the basics of customer service. The proposal department can also use AI to make improvement suggestions. Step 4: The sharing department automatically shares the improvement proposals created by the proposal department with relevant parties. The sharing department creates and shares this month's VOC topics and improvement proposals with relevant parties. The sharing department can also automatically create and share improvement proposals using AI.

[0063] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is a system for improving services by utilizing customer feedback (VOC) in service operations. This AI agent system is a mechanism in which an AI agent, including a generation AI, reads VOC and makes improvement suggestions from various angles. As a result, people are freed from sorting through noisy minorities and creating proposals, and can easily request improvement suggestions repeatedly through dialogue with the AI ​​agent. As a result, the improvement cycle is dramatically improved, service quality is enhanced, and user satisfaction is increased. For example, since VOC contains suggestions of different levels of detail and requests that do not align with the purpose of the service, it is necessary to select them based on basic service knowledge in order to actually implement improvements. Therefore, the AI ​​agent, including a generation AI, is fed VOC and makes improvement suggestions from various angles. For example, by having the AI ​​read records of inquiry emails and calls, and further training it on service functions, it can think of ways to improve. A dialogue UI is provided, allowing planning staff to implement improvement measures through dialogue with the AI. Specifically, it consists of the following steps. First, VOC data is collected. For example, data such as email inquiry texts and call handling records are collected. Next, the collected VOC data is fed into an AI agent, including a generating AI. The AI ​​agent analyzes the collected data and identifies noisy minorities. Furthermore, it learns basic service knowledge and devises improvement measures by comparing it with the VOC data. For example, it learns from documentation, specifications, requirements definitions, and help pages related to service functions. Next, the AI ​​agent makes improvement suggestions. For example, based on the VOC data, it determines which voices are useful and which requests are realistic, and makes improvement suggestions. Furthermore, through a conversational UI, planners can implement improvement measures by interacting with the AI ​​agent. For example, they can give instructions to the AI ​​agent such as "this voice is noise" or "this voice is important," and the AI ​​agent will make improvement suggestions based on that. Finally, the AI ​​agent creates an improvement proposal document and automatically shares it with relevant parties. For example, it creates a document summarizing this month's VOC topics and improvement suggestions and shares them with relevant parties.This dramatically improves the improvement cycle in service operations, enhances service quality, and increases user satisfaction. As a result, the AI ​​agent system can dramatically improve the improvement cycle in service operations, enhance service quality, and increase user satisfaction.

[0064] The AI ​​agent system according to this embodiment comprises a collection unit, an analysis unit, a proposal unit, and a sharing unit. The collection unit collects VOC data. VOC data includes, but is not limited to, customer feedback, complaints, and inquiries. The collection unit collects VOC data such as email inquiry texts and call handling records. The collection unit can also automatically collect VOC data using AI. The analysis unit analyzes the VOC data collected by the collection unit. The analysis unit analyzes the collected VOC data and sorts out noisy minorities, for example. Noisy minorities include, for example, data sorted based on data reliability and importance. The analysis unit can also analyze VOC data using AI. The proposal unit makes improvement suggestions based on the data analyzed by the analysis unit. The proposal unit learns basic service knowledge and devise improvement measures in comparison with VOC data, for example. Basic service knowledge includes, for example, basic service functions and basic customer service. The proposal unit can also make improvement suggestions using AI. The sharing unit automatically shares improvement proposals created by the proposal unit with relevant parties. For example, the sharing unit creates this month's VOC topics and improvement proposals and shares them with relevant parties. The sharing unit can also automatically create and share improvement proposals using AI. This enables the AI ​​agent system according to the embodiment to efficiently collect, analyze, propose improvements to, and share VOC data.

[0065] The collection unit collects VOC data. VOC data includes, but is not limited to, customer feedback, complaints, and inquiries. The collection unit collects VOC data such as email inquiry texts and call handling records. The collection unit can also automatically collect VOC data using AI. Specifically, the collection unit has an interface for automatically collecting emails, chat messages, and telephone recordings from customers. This data is converted into text data using natural language processing (NLP) technology and stored in a database. For example, email inquiry texts are automatically retrieved from the mail server and their content is analyzed by a text analysis engine. Call handling records are converted into text using speech recognition technology, and the content and tone of customer statements are analyzed. Furthermore, the collection unit can also collect VOC data from public platforms such as social networking services (SNS) and online forums. This makes it possible to collect a wide range of customer voices and build a comprehensive database. The collection unit collects this data in real time and provides it to the analysis unit, enabling a rapid response. The collection unit also has a filtering function to remove data duplication and noise, maintaining the quality of the collected data. This allows the data collection unit to efficiently and accurately collect VOC data, improving the overall system performance.

