system

Abstract

The system according to this embodiment aims to analyze customer emotions and inquiry trends and to provide appropriate escalation support. [Solution] The system according to this embodiment comprises an emotion analysis unit, a history analysis unit, and an advice unit. The emotion analysis unit analyzes the content of the current call. The history analysis unit learns past inquiry history and analyzes the customer's personality and inquiry tendencies. The advice unit provides advice when handling escalations based on the analysis results obtained by the emotion analysis unit and the history analysis unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to sufficiently analyze the emotions and inquiry tendencies of customers in a call center and perform appropriate escalation responses.

[0005] The system according to the embodiment aims to analyze the emotions and inquiry tendencies of customers and perform appropriate escalation responses.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an emotion analysis unit, a history analysis unit, and an advice unit. The emotion analysis unit analyzes the current call content. The history analysis unit learns past inquiry history and analyzes the customer's personality and inquiry tendencies. The advice unit provides advice when handling escalations based on the analysis results obtained by the emotion analysis unit and the history analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can analyze customer emotions and inquiry trends and provide appropriate escalation support. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The call center system according to an embodiment of the present invention is a system for streamlining customer service in a call center and increasing the complaint resolution rate. This call center system uses AI to learn from current call content and past inquiry history to analyze the customer's emotions, personality, and inquiry tendencies. Next, based on the analysis results, the AI ​​advises on the "summary of the handling process," "requests," "personality," and "best solution direction" when handling an escalation. Based on this advice, the direction of the escalation is determined, and the complaint resolution rate is increased. First, the AI ​​is trained on current call content and past inquiry history. At this time, the AI ​​analyzes the customer's emotions, personality, and inquiry tendencies. For example, it is possible to understand what kind of personality the customer has and what kind of inquiries they frequently make from past call history. This allows for a detailed understanding of the customer's characteristics. Next, based on the analysis results, the AI ​​advises on the "summary of the handling process," "requests," "personality," and "best solution direction" when handling an escalation. For example, it can summarize what kind of complaints the customer has made in the past and what kind of responses were given, and propose the optimal solution for the current complaint. This allows for a quick determination of the direction of the escalation. Furthermore, based on AI advice, the direction of escalation handling is determined, increasing the complaint resolution rate. For example, by having operator crews take specific actions based on the solutions suggested by the AI, customer satisfaction can be improved. This leads to an increased complaint resolution rate and improved efficiency of the call center. This system streamlines customer service in the call center and improves the complaint resolution rate. By suggesting the optimal response method based on the customer characteristics analyzed by the AI, the burden on operator crews is reduced, enabling quick and appropriate responses. For example, by having operator crews take specific actions based on the solutions suggested by the AI, customer satisfaction can be improved. This leads to an increased complaint resolution rate and improved efficiency of the call center. As a result, the call center system can streamline customer service and increase the complaint resolution rate.

[0029] The call center system according to this embodiment comprises an emotion analysis unit, a history analysis unit, and an advice unit. The emotion analysis unit analyzes the content of the current call. The emotion analysis unit estimates the emotions of the customer during the call, for example, using voice analysis technology. The emotion analysis unit can estimate whether the customer is angry, satisfied, or anxious by analyzing, for example, the tone and speed of the voice and the choice of words. The emotion analysis unit can also convert the content of the call into text data using, for example, voice recognition technology, and analyze that text data. The history analysis unit learns from past inquiry history and analyzes the customer's personality and inquiry tendencies. The history analysis unit can, for example, store past call history and inquiry content in a database and analyze that data. The history analysis unit can, for example, understand what kind of personality the customer has and what kind of inquiries they frequently make from past call history. The history analysis unit can also model the customer's personality and inquiry tendencies using, for example, a machine learning algorithm. The advice unit provides advice when handling escalations based on the analysis results obtained by the emotion analysis unit and the history analysis unit. The advice unit includes, for example, a response history summary unit that summarizes the response history. The advice unit includes, for example, a request analysis unit that analyzes requests. The advice unit includes, for example, a personality analysis unit that analyzes personality. The advice unit includes, for example, a solution direction proposal unit that suggests the best course of action. As a result, the call center system according to the embodiment can improve the complaint resolution rate by analyzing the current call content and past inquiry history and providing appropriate advice when handling escalations.

