system

Abstract

The system according to this embodiment aims to analyze customer complaint data and use it to improve services and products. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a generation unit, a proposal unit, and a recommendation unit. The collection unit collects customer complaint data. The analysis unit analyzes the complaint data collected by the collection unit. The generation unit generates useful insights based on the data analyzed by the analysis unit. The proposal unit proposes improvement measures based on the insights generated by the generation unit. The recommendation unit proposes specific improvement actions based on the improvement measures proposed by the proposal unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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, claim data from customers has not been fully utilized effectively to link to the improvement of services or products, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze claim data from customers and link it to the improvement of services or products.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, a proposal unit, and a recommendation unit. The collection unit collects customer complaint data. The analysis unit analyzes the complaint data collected by the collection unit. The generation unit generates useful insights based on the data analyzed by the analysis unit. The proposal unit proposes improvement measures based on the insights generated by the generation unit. The recommendation unit proposes specific improvement actions based on the improvement measures proposed by the proposal unit. [Effects of the Invention]

[0007] The system according to this embodiment can analyze customer complaint data and use it to improve services and products. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

[0019] The smart device 14 comprises a computer 36, a reception 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 reception 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) An AI agent according to an embodiment of the present invention is a system that analyzes customer complaint data and identifies the root cause of problems. This system extracts the frequency, trends, and relevance of customer complaints and generates useful insights. Based on these insights, it assists in formulating improvement measures for services and products. Furthermore, it clarifies specific problems and process defects hidden within each complaint and proposes specific corrective actions. This AI agent allows complaints to be viewed as valuable customer feedback and used for continuous improvement. For example, it collects customer complaint data. At this time, it collects detailed data such as the content of the complaint, the frequency of occurrence, and related products and services. For example, if a customer frequently complains about a particular product, it collects detailed information about that product. Next, it analyzes the collected complaint data using AI. The AI ​​analyzes the content of the complaints using natural language processing technology and extracts the frequency, trends, and relevance. For example, if there are many complaints about a particular product, it can identify common problems with that product. Furthermore, it generates useful insights based on the data analyzed by the AI. For example, if there are many complaints about a particular product, it can identify which part of that product is problematic and propose improvement measures. Based on these insights, we provide support in formulating improvement measures for services and products. We also clarify the specific problems and process defects hidden within each complaint. For example, if there is a problem with the product manufacturing process, we identify which part of the process is problematic and propose specific corrective actions. This AI agent allows complaints to be treated as valuable customer feedback and used for continuous improvement. For example, by analyzing the content of a complaint in detail and identifying the root cause of the problem, it is possible to prevent similar complaints from recurring. Furthermore, by making rapid improvements based on complaints, customer satisfaction can be improved. In this way, the AI ​​agent can efficiently collect, analyze, generate insights from customer complaint data, propose improvement measures, and recommend corrective actions.

[0029] The AI ​​agent according to this embodiment comprises a collection unit, an analysis unit, a generation unit, a proposal unit, and a recommendation unit. The collection unit collects customer complaint data. The collection unit collects detailed data such as the content of the complaint, its frequency, and related products and services. For example, if a customer frequently makes complaints about a particular product, the collection unit collects detailed information about that product. The collection unit can also collect complaint data using, for example, questionnaires or feedback forms. The analysis unit analyzes the complaint data collected by the collection unit. For example, the analysis unit uses natural language processing technology to analyze the content of the complaints and extract frequency, trends, and relationships. For example, the analysis unit uses technologies such as morphological analysis, grammatical analysis, and semantic analysis to analyze the complaint data in detail. For example, if there are many complaints about a particular product, the analysis unit can identify common problems with that product. The generation unit generates useful insights based on the data analyzed by the analysis unit. For example, the generation unit generates insights to identify problems with a particular product from the analyzed data and propose improvement measures. The generation unit generates insights based on, for example, what kind of information is considered useful and the criteria for evaluating insights. The proposal unit proposes improvement measures based on the insights generated by the generation unit. The proposal unit proposes improvement measures for services and products based on, for example, the generated insights. The proposal unit proposes improvement measures based on, for example, the format of the improvement measures and the evaluation criteria. The recommendation unit proposes specific improvement actions based on the improvement measures proposed by the proposal unit. The recommendation unit proposes specific improvement actions based on, for example, the proposed improvement measures. The recommendation unit proposes improvement actions based on, for example, the format of the improvement actions and the evaluation criteria. As a result, the AI ​​agent according to the embodiment can efficiently collect, analyze, generate insights from customer complaint data, propose improvement measures, and recommend improvement actions.

[0030] The data collection unit collects customer complaint data. Specifically, it collects detailed data such as the content of the complaint, its frequency, and the products or services involved. For example, if a customer frequently complains about a particular product, the unit will collect detailed information about that product. The data collection unit can also collect complaint data using surveys and feedback forms. Furthermore, the data collection unit also collects data such as call records, emails, and chat logs from customer support centers and call centers. This allows for a detailed understanding of the problems customers are experiencing and the circumstances under which complaints occur. The data collection unit centrally manages this data and stores it in a database. The database is organized with metadata that includes attribute information such as the type of complaint, the date and time of occurrence, and the products or services involved. This allows the subsequent analysis unit to process the data efficiently. In addition, the data collection unit can flexibly configure the frequency and method of data collection. For example, it can collect data in real time to monitor the increasing trend of complaints over a specific period. This allows the data collection unit to efficiently and effectively collect customer complaint data and improve the overall system performance.

[0031] The analysis unit analyzes the complaint data collected by the data collection unit. Specifically, it uses natural language processing technology to analyze the content of complaints and extract frequency, trends, and relationships. For example, it uses technologies such as morphological analysis, grammatical analysis, and semantic analysis to analyze the complaint data in detail. If there are many complaints about a particular product, the analysis unit can identify common problems with that product. Furthermore, the analysis unit performs time-series analysis of the complaint data to understand the timing of complaint occurrences and seasonal trends. This makes it possible to identify the causes of an increase in complaints at a particular time and take preventive measures. The analysis unit also clusters the complaint data and groups similar complaints to extract common problems and patterns. This makes it possible to efficiently identify areas for improvement in products and services. The analysis unit also performs sentiment analysis of the complaint data using AI. It classifies customer emotions into positive, negative, and neutral, and evaluates the severity of complaints and customer satisfaction. This allows for a rapid response to particularly serious complaints. The analysis unit visualizes these analysis results and displays them as graphs and charts so that stakeholders can easily understand them. This allows the analysis unit to quickly and accurately analyze the collected claim data and grasp the surrounding risk situation in real time.

[0032] The generation unit generates valuable insights based on data analyzed by the analysis unit. Specifically, it identifies problems with specific products from the analyzed data and generates insights to propose improvement measures. The generation unit generates insights based on what information is considered useful and the criteria for evaluating insights. For example, if there are many complaints about a particular product, it may indicate problems with the product's design or manufacturing process, and generates insights that propose design changes or a review of the manufacturing process. The generation unit can also discover new product and service needs from customer complaints and generate insights that indicate the direction of development. The generation unit uses AI to automate the insight generation process, providing valuable information quickly and efficiently. For example, it uses machine learning algorithms to learn from past complaint data and the effectiveness of subsequent improvement measures to generate optimal insights. Furthermore, the generation unit integrates multiple data sources and analysis results to evaluate the reliability of the insights and conducts a comprehensive evaluation. As a result, the generation unit can generate valuable insights with high accuracy based on the analyzed data and support the proposal of improvement measures for the entire system.