[0066] The analysis unit analyzes the VOC data collected by the collection unit. For example, the analysis unit analyzes the collected VOC data and sorts out noisy minorities. Noisy minorities include data that can be sorted out based on reliability and importance, for example. The analysis unit can also analyze VOC data using AI. Specifically, the analysis unit uses natural language processing (NLP) technology to analyze text data and extract customer opinions and sentiments. For example, it classifies positive and negative opinions from customer feedback and identifies frequently occurring keywords and phrases. It also analyzes complaints and inquiries to extract common problems and areas for improvement. Furthermore, the analysis unit can learn data patterns using machine learning algorithms and automatically sort out noisy minorities. For example, based on past data, it can identify unreliable or unimportant data and exclude it from the analysis results. This allows the analysis unit to provide accurate analysis results based on reliable data. The analysis unit analyzes data in real time, enabling rapid responses. Furthermore, the analysis unit can utilize historical data and statistical information to evaluate long-term trends and risks. This allows the analysis unit to efficiently and accurately analyze VOC data, improving the reliability and safety of the entire system.

[0067] The Proposal Department makes improvement suggestions based on data analyzed by the Analysis Department. For example, the Proposal Department learns fundamental service knowledge and devise improvement measures by comparing it with VOC data. Fundamental service knowledge includes, for example, basic service functions and basic customer service. The Proposal Department can also make improvement suggestions using AI. Specifically, the Proposal Department uses machine learning algorithms to integrate analysis results and fundamental service knowledge and automatically generate optimal improvement measures. For example, if customer feedback indicates many complaints about a particular service function, it will propose improvements to that function. Also, if the content of complaints indicates problems in the customer service process, it will propose a review and improvement of that process. The Proposal Department provides these improvement measures as concrete action plans and presents them in a way that is easy for stakeholders to implement. Furthermore, the Proposal Department can evaluate the effectiveness of past improvement measures and continuously optimize them. For example, it can analyze the results of past improvement measures and prioritize proposing measures that were highly effective. In addition, the Proposal Department can use AI to automatically generate new improvement measures, improving the diversity and accuracy of the proposed content. This allows the proposal department to quickly provide effective improvement suggestions based on analysis results, supporting improvements in service quality and customer satisfaction.

[0068] The sharing department automatically shares improvement proposals created by the proposal department with relevant parties. For example, the sharing department creates and shares this month's VOC topics and improvement proposals with relevant parties. The sharing department can also automatically create and share improvement proposals using AI. Specifically, the sharing department automatically generates reports for relevant parties based on the improvement proposals provided by the proposal department. These reports include an overview of this month's VOC data, key topics, and proposed improvement measures. These reports are visually represented using graphs and charts so that relevant parties can easily understand them. Furthermore, the sharing department has a function to automatically distribute reports to relevant parties. For example, it can distribute reports regularly via email or the company's information sharing system. The sharing department can also collect feedback from relevant parties and use it to improve the report content and the accuracy of the proposals. Through these functions, the sharing department facilitates information sharing among relevant parties and promotes the implementation of improvement proposals. In addition, the sharing department can monitor the distribution status of reports and the viewing status of relevant parties, and send reminders as needed. This allows the shared section to support the reliable sharing and implementation of proposals, maximizing the overall effectiveness of the system.

[0069] The collection unit can collect VOC data such as email inquiry texts and call handling records. For example, the collection unit can collect email inquiry texts that include questions and complaints from customers. The collection unit can also collect call handling records that include the content of conversations with customers and summaries of those conversations. For example, the collection unit can automatically collect inquiry emails from customers and save them as VOC data. The collection unit can also record conversations with customers and automatically create summaries of those conversations. This allows the collection unit to broaden the scope of VOC data collection and obtain more information. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input inquiry emails from customers into a generating AI and have the generating AI perform the VOC data collection.