[0030] The emotion analysis unit analyzes the current call content. For example, it estimates the customer's emotions during a call using voice analysis technology. Specifically, voice analysis technology extracts features such as tone, speed, pitch, and emphasized words, and estimates emotions based on these features. For example, if the voice tone is high and the speed is fast, it is determined that the customer is likely angry. Conversely, if the voice tone is low and the speed is slow, it is determined that the customer is likely calm or satisfied. Furthermore, the emotion analysis unit can also convert the call content into text data using voice recognition technology and analyze that text data. For the analysis of the text data, natural language processing technology is used to analyze word choice and context to more accurately estimate the customer's emotions. For example, if there are many negative words or strong expressions, it is determined that the customer is likely feeling dissatisfied. The emotion analysis unit provides these analysis results in real time to help operators respond quickly. In this way, the emotion analysis unit can accurately understand the customer's emotions and provide important information for taking appropriate action.

[0031] The history analysis department learns from past inquiry history and analyzes customer personalities and inquiry trends. Specifically, the history analysis department stores past call history and inquiry content in a database and analyzes that data. For example, from past call history, it can understand what kind of personality a customer has and what kinds of inquiries they frequently make. The history analysis department can also model customer personalities and inquiry trends using machine learning algorithms. For example, it can use clustering algorithms to classify customers into multiple groups and understand the characteristics of each group. In addition, the history analysis department can analyze past inquiry content to understand what kinds of problems customers are facing and what kinds of solutions they are seeking. This allows the history analysis department to accurately understand customer personalities and inquiry trends and provide important information for operators to respond appropriately. Furthermore, based on past data, the history analysis department can also predict future inquiry trends and take countermeasures in advance. For example, if there is a tendency for certain inquiries to increase during a particular period, countermeasures such as strengthening operator training in preparation for that period can be taken. In this way, the history analysis department can play an important role in improving the efficiency of the call center and customer satisfaction.

[0032] The Advice Unit provides advice during escalation based on the analysis results obtained by the Emotion Analysis Unit and the History Analysis Unit. Specifically, the Advice Unit includes a Response History Summarization Unit that summarizes the history of the response. The Response History Summarization Unit summarizes past response history, enabling operators to quickly grasp the situation. For example, it concisely summarizes past call content and response results, providing important information relevant to the current situation. The Advice Unit also includes a Request Analysis Unit that analyzes requests. The Request Analysis Unit analyzes customer requests and proposes the most appropriate response. For example, if a customer is seeking information about a specific product, it provides detailed information about that product. Furthermore, the Advice Unit includes a Personality Analysis Unit that analyzes personality. The Personality Analysis Unit analyzes the customer's personality and proposes a response tailored to that personality. For example, if a customer has a cautious personality, it proposes a response that provides detailed explanations and reassures the customer. In addition, the Advice Unit includes a Solution Direction Proposal Unit that proposes the best course of action. The Solution Direction Proposal Unit proposes the optimal solution based on the analysis results of the Emotion Analysis Unit and the History Analysis Unit. For example, if a customer is dissatisfied, it proposes specific measures to resolve that dissatisfaction. This allows the advisory department to provide appropriate advice during escalation and increase the complaint resolution rate. Furthermore, the advisory department can contribute to improving the skills of operators, thereby enhancing the overall service quality of the call center.

[0033] The advice unit includes a response history summary unit that summarizes the history of responses. The response history summary unit provides a summary of the response history when an escalation occurs. For example, the response history summary unit summarizes the history of responses to the current claim based on past response history. For example, the response history summary unit can refer to successful past claim responses and propose the optimal response method for the current claim. For example, the response history summary unit can store past response history in a database and analyze that data. This enables quick and appropriate responses by providing a summary of the response history when an escalation occurs.

[0034] The advisory department includes a requirements analysis department that analyzes customer requests. The requirements analysis department analyzes customer requests. For example, the requirements analysis department analyzes customer requests based on past inquiries. For example, the requirements analysis department can understand what kind of requests customers have based on past inquiries. The requirements analysis department can also model customer requests using machine learning algorithms, for example. This allows for more appropriate responses by analyzing customer requests.