[0033] The proposal department proposes improvement measures based on the insights generated by the generation department. Specifically, it proposes improvements to services and products based on the generated insights. The proposal department proposes improvement measures based on the format and evaluation criteria of the improvements. For example, if there are many complaints about a particular product, it will propose design changes or a review of the manufacturing process for that product. The proposal department can also discover new product and service needs from customer complaints and propose directions for development. The proposal department uses AI to automate the proposal process and provide optimal improvement measures quickly and efficiently. For example, it uses machine learning algorithms to learn from past complaint data and the effectiveness of subsequent improvement measures and propose the optimal improvement measures. The proposal department also evaluates the effectiveness of the proposed improvement measures and makes corrections or improvements as needed. In this way, the proposal department can propose optimal improvement measures based on the generated insights and improve the overall system performance.

[0034] The Recommendation Department proposes specific improvement actions based on the improvement measures proposed by the Proposal Department. Specifically, it proposes specific improvement actions based on the proposed improvement measures. The Recommendation Department proposes improvement actions based on the format and evaluation criteria of the improvement actions. For example, if there are many complaints about a particular product, it will propose design changes or a review of the manufacturing process for that product. The Recommendation Department can also discover new product and service needs from customer complaints and make recommendations indicating the direction of development. The Recommendation Department uses AI to automate the recommendation process and provide optimal improvement actions quickly and efficiently. For example, it uses machine learning algorithms to learn from past complaint data and the effectiveness of subsequent improvement measures to propose optimal improvement actions. The Recommendation Department also evaluates the effectiveness of the proposed improvement actions and makes corrections or improvements as necessary. In this way, the Recommendation Department can propose optimal improvement actions based on the proposed improvement measures and improve the overall performance of the system.

[0035] The data collection unit can collect detailed data such as the content of the complaint, its frequency, and the products and services involved. For example, the data collection unit can record the details of the complaint and statistically analyze its frequency. For example, the data collection unit can collect information on related products and services and provide data to identify the cause of the complaint. For example, if a customer frequently complains about a particular product, the data collection unit can collect detailed information about that product. This makes it easier to identify problems and develop corrective measures by collecting detailed data on complaints. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input complaint data into AI, which can then automatically collect and analyze the data.

[0036] The analysis unit can analyze the content of claims using natural language processing technology and extract frequency, trends, and relevance. For example, the analysis unit can use morphological analysis to break down the content of claims and analyze the meaning of each word. For example, the analysis unit can use grammatical analysis to analyze the sentence structure of claims and understand the meaning of the sentences. For example, the analysis unit can use semantic analysis to analyze the content of claims in detail and extract frequency, trends, and relevance. In this way, by using natural language processing technology, the content of claims can be analyzed in detail and the trends and relevances of the issues can be grasped. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input claim data into AI, and the AI ​​can automatically analyze the data and extract frequency, trends, and relevance.

[0037] The generation unit can generate useful insights based on the analyzed data. For example, the generation unit can generate insights to identify problems with a specific product from the analyzed data and propose improvement measures. The generation unit can generate insights based on criteria for evaluating insights, such as what kind of information is considered useful. For example, if there are many complaints about a particular product, the generation unit can generate insights to identify which part of that product is problematic and propose improvement measures based on the analyzed data. In this way, by generating insights based on the analyzed data, useful information can be provided for formulating improvement measures for problems. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the analyzed data into AI, and the AI ​​can automatically generate insights.

[0038] The proposal department can propose improvements to services and products based on the generated insights. For example, the proposal department can propose improvements to services and products based on the generated insights. For example, the proposal department can propose improvements based on the format and evaluation criteria of the improvements. For example, if there are many complaints about a particular product, the proposal department can identify which part of the product is problematic and propose improvements. In this way, the quality of services and products can be improved by proposing improvements based on the generated insights. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input the generated insights into AI, and the AI ​​can automatically propose improvements.

[0039] The recommendation department can propose specific improvement actions based on the proposed improvement measures. For example, the recommendation department will propose specific improvement actions based on the proposed improvement measures. For example, the recommendation department will propose improvement actions based on the format and evaluation criteria of the improvement actions. For example, if there are many complaints about a particular product, the recommendation department will identify which part of the product is problematic and propose specific improvement actions. In this way, by proposing specific improvement actions based on the proposed improvement measures, actual improvement activities are promoted. Some or all of the above processes in the recommendation department may be performed using AI, for example, or not using AI. For example, the recommendation department can input the proposed improvement measures into AI, and the AI ​​can automatically propose specific improvement actions.

[0040] The data collection unit can analyze a customer's past claim filing history and select the optimal collection method. For example, the data collection unit can analyze the content of past claims filed by a customer and collect data quickly if similar problems are recurring. For example, the data collection unit can analyze the frequency of past claims filed by a customer and provide special treatment to customers who file claims frequently. For example, if the data collection unit can determine from a customer's past claim filing history that they tend to file claims during certain time periods, it will collect data during those times. This allows the optimal collection method to be selected by analyzing a customer's past claim filing history. Some or all of the above processes in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input a customer's past claim filing history into an AI, which can then automatically select the optimal collection method.

[0041] The data collection unit can filter claim data based on the customer's current situation and areas of interest. For example, the data collection unit can prioritize collecting claims related to products the customer is currently using. For example, if the customer is interested in a particular service, the data collection unit can prioritize collecting claims related to that service. For example, the data collection unit can filter and collect relevant claims based on the customer's current situation (e.g., traveling). This allows for the collection of highly relevant claim data by filtering based on the customer's current situation and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input data on the customer's current situation and areas of interest into the AI, which can then automatically perform the filtering.

[0042] The data collection unit can prioritize the collection of highly relevant data by considering the customer's geographical location when collecting claim data. For example, if a customer is in a specific region, the data collection unit will prioritize the collection of claims related to that region. For example, if a customer is traveling, the data collection unit will prioritize the collection of claims related to their travel destination. For example, if a customer is visiting a specific store, the data collection unit will prioritize the collection of claims related to that store. This allows for the priority collection of highly relevant claim data by considering the customer's geographical location. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the customer's geographical location information into the AI, which can then automatically prioritize the collection of highly relevant data.

[0043] The data collection unit can analyze customers' social media activity and collect relevant data when collecting claim data. For example, if a customer mentions a particular product on social media, the data collection unit can collect claims related to that product. For example, if a customer expresses dissatisfaction on social media, the data collection unit can collect claims related to that dissatisfaction. For example, if a customer mentions a particular service on social media, the data collection unit can collect claims related to that service. In this way, relevant claim data can be collected by analyzing customers' social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input customer social media activity data into AI, and the AI ​​can automatically collect relevant data.

[0044] The analysis unit can adjust the level of detail of the analysis based on the importance of the claims when analyzing claim data. For example, the analysis unit can analyze high-importance claims in detail to identify the root cause of the problem. For example, the analysis unit can analyze low-importance claims simply to extract the necessary information. For example, the analysis unit can analyze medium-importance claims moderately to find areas for improvement. In this way, by adjusting the level of detail of the analysis based on the importance of the claims, important claims can be analyzed in detail. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input claim data into AI, which can automatically evaluate importance and adjust the level of detail of the analysis.