[0070] The analysis unit can analyze the collected VOC data and separate out noisy minorities. For example, the analysis unit can analyze the collected VOC data and separate out noisy minorities based on the reliability and importance of the data. Noisy minorities include, for example, data with low reliability or low importance. The analysis unit can also analyze VOC data using AI. For example, the analysis unit can input the collected VOC data into a generating AI and have the generating AI perform the sorting out of noisy minorities. This allows the analysis unit to efficiently extract important VOC data.

[0071] The proposal department can learn fundamental service knowledge and devise improvement measures by comparing it with VOC data. For example, the proposal department can learn fundamental service knowledge such as the basic functions of the service and the basics of customer service. Fundamental service knowledge includes, for example, documentation, specifications, requirements definitions, and help pages related to service functions. The proposal department can also use AI to learn fundamental service knowledge and devise improvement measures by comparing it with VOC data. For example, the proposal department can input documentation related to service functions into a generating AI and have the generating AI perform the learning of fundamental service knowledge. As a result, the proposal department can devise more appropriate improvement measures by learning fundamental service knowledge.

[0072] The proposal department can implement improvement measures through dialogue with project managers via a conversational UI. For example, the proposal department can have project managers give instructions through the conversational UI, such as "This voice is noise" or "This voice is important," and an AI agent will make improvement suggestions based on those instructions. The conversational UI includes, for example, the dialogue interface and the flow of the dialogue. The proposal department can also implement improvement measures through the conversational UI using AI. For example, the proposal department can input the conversational UI into a generating AI and have the generating AI execute a dialogue with the project manager. This allows the proposal department to implement improvement measures through the conversational UI while project managers interact with an AI agent.

[0073] The shared department can create this month's VOC topics and improvement proposals and share them with stakeholders. For example, the shared department can create this month's VOC topics and improvement proposals. This month's VOC topics may include frequently occurring issues or customer concerns. The shared department can also use AI to automatically create this month's VOC topics and improvement proposals and share them with stakeholders. For example, the shared department can input this month's VOC topics into a generation AI and have the generation AI create improvement proposals. This streamlines information sharing by allowing the shared department to automatically create and share this month's VOC topics and improvement proposals with stakeholders.

[0074] The data collection unit can estimate the user's emotions and adjust the timing of VOC data collection based on the estimated emotions. For example, if the user is dissatisfied, the data collection unit can immediately collect VOC data to take a quick response. If the user is satisfied, the data collection unit can also collect VOC data regularly to obtain continuous feedback. If the user has neutral emotions, the data collection unit can collect VOC data after a specific event to obtain detailed opinions. This allows the data collection unit to collect data at a more appropriate time by adjusting the timing of VOC data collection 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 data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI adjust the timing of VOC data collection.

[0075] The data collection unit can analyze a user's past inquiry history and select the optimal data collection method. For example, if a user has previously made an inquiry via email, the data collection unit will collect VOC data via email. If a user has previously made an inquiry via telephone, the data collection unit can prioritize collecting VOC data via telephone. If a user has previously made an inquiry via chat, the data collection unit can also collect VOC data via chat. In this way, the data collection unit can select the optimal data collection method by analyzing a user's past inquiry history. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input a user's past inquiry history into a generating AI and have the generating AI select the optimal data collection method.

[0076] The data collection unit can filter VOC data based on the user's current service usage and areas of interest. For example, if a user frequently uses a particular service, the data collection unit will prioritize collecting VOC data related to that service. If a user has a specific area of ​​interest, the data collection unit can also collect VOC data related to that area. If a user is trying a new service, the data collection unit can also collect initial feedback on that service. This allows the data collection unit to collect highly relevant data by filtering based on the user's current service usage and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on the user's current service usage and areas of interest into a generating AI and have the generating AI perform the filtering.

[0077] The data collection unit can estimate the user's emotions and determine the priority of VOC data to collect based on the estimated user emotions. For example, if a user expresses strong dissatisfaction, the data collection unit will prioritize collecting that VOC data. The data collection unit can also periodically collect VOC data if the user is satisfied. If a user has neutral emotions, the data collection unit can collect that VOC data with normal priority. In this way, the data collection unit can prioritize the collection of important data by determining the priority of VOC data 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 data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform the determination of VOC data priorities.