[0035] The advice unit includes a personality analysis unit that analyzes personality. The personality analysis unit analyzes the customer's personality. For example, the personality analysis unit analyzes the customer's personality based on past inquiry history. For example, the personality analysis unit can understand what kind of personality the customer has from past inquiry history. The personality analysis unit can also model the customer's personality using machine learning algorithms, for example. This allows for more appropriate responses by analyzing the customer's personality.

[0036] The advice department includes a solution proposal department that suggests the best course of action. The solution proposal department proposes the optimal course of action. For example, the solution proposal department proposes the best solution to the current complaint based on successful past complaint handling cases. The solution proposal department can also store past handling history in a database and analyze that data. The solution proposal department can also model the optimal solution using machine learning algorithms. By proposing the optimal course of action, the complaint resolution rate can be increased.

[0037] The history analysis unit can analyze past inquiry history while considering the frequency and time of inquiry. For example, in the case of a customer who makes frequent inquiries, the AI ​​in the history analysis unit can analyze the history in detail and extract patterns. For example, in the case of a customer who makes inquiries at a specific time, the AI ​​in the history analysis unit can also consider that time of day when performing the analysis. For example, in the case of a customer who makes infrequent inquiries, the AI ​​in the history analysis unit can also analyze the history in a simplified manner and extract important information. This allows for more appropriate responses by considering the frequency and time of inquiry when performing the analysis. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0038] The history analysis unit can apply different analysis algorithms to each category of inquiry when analyzing past inquiry history. For example, in the case of a technical inquiry, the AI ​​can analyze the technical information in detail. For example, in the case of a service inquiry, the AI ​​can also analyze the service information in detail. For example, in the case of a complaint inquiry, the AI ​​can analyze the complaint information in detail and indicate that urgent action is required. This allows for more appropriate responses by applying different analysis algorithms to each category of inquiry. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0039] The history analysis unit can analyze past inquiry history while considering the customer's geographical location information. For example, if a customer makes an inquiry from a specific region, the AI ​​in the history analysis unit will consider the information of that region when performing the analysis. For example, if a customer makes an inquiry from a different region, the AI ​​in the history analysis unit can also consider the information of each region when performing the analysis. For example, if a customer makes an inquiry while traveling, the AI ​​in the history analysis unit can also consider the travel pattern when performing the analysis. This allows for a more appropriate response by considering the customer's geographical location information when performing the analysis. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0040] The history analysis unit can analyze customers' social media activity and related inquiry history when analyzing past inquiry history. For example, if a customer is very active on social media, the AI ​​will take that activity into consideration during the analysis. If a customer is inactive on social media, the AI ​​can perform a simplified analysis. If a customer is active on a specific social media platform, the AI ​​can also take that platform's information into consideration during the analysis. This allows for more appropriate responses by analyzing customers' social media activity. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0041] The advisory unit can provide optimal advice by referring to past successful escalation cases when giving advice. For example, the advisory unit can refer to cases where similar claims were resolved in the past, and the AI ​​will advise on how to do so. For example, the advisory unit can refer to patterns of successful escalation cases in the past, and the AI ​​can advise on those patterns. For example, the advisory unit can have the AI ​​advise on the optimal solution based on past success cases. This allows for more appropriate advice by referring to past success cases. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0042] The advice unit can customize advice by considering the customer's current situation and background information. For example, if the customer provides a detailed explanation of their current situation, the AI ​​will customize the advice based on that information. The advice unit can also consider the customer's background information and have the AI ​​provide the most appropriate advice. The advice unit can also adjust the content of the advice according to the customer's current situation. This allows for more appropriate advice by considering the customer's current situation and background information. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0043] The advice unit can provide optimal advice by considering the customer's geographical location. For example, if the customer is in a specific region, the AI ​​can provide advice based on information for that region. If the customer is in a different region, the AI ​​can also provide advice based on information for that region. If the customer is on the move, the AI ​​can also provide advice considering their movement pattern. This allows for more appropriate advice by considering the customer's geographical location. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0044] The advice unit can analyze the customer's social media activity and provide relevant advice when giving advice. For example, if the customer is very active on social media, the AI ​​can provide advice based on that activity. If the customer is inactive on social media, the AI ​​can also provide advice based on a simplified analysis of that activity. If the customer is active on a specific social media platform, the AI ​​can provide advice based on information from that platform. This allows for more appropriate advice by analyzing the customer's social media activity. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0045] The response history summarization unit can improve the accuracy of its summaries by referring to past response history when summarizing the response history. For example, the response history summarization unit can refer to cases where similar claims were resolved in the past, and the AI ​​reflects those methods in the summary. For example, the response history summarization unit can also have the AI ​​suggest the optimal summarization method based on past response history. For example, the response history summarization unit can have the AI ​​improve the accuracy of its summaries based on past success stories. In this way, the accuracy of the summaries is improved by referring to past response history. Sentiment estimation is achieved using sentiment estimation functions, for example, using a sentiment engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0046] The response history summarization unit can summarize the response history while considering the time of day and day of the week in which the response took place. For example, if the response was made on a weekday morning, the response history summarization unit can consider commuting stress in the summary. For example, if the response was made on a weekend evening, the response history summarization unit can consider weekend relaxation time in the summary. For example, if the response was made during the daytime on a weekday, the response history summarization unit can consider refreshment during work breaks in the summary. This allows for more appropriate responses by summarizing while considering the time of day and day of the week in which the response took place. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0047] The request analysis unit can improve the accuracy of its analysis by referring to past request history when analyzing requests. For example, the request analysis unit can refer to past cases where similar requests were resolved, and the AI ​​can reflect those methods in the analysis. For example, the request analysis unit can also have the AI ​​propose the optimal analysis method based on past request history. For example, the request analysis unit can have the AI ​​improve the accuracy of its analysis based on past success stories. In this way, the accuracy of the analysis is improved by referring to past request history. Emotion estimation is achieved using emotion estimation functions, 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.