[0045] The analysis unit can apply different analysis algorithms depending on the claim category when analyzing claim data. For example, the analysis unit applies a product-specific analysis algorithm to product-related claims. For example, it applies a service-specific analysis algorithm to service-related claims. For example, it applies a support-specific analysis algorithm to support-related claims. This allows claims to be analyzed in an appropriate manner by applying different analysis algorithms depending on the claim category. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input claim data into AI, which can automatically determine the category and apply an appropriate analysis algorithm.

[0046] The analysis unit can determine the priority of claims based on when the claims were filed when analyzing claim data. For example, the analysis unit may prioritize the analysis of recently filed claims and respond quickly. For example, the analysis unit may postpone the analysis of claims filed in the past. For example, the analysis unit may prioritize the analysis of claims that were filed in a concentrated period. This allows claims that require a quick response to be analyzed preferentially by determining the priority of the analysis based on when the claims were filed. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input claim data into AI, which can automatically evaluate the filing date and determine the priority of the analysis.

[0047] The analysis unit can adjust the order of analysis based on the relevance of the claims when analyzing claim data. For example, the analysis unit may prioritize the analysis of highly relevant claims to find commonalities in the problems. For example, the analysis unit may postpone the analysis of less relevant claims. For example, the analysis unit may dynamically adjust the order of analysis based on the relevance of the claims. This allows for the prioritization of highly relevant claims by adjusting the order of analysis based on the relevance of the claims. Some or all of the above processes in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input claim data into AI, which can then automatically evaluate the relevance and adjust the order of analysis.

[0048] The generation unit can adjust the order of insights based on the relevance of the claims when generating insights. For example, the generation unit can prioritize generating insights for highly relevant claims. For example, the generation unit can postpone generating insights for less relevant claims. The generation unit can dynamically adjust the order of insights based on the relevance of the claims. This allows for the priority generation of highly relevant insights by adjusting the order of insights based on the relevance of the claims. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input claim data into AI, which can automatically evaluate relevance and adjust the order of insights.

[0049] The proposal unit can adjust the level of detail of its proposals based on the importance of the insights it provides. For example, it can provide detailed proposals for high-importance insights, simplified proposals for low-importance insights, and proposals with a moderate level of detail for medium-importance insights. By adjusting the level of detail of proposals based on the importance of the insights, it is possible to provide detailed proposals for important insights. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not. For example, the proposal unit can input insight data into an AI, which can then automatically evaluate importance and adjust the level of detail of the proposals.

[0050] The proposal unit can apply different proposal algorithms depending on the category of the insight when making a proposal. For example, the proposal unit can apply a product-specific proposal algorithm to product-related insights. For example, the proposal unit can apply a service-specific proposal algorithm to service-related insights. For example, the proposal unit can apply a support-specific proposal algorithm to support-related insights. This allows the proposal unit to make appropriate proposals by applying different proposal algorithms depending on the category of the insight. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input insight data into AI, which can automatically determine the category and apply the appropriate proposal algorithm.

[0051] The proposal department can prioritize proposals based on when the insights were submitted. For example, it might prioritize recently generated insights, postpone proposals to previously generated insights, or prioritize insights generated in a concentrated period. By prioritizing proposals based on when the insights were submitted, it can prioritize proposals to insights that require immediate attention. Some or all of the above processes in the proposal department may be performed using AI, or not. For example, the proposal department could input insight data into an AI, which could then automatically evaluate the submission timing and determine the priority of the proposals.

[0052] The suggestion unit can adjust the order of suggestions based on the relevance of the insights when making suggestions. For example, the suggestion unit will prioritize suggestions for highly relevant insights. For example, the suggestion unit will postpone suggestions for less relevant insights. The suggestion unit can dynamically adjust the order of suggestions based on the relevance of the insights. This allows for prioritizing suggestions for highly relevant insights by adjusting the order of suggestions based on the relevance of the insights. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not using AI. For example, the suggestion unit can input insight data into AI, which can then automatically evaluate relevance and adjust the order of suggestions.

[0053] The recommendation unit can adjust the level of detail of its recommendations based on the importance of the insights it makes. For example, it can make detailed recommendations for high-importance insights, simplified recommendations for low-importance insights, and recommendations with a moderate level of detail for medium-importance insights. By adjusting the level of detail of the recommendations based on the importance of the insights, it is possible to make detailed recommendations for important insights. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input insight data into AI, which can then automatically evaluate importance and adjust the level of detail of the recommendations.

[0054] The recommendation unit can apply different recommendation algorithms depending on the category of the insight when making recommendations. For example, the recommendation unit can apply a product-specific recommendation algorithm to product-related insights. For example, the recommendation unit can apply a service-specific recommendation algorithm to service-related insights. For example, the recommendation unit can apply a support-specific recommendation algorithm to support-related insights. This allows the recommendation unit to make recommendations in an appropriate manner by applying different recommendation algorithms depending on the category of the insight. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or not using AI. For example, the recommendation unit can input insight data into AI, which can automatically determine the category and apply the appropriate recommendation algorithm.

[0055] The recommendation department can prioritize recommendations based on when the insights were submitted. For example, it might prioritize recently generated insights, postpone recommendations for previously generated insights, or prioritize insights generated in a concentrated period. By prioritizing recommendations based on when the insights were submitted, it can prioritize recommendations for insights that require immediate attention. Some or all of the above processes in the recommendation department may be performed using AI, or not. For example, the recommendation department could input insight data into an AI, which could then automatically evaluate the submission timing and determine the priority of the recommendations.

[0056] The recommendation unit can adjust the order of recommendations based on the relevance of the insights when making recommendations. For example, the recommendation unit will prioritize recommendations for highly relevant insights. For example, the recommendation unit will postpone recommendations for less relevant insights. The recommendation unit can dynamically adjust the order of recommendations based on the relevance of the insights. This allows for prioritizing recommendations for highly relevant insights by adjusting the order of recommendations based on the relevance of the insights. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or not using AI. For example, the recommendation unit can input insight data into AI, which can then automatically evaluate relevance and adjust the order of recommendations.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] The data collection unit can analyze a customer's past purchase history and optimize how complaint data is collected. For example, it can prioritize collecting complaints about products that a customer frequently purchases. If a customer shows high loyalty to a particular brand, it can collect detailed complaints related to that brand. It can also quickly collect complaints about newly purchased products and assess the likelihood of initial defects. By optimizing how complaint data is collected based on a customer's past purchase history, more effective complaint handling becomes possible.

[0059] The proposal department can collect customer feedback in real time and dynamically update proposals. For example, if a customer provides additional feedback on a proposal, the proposal is immediately revised based on that feedback. If a customer reacts positively to a proposal, it is strengthened and applied to other customers. If a customer reacts negatively to a proposal, it is re-evaluated and areas for improvement are identified. This allows for more effective proposals by reflecting customer feedback in real time.

[0060] The data collection unit can analyze customers' social media activity and optimize how complaint data is collected. For example, if a customer mentions a specific product on social media, complaints related to that product will be prioritized for collection. If a customer expresses dissatisfaction on social media, complaints related to that dissatisfaction will be collected quickly. If a customer mentions a specific service on social media, complaints related to that service will be collected in detail. By optimizing how complaint data is collected based on customers' social media activity, more effective complaint handling becomes possible.