[0078] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location when collecting VOC data. For example, if the user is in a specific region, the data collection unit will prioritize the collection of VOC data related to that region. If the user is traveling, the data collection unit can also collect VOC data related to the travel destination. If the user is at home, the data collection unit can also collect VOC data related to services around their home. In this way, the data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's geographical location information into a generating AI and have the generating AI perform the collection of VOC data.

[0079] The data collection unit can analyze a user's social media activity and collect relevant data when collecting VOC data. For example, if a user mentions a particular service on social media, the data collection unit can collect VOC data related to that service. If a user discusses a particular issue on social media, the data collection unit can also collect VOC data related to that issue. If a user posts about a particular event on social media, the data collection unit can also collect VOC data related to that event. In this way, the data collection unit can collect relevant data by analyzing a user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on a user's social media activity into a generating AI and have the generating AI perform the collection of VOC data.

[0080] The analysis unit can estimate the user's emotions and adjust the analysis criteria based on the estimated emotions. For example, if the user expresses strong dissatisfaction, the analysis unit can perform a detailed analysis to identify the root cause of the problem. If the user is satisfied, the analysis unit can also perform an analysis to grasp the overall trend. If the user has neutral emotions, the analysis unit can also apply normal analysis criteria. This allows the analysis unit to perform a more appropriate analysis by adjusting the analysis criteria 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-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI adjust the analysis criteria.

[0081] The analysis unit can adjust the level of detail of the analysis based on the importance of the VOC data during the analysis. For example, the analysis unit can perform a detailed analysis on highly important VOC data to identify specific areas for improvement. For less important VOC data, the analysis unit can perform an analysis to grasp the overall trend. For moderately important VOC data, the analysis unit can apply normal analysis criteria. In this way, the analysis unit can perform a detailed analysis on important data by adjusting the level of detail of the analysis based on the importance of the VOC data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the importance of the VOC data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0082] The analysis unit can apply different analysis algorithms depending on the category of the VOC data during analysis. For example, the analysis unit can apply an analysis algorithm specialized for service improvement to VOC data related to services. The analysis unit can also apply an analysis algorithm specialized for product improvement to VOC data related to products. The analysis unit can also apply an analysis algorithm specialized for support improvement to VOC data related to support. In this way, the analysis unit can perform more appropriate analysis by applying different analysis algorithms depending on the category of the VOC data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the categories of the VOC data into a generating AI and have the generating AI execute the application of the analysis algorithm.

[0083] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit can provide a simple and highly visible display method. If the user is relaxed, the analysis unit can also provide a display method that includes detailed information. If the user is in a hurry, the analysis unit can also provide a display method that gets straight to the point. In this way, the analysis unit can provide a more appropriate display by adjusting the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using AI or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI adjust the display method of the analysis results.

[0084] The analysis unit can determine the priority of analysis based on the submission timing of VOC data during the analysis process. For example, the analysis unit can prioritize the analysis of recently submitted VOC data to ensure a quick response. The analysis unit can also periodically analyze previously submitted VOC data to grasp long-term trends. The analysis unit can also prioritize the analysis of VOC data submitted after a specific event to evaluate the impact of the event. This allows the analysis unit to respond quickly by determining the priority of analysis based on the submission timing of VOC data. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input the submission timing of VOC data into a generating AI and have the generating AI determine the priority of analysis.

[0085] The analysis unit can adjust the order of analysis based on the relevance of the VOC data during the analysis. For example, the analysis unit may prioritize the analysis of highly relevant VOC data to identify important areas for improvement. The analysis unit may also analyze VOC data with a moderate level of relevance in the normal order. The analysis unit may also postpone the analysis of VOC data with a low level of relevance. In this way, the analysis unit can prioritize the analysis of important data by adjusting the order of analysis based on the relevance of the VOC data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit may input the relevance of the VOC data into a generating AI and have the generating AI perform the adjustment of the analysis order.

[0086] The suggestion unit can estimate the user's emotions and adjust the way it presents its suggestions based on those emotions. For example, if the user expresses dissatisfaction, the suggestion unit can make suggestions that emphasize specific areas for improvement. If the user is satisfied, the suggestion unit can also make suggestions that indicate an overall trend. If the user has neutral emotions, the suggestion unit can apply a standard suggestion expression. This allows the suggestion unit to make more appropriate suggestions by adjusting the way it presents its suggestions 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 be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the way it presents its suggestions.