[0048] The request analysis unit can perform requests while considering the timing and frequency of their submission. For example, in the case of a customer who frequently submits requests, the AI ​​can analyze their history in detail and extract patterns. For example, in the case of a customer who submits requests at a specific time, the AI ​​can also consider that time when performing the analysis. For example, in the case of a customer who submits requests infrequently, the AI ​​can also perform a simplified analysis of their history and extract important information. This allows for more appropriate responses by considering the timing and frequency of requests during the analysis. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0049] The personality analysis unit can improve the accuracy of its analysis by referring to past inquiry history during personality analysis. For example, the personality analysis unit can refer to cases where similar inquiries were resolved in the past, and the AI ​​can reflect those methods in the analysis. For example, the personality analysis unit can also have the AI ​​suggest the optimal analysis method based on past inquiry history. For example, the personality analysis unit can have the AI ​​improve the accuracy of its analysis based on past success stories. In this way, the accuracy of the analysis is improved by referring to past inquiry history. Emotion estimation is achieved using emotion estimation functions, 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.

[0050] The personality analysis unit can analyze a customer's social media activity and analyze relevant personality information during personality analysis. For example, if a customer is very active on social media, the AI ​​can analyze their personality based on that activity. If a customer is inactive on social media, the AI ​​can also perform a simplified analysis of their activity and analyze their personality. If a customer is active on a specific social media platform, the AI ​​can analyze their personality based on information from that platform. This allows for more appropriate responses by analyzing the customer's social media activity. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0051] The solution direction proposal unit can make optimal proposals by referring to past successful cases when proposing solutions. For example, the solution direction proposal unit can refer to cases where similar claims were resolved in the past, and the AI ​​will reflect those methods in the proposal. For example, the solution direction proposal unit can also have the AI ​​propose the optimal solution direction based on past successful cases. For example, the solution direction proposal unit can also have the AI ​​improve the accuracy of the proposal based on past successful cases. Thus, the accuracy of the proposal is improved by referring to past successful cases. Sentiment estimation is achieved using sentiment estimation functions, 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.

[0052] The solution direction proposal unit can make optimal suggestions by considering the customer's geographical location information when proposing solutions. For example, if the customer is in a specific region, the AI ​​will make suggestions based on information for that region. For example, if the customer is in a different region, the AI ​​can make suggestions based on information for that region. For example, if the customer is on the move, the AI ​​can make suggestions considering the customer's movement pattern. This makes it possible to make more appropriate suggestions by considering the customer's geographical location information. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0053] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0054] The call center system can also be equipped with a background sound analysis unit that analyzes background noise during customer calls. The background sound analysis unit analyzes the ambient noise during a call to understand the call situation. For example, if the background noise is loud, it can notify the operator that the call is difficult and prompt them to take appropriate action. It can also estimate the customer's location from the background noise and provide appropriate advice. For example, if traffic noise is heard during a call, it can estimate that the customer is on the move and provide concise advice that can be used even while moving. This enables responses that take background noise into account, allowing for the provision of more appropriate service.