[0061] The generation unit can generate a model to predict future claims based on the analysis results of claim data. For example, it can predict when claims for a particular product will increase based on past claim data. It can identify factors that increase claims for a particular service and generate a predictive model based on those factors. It can analyze trends in increasing claims for a particular customer group and generate a predictive model based on those trends. This makes it possible to take preventative measures by predicting future claims.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The collection department collects customer complaint data. The collection department collects detailed data such as the nature of the complaint, its frequency, and the products or services involved. For example, if a customer frequently complains about a particular product, the department will collect detailed information about that product. Complaint data can also be collected using surveys or feedback forms. Step 2: The analysis unit analyzes the claim data collected by the collection unit. The analysis unit uses natural language processing technology to analyze the content of the claims and extract frequency, trends, and relationships. For example, by using technologies such as morphological analysis, grammatical analysis, and semantic analysis to analyze the claim data in detail, if there are many claims related to a particular product, it is possible to identify common problems with that product. Step 3: The generation unit generates useful insights based on the data analyzed by the analysis unit. The generation unit identifies problems with specific products from the analyzed data and generates insights to propose improvement measures. Insights are generated based on what information is considered useful and the criteria for evaluating insights. Step 4: The proposal team proposes improvement measures based on the insights generated by the generation team. The proposal team proposes improvement measures for services and products based on the generated insights. They propose improvement measures based on the format of the improvement measures and evaluation criteria. Step 5: The recommendations department proposes specific improvement actions based on the improvement measures proposed by the proposal department. The recommendations department proposes specific improvement actions based on the proposed improvement measures. They propose improvement actions based on the format of the improvement actions and evaluation criteria.

[0064] (Example of form 2) An AI agent according to an embodiment of the present invention is a system that analyzes customer complaint data and identifies the root cause of problems. This system extracts the frequency, trends, and relevance of customer complaints and generates useful insights. Based on these insights, it assists in formulating improvement measures for services and products. Furthermore, it clarifies specific problems and process defects hidden within each complaint and proposes specific corrective actions. This AI agent allows complaints to be viewed as valuable customer feedback and used for continuous improvement. For example, it collects customer complaint data. At this time, it collects detailed data such as the content of the complaint, the frequency of occurrence, and related products and services. For example, if a customer frequently complains about a particular product, it collects detailed information about that product. Next, it analyzes the collected complaint data using AI. The AI ​​analyzes the content of the complaints using natural language processing technology and extracts the frequency, trends, and relevance. For example, if there are many complaints about a particular product, it can identify common problems with that product. Furthermore, it generates useful insights based on the data analyzed by the AI. For example, if there are many complaints about a particular product, it can identify which part of that product is problematic and propose improvement measures. Based on these insights, we provide support in formulating improvement measures for services and products. We also clarify the specific problems and process defects hidden within each complaint. For example, if there is a problem with the product manufacturing process, we identify which part of the process is problematic and propose specific corrective actions. This AI agent allows complaints to be treated as valuable customer feedback and used for continuous improvement. For example, by analyzing the content of a complaint in detail and identifying the root cause of the problem, it is possible to prevent similar complaints from recurring. Furthermore, by making rapid improvements based on complaints, customer satisfaction can be improved. In this way, the AI ​​agent can efficiently collect, analyze, generate insights from customer complaint data, propose improvement measures, and recommend corrective actions.

[0065] The AI ​​agent according to this embodiment comprises a collection unit, an analysis unit, a generation unit, a proposal unit, and a recommendation unit. The collection unit collects customer complaint data. The collection unit collects detailed data such as the content of the complaint, its frequency, and related products and services. For example, if a customer frequently makes complaints about a particular product, the collection unit collects detailed information about that product. The collection unit can also collect complaint data using, for example, questionnaires or feedback forms. The analysis unit analyzes the complaint data collected by the collection unit. For example, the analysis unit uses natural language processing technology to analyze the content of the complaints and extract frequency, trends, and relationships. For example, the analysis unit uses technologies such as morphological analysis, grammatical analysis, and semantic analysis to analyze the complaint data in detail. For example, if there are many complaints about a particular product, the analysis unit can identify common problems with that product. The generation unit generates useful insights based on the data analyzed by the analysis unit. For example, the generation unit generates insights to identify problems with a particular product from the analyzed data and propose improvement measures. The generation unit generates insights based on, for example, what kind of information is considered useful and the criteria for evaluating insights. The proposal unit proposes improvement measures based on the insights generated by the generation unit. The proposal unit proposes improvement measures for services and products based on, for example, the generated insights. The proposal unit proposes improvement measures based on, for example, the format of the improvement measures and the evaluation criteria. The recommendation unit proposes specific improvement actions based on the improvement measures proposed by the proposal unit. The recommendation unit proposes specific improvement actions based on, for example, the proposed improvement measures. The recommendation unit proposes improvement actions based on, for example, the format of the improvement actions and the evaluation criteria. As a result, the AI ​​agent according to the embodiment can efficiently collect, analyze, generate insights from customer complaint data, propose improvement measures, and recommend improvement actions.

[0066] The data collection unit collects customer complaint data. Specifically, it collects detailed data such as the content of the complaint, its frequency, and the products or services involved. For example, if a customer frequently complains about a particular product, the unit will collect detailed information about that product. The data collection unit can also collect complaint data using surveys and feedback forms. Furthermore, the data collection unit also collects data such as call records, emails, and chat logs from customer support centers and call centers. This allows for a detailed understanding of the problems customers are experiencing and the circumstances under which complaints occur. The data collection unit centrally manages this data and stores it in a database. The database is organized with metadata that includes attribute information such as the type of complaint, the date and time of occurrence, and the products or services involved. This allows the subsequent analysis unit to process the data efficiently. In addition, the data collection unit can flexibly configure the frequency and method of data collection. For example, it can collect data in real time to monitor the increasing trend of complaints over a specific period. This allows the data collection unit to efficiently and effectively collect customer complaint data and improve the overall system performance.

[0067] The analysis unit analyzes the complaint data collected by the data collection unit. Specifically, it uses natural language processing technology to analyze the content of complaints and extract frequency, trends, and relationships. For example, it uses technologies such as morphological analysis, grammatical analysis, and semantic analysis to analyze the complaint data in detail. If there are many complaints about a particular product, the analysis unit can identify common problems with that product. Furthermore, the analysis unit performs time-series analysis of the complaint data to understand the timing of complaint occurrences and seasonal trends. This makes it possible to identify the causes of an increase in complaints at a particular time and take preventive measures. The analysis unit also clusters the complaint data and groups similar complaints to extract common problems and patterns. This makes it possible to efficiently identify areas for improvement in products and services. The analysis unit also performs sentiment analysis of the complaint data using AI. It classifies customer emotions into positive, negative, and neutral, and evaluates the severity of complaints and customer satisfaction. This allows for a rapid response to particularly serious complaints. The analysis unit visualizes these analysis results and displays them as graphs and charts so that stakeholders can easily understand them. This allows the analysis unit to quickly and accurately analyze the collected claim data and grasp the surrounding risk situation in real time.