[0087] The suggestion unit can estimate the user's emotions and adjust the way it presents its suggestions based on those emotions. For example, if the user expresses dissatisfaction, the suggestion unit can make suggestions that emphasize specific areas for improvement. If the user is satisfied, the suggestion unit can also make suggestions that indicate an overall trend. If the user has neutral emotions, the suggestion unit can apply a standard suggestion expression. This allows the suggestion unit to make more appropriate suggestions by adjusting the way it presents its suggestions 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 be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the way it presents its suggestions.

[0088] The proposal unit can adjust the level of detail of a proposal based on its importance when it makes a proposal. For example, for high-importance improvement proposals, the proposal unit will provide a detailed proposal outlining specific areas for improvement. For low-importance improvement proposals, the proposal unit may provide a proposal that shows the overall trend. For medium-importance improvement proposals, the proposal unit may apply the normal level of detail. In this way, the proposal unit can provide detailed proposals for important proposals by adjusting the level of detail based on the importance of the improvement proposal. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input the importance of the improvement proposal into a generating AI and have the generating AI perform the adjustment of the level of detail of the proposal.

[0089] The proposal unit can apply different proposal algorithms depending on the category of the improvement suggestion when making a proposal. For example, for a service improvement suggestion, the proposal unit can apply a proposal algorithm specialized in service improvement. For a product improvement suggestion, the proposal unit can also apply a proposal algorithm specialized in product improvement. For a support improvement suggestion, the proposal unit can also apply a proposal algorithm specialized in support improvement. In this way, the proposal unit can make more appropriate suggestions by applying different proposal algorithms depending on the category of the improvement suggestion. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input the category of the improvement suggestion into a generation AI and have the generation AI execute the application of the proposal algorithm.

[0090] The suggestion unit can estimate the user's emotions and adjust the length of the suggestions based on the estimated emotions. For example, if the user is in a hurry, the suggestion unit can provide short, concise suggestions. If the user is relaxed, the suggestion unit can provide longer suggestions with detailed explanations. If the user is excited, the suggestion unit can provide suggestions with visually stimulating effects. In this way, the suggestion unit can provide more appropriate suggestions by adjusting the length of the suggestions 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 suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the length of the suggestions.

[0091] The proposal department can prioritize proposals based on when they are submitted. For example, the proposal department can prioritize recently submitted proposals to ensure a quick response. The proposal department can also periodically submit previously submitted proposals to understand long-term trends. The proposal department can also prioritize proposals submitted after a specific event to evaluate the impact of that event. This allows the proposal department to respond quickly by prioritizing proposals based on when they are submitted. Some or all of the above processes in the proposal department may be performed using AI or not. For example, the proposal department can input the submission dates of improvement proposals into a generating AI and have the generating AI determine the priority of the proposals.

[0092] The proposal unit can adjust the order of improvement suggestions based on their relevance when making a proposal. For example, the proposal unit can prioritize highly relevant improvement suggestions to identify important areas for improvement. The proposal unit can also propose moderately relevant improvement suggestions in the usual order. The proposal unit can also postpone proposing less relevant improvement suggestions. In this way, the proposal unit can prioritize important suggestions by adjusting the order of suggestions based on their relevance. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input the relevance of improvement suggestions into a generating AI and have the generating AI perform the adjustment of the order of suggestions.

[0093] The sharing unit can estimate the user's emotions and determine the priority of information to share based on the estimated emotions. For example, if the user expresses strong dissatisfaction, the sharing unit will share that information with the highest priority. If the user is satisfied, the sharing unit can also share that information periodically. If the user has neutral emotions, the sharing unit can share that information with the normal priority. In this way, the sharing unit can prioritize the sharing of important information by determining the priority of information to share 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 sharing unit may be performed using AI or not. For example, the sharing unit can input user emotion data into a generative AI and have the generative AI perform the determination of information priority.

[0094] The sharing function can adjust the level of detail of information shared based on the roles and responsibilities of the stakeholders. For example, the sharing function can share overall trends and key areas for improvement concisely with management. It can also share specific areas for improvement and detailed information with field staff. It can also share overall trends and specific areas for improvement in a balanced way with middle management. In this way, the sharing function can share information appropriately by adjusting the level of detail based on the roles and responsibilities of the stakeholders. Some or all of the above processing in the sharing function may be performed using AI or not. For example, the sharing function can input data on the roles and responsibilities of stakeholders into a generating AI and have the generating AI perform the adjustment of the level of detail of the information.