[0055] The call center system can also be equipped with a background sound analysis unit that analyzes background noise during customer calls. The background sound analysis unit analyzes the ambient noise during a call to understand the call situation. For example, if the background noise is loud, it can notify the operator that the call is difficult and prompt them to take appropriate action. It can also estimate the customer's location from the background noise and provide appropriate advice. For example, if traffic noise is heard during a call, it can estimate that the customer is on the move and provide concise advice that can be used even while moving. This enables responses that take background noise into account, allowing for the provision of more appropriate service.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The emotion analysis unit analyzes the current call content. The emotion analysis unit uses voice analysis technology to estimate the customer's emotions during the call. For example, it can analyze the tone and speed of the voice, the choice of words, etc., to estimate whether the customer is angry, satisfied, or anxious. It can also use voice recognition technology to convert the call content into text data and analyze that text data. Step 2: The history analysis unit learns from past inquiry history and analyzes the customer's personality and inquiry tendencies. The history analysis unit stores past call history and inquiry content in a database and analyzes that data. For example, it can understand the customer's personality and what kinds of inquiries they frequently make from past call history. Furthermore, machine learning algorithms can be used to model the customer's personality and inquiry tendencies. Step 3: The advice unit provides advice during escalation based on the analysis results obtained by the emotion analysis unit and the history analysis unit. The advice unit includes a response history summary unit that summarizes the response history, a request analysis unit that analyzes the request, a personality analysis unit that analyzes the personality, and a solution direction proposal unit that suggests the best course of action. As a result, the call center system can improve the complaint resolution rate by analyzing the current call content and past inquiry history and providing appropriate advice during escalation.

[0058] (Example of form 2) The call center system according to an embodiment of the present invention is a system for streamlining customer service in a call center and increasing the complaint resolution rate. This call center system uses AI to learn from current call content and past inquiry history to analyze the customer's emotions, personality, and inquiry tendencies. Next, based on the analysis results, the AI ​​advises on the "summary of the handling process," "requests," "personality," and "best solution direction" when handling an escalation. Based on this advice, the direction of the escalation is determined, and the complaint resolution rate is increased. First, the AI ​​is trained on current call content and past inquiry history. At this time, the AI ​​analyzes the customer's emotions, personality, and inquiry tendencies. For example, it is possible to understand what kind of personality the customer has and what kind of inquiries they frequently make from past call history. This allows for a detailed understanding of the customer's characteristics. Next, based on the analysis results, the AI ​​advises on the "summary of the handling process," "requests," "personality," and "best solution direction" when handling an escalation. For example, it can summarize what kind of complaints the customer has made in the past and what kind of responses were given, and propose the optimal solution for the current complaint. This allows for a quick determination of the direction of the escalation. Furthermore, based on AI advice, the direction of escalation handling is determined, increasing the complaint resolution rate. For example, by having operator crews take specific actions based on the solutions suggested by the AI, customer satisfaction can be improved. This leads to an increased complaint resolution rate and improved efficiency of the call center. This system streamlines customer service in the call center and improves the complaint resolution rate. By suggesting the optimal response method based on the customer characteristics analyzed by the AI, the burden on operator crews is reduced, enabling quick and appropriate responses. For example, by having operator crews take specific actions based on the solutions suggested by the AI, customer satisfaction can be improved. This leads to an increased complaint resolution rate and improved efficiency of the call center. As a result, the call center system can streamline customer service and increase the complaint resolution rate.