[0068] The generation unit generates valuable insights based on data analyzed by the analysis unit. Specifically, it identifies problems with specific products from the analyzed data and generates insights to propose improvement measures. The generation unit generates insights based on what information is considered useful and the criteria for evaluating insights. For example, if there are many complaints about a particular product, it may indicate problems with the product's design or manufacturing process, and generates insights that propose design changes or a review of the manufacturing process. The generation unit can also discover new product and service needs from customer complaints and generate insights that indicate the direction of development. The generation unit uses AI to automate the insight generation process, providing valuable information quickly and efficiently. For example, it uses machine learning algorithms to learn from past complaint data and the effectiveness of subsequent improvement measures to generate optimal insights. Furthermore, the generation unit integrates multiple data sources and analysis results to evaluate the reliability of the insights and conducts a comprehensive evaluation. As a result, the generation unit can generate valuable insights with high accuracy based on the analyzed data and support the proposal of improvement measures for the entire system.

[0069] The proposal department proposes improvement measures based on the insights generated by the generation department. Specifically, it proposes improvements to services and products based on the generated insights. The proposal department proposes improvement measures based on the format and evaluation criteria of the improvements. For example, if there are many complaints about a particular product, it will propose design changes or a review of the manufacturing process for that product. The proposal department can also discover new product and service needs from customer complaints and propose directions for development. The proposal department uses AI to automate the proposal process and provide optimal improvement measures quickly and efficiently. For example, it uses machine learning algorithms to learn from past complaint data and the effectiveness of subsequent improvement measures and propose the optimal improvement measures. The proposal department also evaluates the effectiveness of the proposed improvement measures and makes corrections or improvements as needed. In this way, the proposal department can propose optimal improvement measures based on the generated insights and improve the overall system performance.

[0070] The Recommendation Department proposes specific improvement actions based on the improvement measures proposed by the Proposal Department. Specifically, it proposes specific improvement actions based on the proposed improvement measures. The Recommendation Department proposes improvement actions based on the format and evaluation criteria of the improvement actions. For example, if there are many complaints about a particular product, it will propose design changes or a review of the manufacturing process for that product. The Recommendation Department can also discover new product and service needs from customer complaints and make recommendations indicating the direction of development. The Recommendation Department uses AI to automate the recommendation process and provide optimal improvement actions quickly and efficiently. For example, it uses machine learning algorithms to learn from past complaint data and the effectiveness of subsequent improvement measures to propose optimal improvement actions. The Recommendation Department also evaluates the effectiveness of the proposed improvement actions and makes corrections or improvements as necessary. In this way, the Recommendation Department can propose optimal improvement actions based on the proposed improvement measures and improve the overall performance of the system.

[0071] The data collection unit can collect detailed data such as the content of the complaint, its frequency, and the products and services involved. For example, the data collection unit can record the details of the complaint and statistically analyze its frequency. For example, the data collection unit can collect information on related products and services and provide data to identify the cause of the complaint. For example, if a customer frequently complains about a particular product, the data collection unit can collect detailed information about that product. This makes it easier to identify problems and develop corrective measures by collecting detailed data on complaints. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input complaint data into AI, which can then automatically collect and analyze the data.

[0072] The analysis unit can analyze the content of claims using natural language processing technology and extract frequency, trends, and relevance. For example, the analysis unit can use morphological analysis to break down the content of claims and analyze the meaning of each word. For example, the analysis unit can use grammatical analysis to analyze the sentence structure of claims and understand the meaning of the sentences. For example, the analysis unit can use semantic analysis to analyze the content of claims in detail and extract frequency, trends, and relevance. In this way, by using natural language processing technology, the content of claims can be analyzed in detail and the trends and relevances of the issues can be grasped. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input claim data into AI, and the AI ​​can automatically analyze the data and extract frequency, trends, and relevance.

[0073] The generation unit can generate useful insights based on the analyzed data. For example, the generation unit can generate insights to identify problems with a specific product from the analyzed data and propose improvement measures. The generation unit can generate insights based on criteria for evaluating insights, such as what kind of information is considered useful. For example, if there are many complaints about a particular product, the generation unit can generate insights to identify which part of that product is problematic and propose improvement measures based on the analyzed data. In this way, by generating insights based on the analyzed data, useful information can be provided for formulating improvement measures for problems. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the analyzed data into AI, and the AI ​​can automatically generate insights.

[0074] The proposal department can propose improvements to services and products based on the generated insights. For example, the proposal department can propose improvements to services and products based on the generated insights. For example, the proposal department can propose improvements based on the format and evaluation criteria of the improvements. For example, if there are many complaints about a particular product, the proposal department can identify which part of the product is problematic and propose improvements. In this way, the quality of services and products can be improved by proposing improvements based on the generated insights. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input the generated insights into AI, and the AI ​​can automatically propose improvements.

[0075] The recommendation department can propose specific improvement actions based on the proposed improvement measures. For example, the recommendation department will propose specific improvement actions based on the proposed improvement measures. For example, the recommendation department will propose improvement actions based on the format and evaluation criteria of the improvement actions. For example, if there are many complaints about a particular product, the recommendation department will identify which part of the product is problematic and propose specific improvement actions. In this way, by proposing specific improvement actions based on the proposed improvement measures, actual improvement activities are promoted. Some or all of the above processes in the recommendation department may be performed using AI, for example, or not using AI. For example, the recommendation department can input the proposed improvement measures into AI, and the AI ​​can automatically propose specific improvement actions.

[0076] The data collection unit can estimate the customer's emotions and adjust the timing of complaint data collection based on the estimated emotions. For example, if the customer is angry, the data collection unit can immediately collect complaint data and respond quickly. For example, if the customer is calm, the data collection unit can collect complaint data after a certain period of time to obtain detailed information. For example, if the customer is feeling anxious, the data collection unit can collect complaint data at an appropriate time to provide reassurance. In this way, by adjusting the collection timing according to the customer's emotions, complaint data can be collected at the appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input customer emotion data into AI, which can automatically estimate emotions and adjust the collection timing.

[0077] The data collection unit can analyze a customer's past claim filing history and select the optimal collection method. For example, the data collection unit can analyze the content of past claims filed by a customer and collect data quickly if similar problems are recurring. For example, the data collection unit can analyze the frequency of past claims filed by a customer and provide special treatment to customers who file claims frequently. For example, if the data collection unit can determine from a customer's past claim filing history that they tend to file claims during certain time periods, it will collect data during those times. This allows the optimal collection method to be selected by analyzing a customer's past claim filing history. Some or all of the above processes in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input a customer's past claim filing history into an AI, which can then automatically select the optimal collection method.

[0078] The data collection unit can filter claim data based on the customer's current situation and areas of interest. For example, the data collection unit can prioritize collecting claims related to products the customer is currently using. For example, if the customer is interested in a particular service, the data collection unit can prioritize collecting claims related to that service. For example, the data collection unit can filter and collect relevant claims based on the customer's current situation (e.g., traveling). This allows for the collection of highly relevant claim data by filtering based on the customer's current situation and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input data on the customer's current situation and areas of interest into the AI, which can then automatically perform the filtering.

[0079] The data collection unit can estimate customer emotions and prioritize the complaint data to be collected based on the estimated emotions. For example, if a customer is angry, the data collection unit will prioritize collecting that complaint and respond quickly. For example, if a customer is dissatisfied, the data collection unit will prioritize collecting that complaint and strive to resolve the problem. For example, if a customer is satisfied, the data collection unit will determine that it is acceptable to postpone collecting that complaint. In this way, by prioritizing complaint data based on customer emotions, important complaints can be collected preferentially. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input customer emotion data into an AI, which can automatically estimate emotions and determine the priority of the complaint data.