[0095] The sharing unit can select the optimal sharing method by referring to past sharing history when sharing information. For example, the sharing unit may prioritize sharing via email based on information previously shared via email. It may also prioritize sharing in meetings based on information previously shared in meetings. It may also prioritize sharing via chat based on information previously shared via chat. In this way, the sharing unit can select the optimal sharing method by referring to past sharing history. Some or all of the above processing in the sharing unit may be performed using AI or not. For example, the sharing unit can input past sharing history into a generating AI and have the generating AI select the optimal sharing method.

[0096] The sharing unit can estimate the user's emotions and adjust how the shared information is displayed based on the estimated emotions. For example, if the user is nervous, the sharing unit can provide a simple and highly visible display method. If the user is relaxed, the sharing unit can also provide a display method that includes detailed information. If the user is in a hurry, the sharing unit can provide a concise display method. In this way, the sharing unit can provide more appropriate information sharing by adjusting how the shared information is displayed 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 sharing unit may be performed using AI or not. For example, the sharing unit can input user emotion data into a generative AI and have the generative AI adjust how the information is displayed.

[0097] The sharing function can select the optimal sharing method by considering the geographical location information of the stakeholders during the sharing process. For example, if stakeholders are in different regions, the sharing function may prioritize online sharing. If stakeholders are in the same office, the sharing function may also prioritize in-person sharing. If stakeholders are traveling, the sharing function may also share via mobile devices. This allows the sharing function to select the optimal sharing method by considering the geographical location information of the stakeholders. Some or all of the above processing in the sharing function may be performed using AI or not. For example, the sharing function can input the geographical location information of stakeholders into a generating AI and have the generating AI select the optimal sharing method.

[0098] The sharing unit can analyze the social media activity of stakeholders and share relevant information when sharing. For example, if a stakeholder mentions a specific topic on social media, the sharing unit can share information related to that topic. If a stakeholder discusses a specific issue on social media, the sharing unit can also share information related to that issue. If a stakeholder posts about a specific event on social media, the sharing unit can also share information related to that event. In this way, the sharing unit can share relevant information by analyzing the social media activity of stakeholders. Some or all of the above processing in the sharing unit may be performed using AI or not. For example, the sharing unit can input data on the stakeholders' social media activity into a generating AI and have the generating AI perform the information sharing.

[0099] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0100] The data collection unit can estimate the user's emotions and adjust the method of collecting VOC data based on the estimated emotions. For example, if a user expresses dissatisfaction, the data collection unit can immediately request detailed feedback. If the user is satisfied, the data collection unit can also collect feedback through periodic surveys. If the user has neutral emotions, the data collection unit can request feedback after a specific event. This allows the data collection unit to select the optimal collection method according to the user's emotions.

[0101] The analysis unit can estimate user sentiment during VOC (Voice of the Customer) data analysis and determine analysis priorities based on the estimated sentiment. For example, if a user expresses strong dissatisfaction, that data can be analyzed with the highest priority to enable a quick response. If a user is satisfied, that data can be analyzed periodically to grasp the overall trend. If a user has a neutral sentiment, that data can be analyzed with the normal priority. In this way, the analysis unit can adjust the analysis priority according to the user's sentiment.

[0102] The proposal function can estimate the user's emotions and adjust the content of the proposal based on those emotions. For example, if the user expresses dissatisfaction, it can make a proposal that emphasizes specific areas for improvement. If the user is satisfied, it can make a proposal that shows the overall trend. If the user has neutral emotions, it can apply the standard proposal. In this way, the proposal function can make the most appropriate proposal according to the user's emotions.

[0103] The sharing function can estimate the user's emotions and determine the priority of information to share based on those estimated emotions. For example, if a user expresses strong dissatisfaction, that information can be shared with the highest priority. If the user is satisfied, that information can be shared regularly. If the user has neutral emotions, that information can be shared with the normal priority. In this way, the sharing function can prioritize the sharing of important information according to the user's emotions.