[0059] The call center system according to this embodiment comprises an emotion analysis unit, a history analysis unit, and an advice unit. The emotion analysis unit analyzes the content of the current call. The emotion analysis unit estimates the emotions of the customer during the call, for example, using voice analysis technology. The emotion analysis unit can estimate whether the customer is angry, satisfied, or anxious by analyzing, for example, the tone and speed of the voice and the choice of words. The emotion analysis unit can also convert the content of the call into text data using, for example, voice recognition technology, and analyze that text data. The history analysis unit learns from past inquiry history and analyzes the customer's personality and inquiry tendencies. The history analysis unit can, for example, store past call history and inquiry content in a database and analyze that data. The history analysis unit can, for example, understand what kind of personality the customer has and what kind of inquiries they frequently make from past call history. The history analysis unit can also model the customer's personality and inquiry tendencies using, for example, a machine learning algorithm. The advice unit provides advice when handling escalations based on the analysis results obtained by the emotion analysis unit and the history analysis unit. The advice unit includes, for example, a response history summary unit that summarizes the response history. The advice unit includes, for example, a request analysis unit that analyzes requests. The advice unit includes, for example, a personality analysis unit that analyzes personality. The advice unit includes, for example, a solution direction proposal unit that suggests the best course of action. As a result, the call center system according to the embodiment can improve the complaint resolution rate by analyzing the current call content and past inquiry history and providing appropriate advice when handling escalations.

[0060] The emotion analysis unit analyzes the current call content. For example, it estimates the customer's emotions during a call using voice analysis technology. Specifically, voice analysis technology extracts features such as tone, speed, pitch, and emphasized words, and estimates emotions based on these features. For example, if the voice tone is high and the speed is fast, it is determined that the customer is likely angry. Conversely, if the voice tone is low and the speed is slow, it is determined that the customer is likely calm or satisfied. Furthermore, the emotion analysis unit can also convert the call content into text data using voice recognition technology and analyze that text data. For the analysis of the text data, natural language processing technology is used to analyze word choice and context to more accurately estimate the customer's emotions. For example, if there are many negative words or strong expressions, it is determined that the customer is likely feeling dissatisfied. The emotion analysis unit provides these analysis results in real time to help operators respond quickly. In this way, the emotion analysis unit can accurately understand the customer's emotions and provide important information for taking appropriate action.

[0061] The history analysis department learns from past inquiry history and analyzes customer personalities and inquiry trends. Specifically, the history analysis department stores past call history and inquiry content in a database and analyzes that data. For example, from past call history, it can understand what kind of personality a customer has and what kinds of inquiries they frequently make. The history analysis department can also model customer personalities and inquiry trends using machine learning algorithms. For example, it can use clustering algorithms to classify customers into multiple groups and understand the characteristics of each group. In addition, the history analysis department can analyze past inquiry content to understand what kinds of problems customers are facing and what kinds of solutions they are seeking. This allows the history analysis department to accurately understand customer personalities and inquiry trends and provide important information for operators to respond appropriately. Furthermore, based on past data, the history analysis department can also predict future inquiry trends and take countermeasures in advance. For example, if there is a tendency for certain inquiries to increase during a particular period, countermeasures such as strengthening operator training in preparation for that period can be taken. In this way, the history analysis department can play an important role in improving the efficiency of the call center and customer satisfaction.

[0062] The Advice Unit provides advice during escalation based on the analysis results obtained by the Emotion Analysis Unit and the History Analysis Unit. Specifically, the Advice Unit includes a Response History Summarization Unit that summarizes the history of the response. The Response History Summarization Unit summarizes past response history, enabling operators to quickly grasp the situation. For example, it concisely summarizes past call content and response results, providing important information relevant to the current situation. The Advice Unit also includes a Request Analysis Unit that analyzes requests. The Request Analysis Unit analyzes customer requests and proposes the most appropriate response. For example, if a customer is seeking information about a specific product, it provides detailed information about that product. Furthermore, the Advice Unit includes a Personality Analysis Unit that analyzes personality. The Personality Analysis Unit analyzes the customer's personality and proposes a response tailored to that personality. For example, if a customer has a cautious personality, it proposes a response that provides detailed explanations and reassures the customer. In addition, the Advice Unit includes a Solution Direction Proposal Unit that proposes the best course of action. The Solution Direction Proposal Unit proposes the optimal solution based on the analysis results of the Emotion Analysis Unit and the History Analysis Unit. For example, if a customer is dissatisfied, it proposes specific measures to resolve that dissatisfaction. This allows the advisory department to provide appropriate advice during escalation and increase the complaint resolution rate. Furthermore, the advisory department can contribute to improving the skills of operators, thereby enhancing the overall service quality of the call center.