[0080] The data collection unit can prioritize the collection of highly relevant data by considering the customer's geographical location when collecting claim data. For example, if a customer is in a specific region, the data collection unit will prioritize the collection of claims related to that region. For example, if a customer is traveling, the data collection unit will prioritize the collection of claims related to their travel destination. For example, if a customer is visiting a specific store, the data collection unit will prioritize the collection of claims related to that store. This allows for the priority collection of highly relevant claim data by considering the customer's geographical location. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the customer's geographical location information into the AI, which can then automatically prioritize the collection of highly relevant data.

[0081] The data collection unit can analyze customers' social media activity and collect relevant data when collecting claim data. For example, if a customer mentions a particular product on social media, the data collection unit can collect claims related to that product. For example, if a customer expresses dissatisfaction on social media, the data collection unit can collect claims related to that dissatisfaction. For example, if a customer mentions a particular service on social media, the data collection unit can collect claims related to that service. In this way, relevant claim data can be collected by analyzing customers' social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input customer social media activity data into AI, and the AI ​​can automatically collect relevant data.

[0082] The analysis unit can estimate the customer's emotions and adjust the method of analyzing the complaint based on the estimated emotions. For example, if the customer is angry, the analysis unit can quickly analyze the complaint and assess the urgency of the problem. For example, if the customer is dissatisfied, the analysis unit can analyze the complaint in detail and identify the root cause of the problem. For example, if the customer is satisfied, the analysis unit can analyze the complaint in the usual way and find areas for improvement. This allows for the analysis of complaints in an appropriate manner by adjusting the analysis method based on the customer'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 analysis unit may be performed using AI or not using AI. For example, the analysis unit can input customer emotion data into AI, which can automatically estimate emotions and adjust the analysis method.

[0083] The analysis unit can adjust the level of detail of the analysis based on the importance of the claims when analyzing claim data. For example, the analysis unit can analyze high-importance claims in detail to identify the root cause of the problem. For example, the analysis unit can analyze low-importance claims simply to extract the necessary information. For example, the analysis unit can analyze medium-importance claims moderately to find areas for improvement. In this way, by adjusting the level of detail of the analysis based on the importance of the claims, important claims can be analyzed in detail. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input claim data into AI, which can automatically evaluate importance and adjust the level of detail of the analysis.

[0084] The analysis unit can apply different analysis algorithms depending on the claim category when analyzing claim data. For example, the analysis unit applies a product-specific analysis algorithm to product-related claims. For example, it applies a service-specific analysis algorithm to service-related claims. For example, it applies a support-specific analysis algorithm to support-related claims. This allows claims to be analyzed in an appropriate manner by applying different analysis algorithms depending on the claim category. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input claim data into AI, which can automatically determine the category and apply an appropriate analysis algorithm.

[0085] The analysis unit can estimate the customer's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the customer is angry, the analysis unit can quickly display the analysis results and emphasize the urgency of the problem. For example, if the customer is dissatisfied, the analysis unit can display the analysis results in detail and clarify the root cause of the problem. For example, if the customer is satisfied, the analysis unit can display the analysis results in the usual way and indicate areas for improvement. In this way, by adjusting how the analysis results are displayed based on the customer's emotions, the analysis results can be displayed in an appropriate manner. 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 analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input customer emotion data into AI, which can automatically estimate emotions and adjust how the analysis results are displayed.

[0086] The analysis unit can determine the priority of claims based on when the claims were filed when analyzing claim data. For example, the analysis unit may prioritize the analysis of recently filed claims and respond quickly. For example, the analysis unit may postpone the analysis of claims filed in the past. For example, the analysis unit may prioritize the analysis of claims that were filed in a concentrated period. This allows claims that require a quick response to be analyzed preferentially by determining the priority of the analysis based on when the claims were filed. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input claim data into AI, which can automatically evaluate the filing date and determine the priority of the analysis.

[0087] The analysis unit can adjust the order of analysis based on the relevance of the claims when analyzing claim data. For example, the analysis unit may prioritize the analysis of highly relevant claims to find commonalities in the problems. For example, the analysis unit may postpone the analysis of less relevant claims. For example, the analysis unit may dynamically adjust the order of analysis based on the relevance of the claims. This allows for the prioritization of highly relevant claims by adjusting the order of analysis based on the relevance of the claims. Some or all of the above processes in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input claim data into AI, which can then automatically evaluate the relevance and adjust the order of analysis.

[0088] The generation unit can adjust the order of insights based on the relevance of the claims when generating insights. For example, the generation unit can prioritize generating insights for highly relevant claims. For example, the generation unit can postpone generating insights for less relevant claims. The generation unit can dynamically adjust the order of insights based on the relevance of the claims. This allows for the priority generation of highly relevant insights by adjusting the order of insights based on the relevance of the claims. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input claim data into AI, which can automatically evaluate relevance and adjust the order of insights.

[0089] The proposal department can estimate the customer's emotions and adjust the way the proposal is presented based on those emotions. For example, if the customer is angry, the proposal department will provide a proposal quickly and emphasize the urgency of the problem. If the customer is dissatisfied, the proposal department will provide a detailed proposal and clarify the root cause of the problem. If the customer is satisfied, the proposal department will provide a proposal in the usual way and indicate areas for improvement. This allows the proposal to be presented in an appropriate manner by adjusting its presentation based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the proposal department may be performed using AI or not. For example, the proposal department can input customer emotion data into an AI, which can automatically estimate the emotion and adjust the way the proposal is presented.

[0090] The proposal unit can adjust the level of detail of its proposals based on the importance of the insights it provides. For example, it can provide detailed proposals for high-importance insights, simplified proposals for low-importance insights, and proposals with a moderate level of detail for medium-importance insights. By adjusting the level of detail of proposals based on the importance of the insights, it is possible to provide detailed proposals for important insights. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not. For example, the proposal unit can input insight data into an AI, which can then automatically evaluate importance and adjust the level of detail of the proposals.

[0091] The proposal unit can apply different proposal algorithms depending on the category of the insight when making a proposal. For example, the proposal unit can apply a product-specific proposal algorithm to product-related insights. For example, the proposal unit can apply a service-specific proposal algorithm to service-related insights. For example, the proposal unit can apply a support-specific proposal algorithm to support-related insights. This allows the proposal unit to make appropriate proposals by applying different proposal algorithms depending on the category of the insight. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input insight data into AI, which can automatically determine the category and apply the appropriate proposal algorithm.

[0092] The suggestion unit can estimate the customer's emotions and adjust the length of the suggestion based on the estimated emotions. For example, if the customer is angry, the suggestion unit will make a short, to-the-point suggestion. If the customer is dissatisfied, the suggestion unit will make a longer suggestion with detailed explanations. If the customer is satisfied, the suggestion unit will make a suggestion of normal length. In this way, by adjusting the length of the suggestion based on the customer's emotions, it is possible to provide suggestions of appropriate length. 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 using AI. For example, the suggestion unit can input customer emotion data into an AI, which can automatically estimate the emotion and adjust the length of the suggestion.