[0104] The data collection unit can estimate the user's emotions and determine the priority of VOC data to collect based on the estimated emotions. For example, if a user expresses strong dissatisfaction, that VOC data can be collected with the highest priority. If the user is satisfied, that VOC data can be collected regularly. If the user has neutral emotions, that VOC data can be collected with the normal priority. In this way, the data collection unit can prioritize the collection of important data according to the user's emotions.

[0105] The data collection unit can analyze a user's past inquiry history and select the most suitable collection method. For example, if a user has previously made an inquiry via email, VOC data can be collected via email. If a user has previously made an inquiry via telephone, priority can be given to collecting VOC data via telephone. If a user has previously made an inquiry via chat, VOC data can be collected via chat. In this way, the data collection unit can select the most suitable collection method by analyzing a user's past inquiry history.

[0106] The analysis unit can adjust the level of detail of the analysis based on the importance of the VOC data. For example, for highly important VOC data, a detailed analysis can be performed to identify specific areas for improvement. For less important VOC data, an analysis can be performed to grasp the overall trend. For VOC data of moderate importance, the normal analysis criteria can be applied. In this way, the analysis unit can adjust the level of detail of the analysis based on the importance of the VOC data.

[0107] The proposal department can adjust the level of detail in proposals based on the importance of each improvement suggestion. For example, for highly important improvement suggestions, a detailed proposal can be provided, outlining specific areas for improvement. For less important suggestions, a proposal outlining the overall trend can be provided. For moderately important suggestions, the standard level of detail can be applied. This allows the proposal department to adjust the level of detail in proposals based on their importance.

[0108] The shared information system can adjust the level of detail based on the roles and responsibilities of the stakeholders. For example, it can share overall trends and key areas for improvement concisely with management, specific areas for improvement and detailed information with frontline staff, and a balanced approach to sharing overall trends and specific areas for improvement with middle management. This allows the shared information system to adjust the level of detail based on the roles and responsibilities of the stakeholders.

[0109] The sharing department can select the optimal sharing method by referring to past sharing history. For example, it can prioritize sharing via email based on information previously shared via email. It can prioritize sharing in meetings based on information previously shared in meetings. It can prioritize sharing via chat based on information previously shared via chat. In this way, the sharing department can select the optimal sharing method by referring to past sharing history.

[0110] The following briefly describes the processing flow for example form 2.

[0111] Step 1: The collection unit collects VOC data. VOC data includes customer feedback, complaints, and inquiries. The collection unit collects VOC data such as email inquiry texts and call handling records. The collection unit can also automatically collect VOC data using AI. Step 2: The analysis unit analyzes the VOC data collected by the collection unit. The analysis unit analyzes the collected VOC data and sorts out the noisy minority. The noisy minority includes data sorted based on data reliability and importance. The analysis unit can also analyze the VOC data using AI. Step 3: The proposal department makes improvement suggestions based on the data analyzed by the analysis department. The proposal department learns basic service knowledge and devise improvement measures by comparing them with VOC data. Basic service knowledge includes the basic functions of the service and the basics of customer service. The proposal department can also use AI to make improvement suggestions. Step 4: The sharing department automatically shares the improvement proposals created by the proposal department with relevant parties. The sharing department creates and shares this month's VOC topics and improvement proposals with relevant parties. The sharing department can also automatically create and share improvement proposals using AI.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, and sharing unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects VOC data such as email inquiry texts and call response records. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the collected VOC data to identify noisy minorities. The proposal unit is implemented by the identification processing unit 290 of the data processing unit 12 and learns basic service knowledge and devise improvement measures in comparison with the VOC data. The sharing unit is implemented by the control unit 46A of the smart device 14 and automatically shares the improvement proposal document created by the proposal unit with relevant parties. 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.

[0116] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, and sharing unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects VOC data such as email inquiry texts and call handling records. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the collected VOC data to identify noisy minorities. The proposal unit is implemented by the identification processing unit 290 of the data processing unit 12 and learns basic service knowledge and devise improvement measures in comparison with the VOC data. The sharing unit is implemented by the control unit 46A of the smart glasses 214 and automatically shares the improvement proposal created by the proposal unit with relevant parties. 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.