[0063] The advice unit includes a response history summary unit that summarizes the history of responses. The response history summary unit provides a summary of the response history when an escalation occurs. For example, the response history summary unit summarizes the history of responses to the current claim based on past response history. For example, the response history summary unit can refer to successful past claim responses and propose the optimal response method for the current claim. For example, the response history summary unit can store past response history in a database and analyze that data. This enables quick and appropriate responses by providing a summary of the response history when an escalation occurs.

[0064] The advisory department includes a requirements analysis department that analyzes customer requests. The requirements analysis department analyzes customer requests. For example, the requirements analysis department analyzes customer requests based on past inquiries. For example, the requirements analysis department can understand what kind of requests customers have based on past inquiries. The requirements analysis department can also model customer requests using machine learning algorithms, for example. This allows for more appropriate responses by analyzing customer requests.

[0065] The advice unit includes a personality analysis unit that analyzes personality. The personality analysis unit analyzes the customer's personality. For example, the personality analysis unit analyzes the customer's personality based on past inquiry history. For example, the personality analysis unit can understand what kind of personality the customer has from past inquiry history. The personality analysis unit can also model the customer's personality using machine learning algorithms, for example. This allows for more appropriate responses by analyzing the customer's personality.

[0066] The advice department includes a solution proposal department that suggests the best course of action. The solution proposal department proposes the optimal course of action. For example, the solution proposal department proposes the best solution to the current complaint based on successful past complaint handling cases. The solution proposal department can also store past handling history in a database and analyze that data. The solution proposal department can also model the optimal solution using machine learning algorithms. By proposing the optimal course of action, the complaint resolution rate can be increased.

[0067] The emotion analysis unit can estimate the customer's emotions and adjust the call content analysis method based on the estimated emotions. For example, if the customer is angry, the emotion analysis unit's AI can quickly analyze the call content and highlight areas requiring urgent attention. For example, if the customer is feeling anxious, the emotion analysis unit's AI can analyze the call content in detail and extract information to provide reassurance. For example, if the customer is satisfied, the emotion analysis unit's AI can simplify the call content and highlight positive feedback. This allows for more appropriate responses by adjusting the call content analysis method based on the customer's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0068] The emotion analysis unit can analyze the operator's emotions simultaneously with the call content analysis, taking into account the interaction between their emotions. For example, if a customer is angry, the emotion analysis unit can analyze the operator's stress level and suggest an appropriate response. For example, if a customer is sad, the emotion analysis unit can analyze the operator's level of empathy and enhance emotional support. For example, if a customer is agitated, the emotion analysis unit can analyze the operator's composure and encourage a calm response. This allows for a more appropriate response by considering the interaction between the operator's and customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0069] The sentiment analysis unit can detect changes in emotion based on specific keywords or phrases when analyzing call content. For example, if a customer says "dissatisfied," the AI ​​in the sentiment analysis unit will highlight that part and prompt a quick response. For example, if a customer says "thank you," the AI ​​in the sentiment analysis unit can also highlight that part and provide positive feedback. For example, if a customer says "I'm in trouble," the AI ​​in the sentiment analysis unit can also highlight that part and extract information for problem solving. This enables a quick response by detecting changes in emotion based on specific keywords or phrases. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0070] The emotion analysis unit can estimate the customer's emotions and adjust how the call analysis results are displayed based on the estimated emotions. For example, if the customer is angry, the emotion analysis unit may display the analysis results in red to indicate that urgent action is needed. For example, if the customer is feeling anxious, the emotion analysis unit may display the analysis results in blue to highlight reassuring information. For example, if the customer is satisfied, the emotion analysis unit may display the analysis results in green to highlight positive feedback. This allows for more appropriate responses by adjusting how the analysis results are displayed 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.

[0071] The emotion analysis unit can analyze changes in emotions by considering the time of day and day of the week when analyzing call content. For example, if a customer is angry on a weekday morning, the emotion analysis unit will take commuting stress into consideration during the analysis. For example, if a customer is feeling anxious on a weekend evening, the emotion analysis unit can also take into account their weekend relaxation time during the analysis. For example, if a customer is satisfied during the daytime on a weekday, the emotion analysis unit can also take into account their refreshing break during work during the analysis. By analyzing changes in emotions by considering the time of day and day of the week when the call is made, it becomes possible to respond more appropriately. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is not limited to, but may include, text generation AI (e.g., LLM) or multimodal generation AI.