[0093] The proposal department can prioritize proposals based on when the insights were submitted. For example, it might prioritize recently generated insights, postpone proposals to previously generated insights, or prioritize insights generated in a concentrated period. By prioritizing proposals based on when the insights were submitted, it can prioritize proposals to insights that require immediate attention. Some or all of the above processes in the proposal department may be performed using AI, or not. For example, the proposal department could input insight data into an AI, which could then automatically evaluate the submission timing and determine the priority of the proposals.

[0094] The suggestion unit can adjust the order of suggestions based on the relevance of the insights when making suggestions. For example, the suggestion unit will prioritize suggestions for highly relevant insights. For example, the suggestion unit will postpone suggestions for less relevant insights. The suggestion unit can dynamically adjust the order of suggestions based on the relevance of the insights. This allows for prioritizing suggestions for highly relevant insights by adjusting the order of suggestions based on the relevance of the insights. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not using AI. For example, the suggestion unit can input insight data into AI, which can then automatically evaluate relevance and adjust the order of suggestions.

[0095] The recommendation unit can estimate the customer's emotions and adjust its recommendation methods based on the estimated emotions. For example, if the customer is angry, the recommendation unit will provide recommendations quickly and emphasize the urgency of the problem. For example, if the customer is dissatisfied, the recommendation unit will provide detailed recommendations and clarify the root cause of the problem. For example, if the customer is satisfied, the recommendation unit will provide recommendations in the usual way and indicate areas for improvement. This allows for the provision of appropriate recommendations by adjusting the recommendation methods based on the customer'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 recommendation unit may be performed using AI or not using AI. For example, the recommendation unit can input customer emotion data into AI, which can automatically estimate emotions and adjust the recommendation methods.

[0096] The recommendation unit can adjust the level of detail of its recommendations based on the importance of the insights it makes. For example, it can make detailed recommendations for high-importance insights, simplified recommendations for low-importance insights, and recommendations with a moderate level of detail for medium-importance insights. By adjusting the level of detail of the recommendations based on the importance of the insights, it is possible to make detailed recommendations for important insights. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input insight data into AI, which can then automatically evaluate importance and adjust the level of detail of the recommendations.

[0097] The recommendation unit can apply different recommendation algorithms depending on the category of the insight when making recommendations. For example, the recommendation unit can apply a product-specific recommendation algorithm to product-related insights. For example, the recommendation unit can apply a service-specific recommendation algorithm to service-related insights. For example, the recommendation unit can apply a support-specific recommendation algorithm to support-related insights. This allows the recommendation unit to make recommendations in an appropriate manner by applying different recommendation algorithms depending on the category of the insight. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or not using AI. For example, the recommendation unit can input insight data into AI, which can automatically determine the category and apply the appropriate recommendation algorithm.

[0098] The recommendation department can estimate customer emotions and prioritize recommendations based on those estimated emotions. For example, if a customer is angry, the recommendation department will prioritize that recommendation and respond quickly. For example, if a customer is dissatisfied, the recommendation department will prioritize that recommendation and strive to resolve the problem. For example, if a customer is satisfied, the recommendation department will determine that it is acceptable to postpone that recommendation. This allows important recommendations to be prioritized by determining the priority of recommendations based on customer emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 recommendation department may be performed using AI or not. For example, the recommendation department can input customer emotion data into an AI, which can automatically estimate emotions and determine the priority of recommendations.

[0099] The recommendation department can prioritize recommendations based on when the insights were submitted. For example, it might prioritize recently generated insights, postpone recommendations for previously generated insights, or prioritize insights generated in a concentrated period. By prioritizing recommendations based on when the insights were submitted, it can prioritize recommendations for insights that require immediate attention. Some or all of the above processes in the recommendation department may be performed using AI, or not. For example, the recommendation department could input insight data into an AI, which could then automatically evaluate the submission timing and determine the priority of the recommendations.

[0100] The recommendation unit can adjust the order of recommendations based on the relevance of the insights when making recommendations. For example, the recommendation unit will prioritize recommendations for highly relevant insights. For example, the recommendation unit will postpone recommendations for less relevant insights. The recommendation unit can dynamically adjust the order of recommendations based on the relevance of the insights. This allows for prioritizing recommendations for highly relevant insights by adjusting the order of recommendations based on the relevance of the insights. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or not using AI. For example, the recommendation unit can input insight data into AI, which can then automatically evaluate relevance and adjust the order of recommendations.

[0101] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0102] The analysis unit can estimate customer emotions and evaluate the importance of a complaint based on those emotions. For example, if a customer is angry, the complaint is evaluated as high importance and addressed promptly. If a customer is dissatisfied, the complaint is evaluated as moderately important and a detailed analysis is performed. If a customer is satisfied, the complaint is evaluated as low importance and a standard analysis is performed. This allows for appropriate responses by evaluating the importance of complaints based on customer emotions.

[0103] The data collection unit can analyze a customer's past purchase history and optimize how complaint data is collected. For example, it can prioritize collecting complaints about products that a customer frequently purchases. If a customer shows high loyalty to a particular brand, it can collect detailed complaints related to that brand. It can also quickly collect complaints about newly purchased products and assess the likelihood of initial defects. By optimizing how complaint data is collected based on a customer's past purchase history, more effective complaint handling becomes possible.

[0104] The generation unit can estimate customer emotions and adjust how insights are presented based on those emotions. For example, if a customer is angry, the insights are presented concisely and clearly to encourage a quick response. If a customer is dissatisfied, the insights are explained in detail to clarify the root cause of the problem. If a customer is satisfied, the insights are presented in a normal manner, indicating areas for improvement. This allows insights to be delivered in an appropriate way by adjusting how they are presented based on customer emotions.

[0105] The proposal department can collect customer feedback in real time and dynamically update proposals. For example, if a customer provides additional feedback on a proposal, the proposal is immediately revised based on that feedback. If a customer reacts positively to a proposal, it is strengthened and applied to other customers. If a customer reacts negatively to a proposal, it is re-evaluated and areas for improvement are identified. This allows for more effective proposals by reflecting customer feedback in real time.

[0106] The recommendations department can estimate customer emotions and prioritize recommendations based on those emotions. For example, if a customer is angry, that recommendation will be given top priority and addressed quickly. If a customer is dissatisfied, that recommendation will be given priority and efforts will be made to resolve the problem. If a customer is satisfied, it will be determined that it is acceptable to postpone that recommendation. In this way, by prioritizing recommendations based on customer emotions, important recommendations can be delivered preferentially.

[0107] The data collection unit can analyze customers' social media activity and optimize how complaint data is collected. For example, if a customer mentions a specific product on social media, complaints related to that product will be prioritized for collection. If a customer expresses dissatisfaction on social media, complaints related to that dissatisfaction will be collected quickly. If a customer mentions a specific service on social media, complaints related to that service will be collected in detail. By optimizing how complaint data is collected based on customers' social media activity, more effective complaint handling becomes possible.

[0108] The analysis unit can estimate customer emotions and adjust the complaint analysis method based on those emotions. For example, if a customer is angry, it can quickly analyze the complaint and assess the urgency of the problem. If a customer is dissatisfied, it can analyze the complaint in detail and identify the root cause of the problem. If a customer is satisfied, it can analyze the complaint in the usual way and find areas for improvement. In this way, by adjusting the analysis method based on customer emotions, complaints can be analyzed in an appropriate manner.