[0132] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, and sharing unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and collects VOC data such as email inquiry texts and call handling records. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the collected VOC data to identify noisy minorities. The proposal unit is implemented by the identification processing unit 290 of the data processing unit 12 and learns basic service knowledge and devise improvement measures in comparison with the VOC data. The sharing unit is implemented by the control unit 46A of the headset terminal 314 and automatically shares the improvement proposal document created by the proposal unit with relevant parties. 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.

[0148] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, and sharing unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects VOC data such as email inquiry texts and call response records. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the collected VOC data to identify noisy minorities. The proposal unit is implemented by the identification processing unit 290 of the data processing unit 12 and learns basic service knowledge and devise improvement measures in comparison with the VOC data. The sharing unit is implemented by the control unit 46A of the robot 414 and automatically shares the improvement proposal document created by the proposal unit with relevant parties. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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."

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] (Note 1) A collection unit that collects VOC data, An analysis unit analyzes the VOC data collected by the aforementioned collection unit, A proposal unit makes improvement suggestions based on the data analyzed by the aforementioned analysis unit, The system includes a sharing unit that automatically shares improvement proposals created by the proposal unit with relevant parties. A system characterized by the following features. (Note 2) The aforementioned collection unit is We collect VOC data such as email inquiry texts and call handling records. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, The collected VOC data is analyzed to identify the noisy minority. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned proposal section is, Learn the fundamentals of service provision and devise improvement measures by comparing them with VOC (Voice of the Customer) data. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned proposal section is, Through a conversational UI, we will implement improvement measures through dialogue with the project manager. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned shared portion is, Prepare this month's VOC topics and improvement proposals, and share them with relevant parties. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is We estimate user sentiment and adjust the timing of VOC data collection based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Analyze the user's past inquiry history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting VOC data, filtering is performed based on the user's current service usage and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates user sentiment and determines the priority of VOC data to collect based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting VOC data, the system prioritizes collecting highly relevant data by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting VOC data, we analyze users' social media activity and collect relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, We estimate the user's emotions and adjust the analysis criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the VOC data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of VOC data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, the priority of the analysis will be determined based on when the VOC data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the VOC data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned proposal section is, When submitting a proposal, adjust the level of detail based on the importance of the improvement suggestion. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned proposal section is, When submitting a proposal, different proposal algorithms are applied depending on the category of the improvement suggestion. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggestion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned proposal section is, When submitting a proposal, the priority of the proposals will be determined based on when the improvement suggestions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned proposal section is, When submitting proposals, adjust the order of the suggestions based on their relevance. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned shared portion is, It estimates the user's emotions and prioritizes the information to share based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned shared portion is, When sharing information, adjust the level of detail based on the roles and responsibilities of the stakeholders. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned shared portion is, When sharing, refer to past sharing history to select the most suitable sharing method. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned shared portion is, It estimates the user's emotions and adjusts how shared information is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned shared portion is, When sharing information, the optimal sharing method will be selected considering the geographical location information of the stakeholders. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned shared portion is, When sharing, we analyze the social media activity of stakeholders and share relevant information. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0184] 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 collection unit that collects VOC data, An analysis unit analyzes the VOC data collected by the aforementioned collection unit, A proposal unit makes improvement suggestions based on the data analyzed by the aforementioned analysis unit, The system includes a sharing unit that automatically shares improvement proposals created by the proposal unit with relevant parties. A system characterized by the following features.

2. The aforementioned collection unit is We collect VOC data such as email inquiry texts and call handling records. The system according to feature 1.

3. The aforementioned analysis unit, The collected VOC data is analyzed to identify the noisy minority. The system according to feature 1.

4. The aforementioned proposal section is, Learn the fundamentals of service provision and devise improvement measures by comparing them with VOC (Voice of the Customer) data. The system according to feature 1.

5. The aforementioned proposal section is, Through a conversational UI, we will implement improvement measures through dialogue with the project manager. The system according to feature 1.

6. The aforementioned shared portion is, Prepare this month's VOC topics and improvement proposals, and share them with relevant parties. The system according to feature 1.

7. The aforementioned collection unit is We estimate user sentiment and adjust the timing of VOC data collection based on the estimated user sentiment. The system according to feature 1.

8. The aforementioned collection unit is Analyze the user's past inquiry history and select the optimal data collection method. The system according to feature 1.

Images