[0109] The generation unit can generate a model to predict future claims based on the analysis results of claim data. For example, it can predict when claims for a particular product will increase based on past claim data. It can identify factors that increase claims for a particular service and generate a predictive model based on those factors. It can analyze trends in increasing claims for a particular customer group and generate a predictive model based on those trends. This makes it possible to take preventative measures by predicting future claims.

[0110] The proposal team can estimate the customer's emotions and adjust the way the proposal is presented based on those emotions. For example, if the customer is angry, the proposal can be presented quickly, emphasizing the urgency of the problem. If the customer is dissatisfied, the proposal can be presented in detail, clarifying the root cause of the problem. If the customer is satisfied, the proposal can be presented in the usual way, highlighting areas for improvement. In this way, by adjusting the presentation of the proposal based on the customer's emotions, the proposal can be delivered in an appropriate manner.

[0111] The recommendation team can estimate customer emotions and adjust their recommendation approach based on those emotions. For example, if a customer is angry, they can provide recommendations quickly and emphasize the urgency of the problem. If a customer is dissatisfied, they can provide detailed recommendations and clarify the root cause of the problem. If a customer is satisfied, they can provide recommendations in the usual way and indicate areas for improvement. This allows them to provide recommendations in an appropriate manner by adjusting their approach based on customer emotions.

[0112] The following briefly describes the processing flow for example form 2.

[0113] Step 1: The collection department collects customer complaint data. The collection department collects detailed data such as the nature of the complaint, its frequency, and the products or services involved. For example, if a customer frequently complains about a particular product, the department will collect detailed information about that product. Complaint data can also be collected using surveys or feedback forms. Step 2: The analysis unit analyzes the claim data collected by the collection unit. The analysis unit uses natural language processing technology to analyze the content of the claims and extract frequency, trends, and relationships. For example, by using technologies such as morphological analysis, grammatical analysis, and semantic analysis to analyze the claim data in detail, if there are many claims related to a particular product, it is possible to identify common problems with that product. Step 3: The generation unit generates useful insights based on the data analyzed by the analysis unit. The generation unit identifies problems with specific products from the analyzed data and generates insights to propose improvement measures. Insights are generated based on what information is considered useful and the criteria for evaluating insights. Step 4: The proposal team proposes improvement measures based on the insights generated by the generation team. The proposal team proposes improvement measures for services and products based on the generated insights. They propose improvement measures based on the format of the improvement measures and evaluation criteria. Step 5: The recommendations department proposes specific improvement actions based on the improvement measures proposed by the proposal department. The recommendations department proposes specific improvement actions based on the proposed improvement measures. They propose improvement actions based on the format of the improvement actions and evaluation criteria.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, proposal unit, and recommendation 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 customer complaint data. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected complaint data. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates useful insights based on the analyzed data. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes improvement measures based on the generated insights. The recommendation unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes specific improvement actions based on the proposed improvement measures. 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.

[0118] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, proposal unit, and recommendation 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 customer complaint data. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected complaint data. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates useful insights based on the analyzed data. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes improvement measures based on the generated insights. The recommendation unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes specific improvement actions based on the proposed improvement measures. 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.

[0134] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, proposal unit, and recommendation 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 customer complaint data. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected complaint data. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates useful insights based on the analyzed data. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes improvement measures based on the generated insights. The recommendation unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes specific improvement actions based on the proposed improvement measures. 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.

[0150] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, proposal unit, and recommendation unit, is implemented, for example, in at least one of 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 customer complaint data. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the collected complaint data. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates useful insights based on the analyzed data. The proposal unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and proposes improvement measures based on the generated insights. The recommendation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and proposes specific improvement actions based on the proposed improvement measures. 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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."

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] (Note 1) The data collection department collects customer complaint data, An analysis unit analyzes the claim data collected by the aforementioned collection unit, A generation unit that generates useful insights based on the data analyzed by the analysis unit, A proposal unit that proposes improvement measures based on the insights generated by the generation unit, The system includes a proposal unit that proposes specific improvement actions based on the improvement measures proposed by the proposal unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is Collect detailed data on the nature of the complaint, its frequency, and the products and services involved. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, We use natural language processing technology to analyze the content of claims and extract their frequency, trends, and relevance. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Generate useful insights based on analyzed data. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned proposal section is, Based on the generated insights, we propose improvements to our services and products. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned recommendation section, Based on the proposed improvement measures, we will suggest specific improvement actions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is We estimate customer emotions and adjust the timing of complaint data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Analyze the customer's past complaint filing 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 complaint data, filter it based on the customer's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is We estimate customer sentiment and prioritize the complaint data to collect based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting claims data, the collection of highly relevant data is prioritized by considering the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting complaint data, analyze customers' 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 customer emotions and adjust the method of analyzing complaints based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, When analyzing claim data, adjust the level of detail of the analysis based on the importance of the claim. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, When analyzing claim data, different analysis algorithms are applied depending on the claim category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates customer emotions and adjusts how the analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, When analyzing claim data, the priority of the analysis is determined based on the date the claim was filed. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, When analyzing claim data, the order of analysis is adjusted based on the relevance of the claims. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is When generating insights, adjust the order of insights based on the relevance of the claims. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned proposal section is, We estimate the customer's emotions and adjust the way we present our proposals 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 making a proposal, adjust the level of detail in the proposal based on the importance of the insights. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned proposal section is, When making suggestions, different suggestion algorithms are applied depending on the category of the insight. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned proposal section is, Estimate the customer's emotions and adjust the length of the suggestion based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned proposal section is, When submitting proposals, prioritize them based on when the insights were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned proposal section is, When making suggestions, adjust the order of suggestions based on the relevance of the insights. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned recommendation section, We estimate customer emotions and adjust our recommendation methods based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned recommendation section, When making recommendations, adjust the level of detail in the recommendations based on the importance of the insights. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned recommendation section, When making recommendations, different recommendation algorithms are applied depending on the category of the insight. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned recommendation section, We estimate customer emotions and prioritize recommendations based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned recommendation section, When making recommendations, prioritize them based on when the insights were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned recommendation section, When making recommendations, adjust the order of the recommendations based on the relevance of the insights. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0186] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The data collection department collects customer complaint data, An analysis unit analyzes the claim data collected by the aforementioned collection unit, A generation unit that generates useful insights based on the data analyzed by the analysis unit, A proposal unit that proposes improvement measures based on the insights generated by the generation unit, The system includes a proposal unit that proposes specific improvement actions based on the improvement measures proposed by the proposal unit. A system characterized by the following features.

2. The aforementioned collection unit is Collect detailed data on the nature of the complaint, its frequency, and the products and services involved. The system according to feature 1.

3. The aforementioned analysis unit, We use natural language processing technology to analyze the content of claims and extract their frequency, trends, and relevance. The system according to feature 1.

4. The generating unit is Generate useful insights based on analyzed data. The system according to feature 1.

5. The aforementioned proposal section is, Based on the generated insights, we propose improvements to our services and products. The system according to feature 1.

6. The aforementioned recommendation section, Based on the proposed improvement measures, we will suggest specific improvement actions. The system according to feature 1.

7. The aforementioned collection unit is We estimate customer emotions and adjust the timing of complaint data collection based on those estimated emotions. The system according to feature 1.

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

Images