[0072] The emotion analysis unit can improve the accuracy of emotion analysis by considering background noise and noise levels during call content analysis. For example, if there is loud background noise, the AI ​​in the emotion analysis unit will remove the noise and perform emotion analysis. For example, in the case of a call in a quiet environment, the AI ​​in the emotion analysis unit can also improve the accuracy of emotion analysis. For example, if music is playing during a call, the AI ​​in the emotion analysis unit can also consider the effect of the music when performing emotion analysis. By improving the accuracy of emotion analysis by considering background noise and noise levels, more accurate analysis becomes possible. 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.

[0073] The history analysis unit can estimate the customer's emotions and adjust the analysis method of past inquiry history based on the estimated emotions. For example, if the customer was angry in the past, the AI ​​in the history analysis unit can highlight that history and indicate that urgent action is needed. For example, if the customer felt anxious in the past, the AI ​​in the history analysis unit can analyze that history in detail and extract information that provides reassurance. For example, if the customer was satisfied in the past, the AI ​​in the history analysis unit can simplify that history and highlight positive feedback. This allows for more appropriate responses by adjusting the analysis method of past inquiry history based on the customer's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0074] The history analysis unit can analyze past inquiry history while considering the frequency and time of inquiry. For example, in the case of a customer who makes frequent inquiries, the AI ​​in the history analysis unit can analyze the history in detail and extract patterns. For example, in the case of a customer who makes inquiries at a specific time, the AI ​​in the history analysis unit can also consider that time of day when performing the analysis. For example, in the case of a customer who makes infrequent inquiries, the AI ​​in the history analysis unit can also analyze the history in a simplified manner and extract important information. This allows for more appropriate responses by considering the frequency and time of inquiry when performing the analysis. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0075] The history analysis unit can apply different analysis algorithms to each category of inquiry when analyzing past inquiry history. For example, in the case of a technical inquiry, the AI ​​can analyze the technical information in detail. For example, in the case of a service inquiry, the AI ​​can also analyze the service information in detail. For example, in the case of a complaint inquiry, the AI ​​can analyze the complaint information in detail and indicate that urgent action is required. This allows for more appropriate responses by applying different analysis algorithms to each category of inquiry. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0076] The history analysis unit can estimate the customer's emotions and adjust how the analysis results of past inquiry history are displayed based on the estimated emotions. For example, if the customer was angry in the past, the history analysis unit can display the analysis results in red to indicate that urgent action is needed. For example, if the customer was anxious in the past, the history analysis unit can display the analysis results in blue to highlight reassuring information. For example, if the customer was satisfied in the past, the history analysis unit can display the analysis results in green to highlight positive feedback. This allows for more appropriate responses by adjusting how the analysis results are displayed 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 includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0077] The history analysis unit can analyze past inquiry history while considering the customer's geographical location information. For example, if a customer makes an inquiry from a specific region, the AI ​​in the history analysis unit will consider the information of that region when performing the analysis. For example, if a customer makes an inquiry from a different region, the AI ​​in the history analysis unit can also consider the information of each region when performing the analysis. For example, if a customer makes an inquiry while traveling, the AI ​​in the history analysis unit can also consider the travel pattern when performing the analysis. This allows for a more appropriate response by considering the customer's geographical location information when performing the analysis. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0078] The history analysis unit can analyze customers' social media activity and related inquiry history when analyzing past inquiry history. For example, if a customer is very active on social media, the AI ​​will take that activity into consideration during the analysis. If a customer is inactive on social media, the AI ​​can perform a simplified analysis. If a customer is active on a specific social media platform, the AI ​​can also take that platform's information into consideration during the analysis. This allows for more appropriate responses by analyzing customers' social media activity. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0079] The advice unit can estimate the customer's emotions and adjust the way it expresses advice based on those emotions. For example, if the customer is angry, the AI ​​will provide advice using calm and polite language. If the customer is feeling anxious, the AI ​​can also provide advice using reassuring language. If the customer is satisfied, the AI ​​can also provide advice using positive language. By adjusting the way advice is expressed based on the customer's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0080] The advisory unit can provide optimal advice by referring to past successful escalation cases when giving advice. For example, the advisory unit can refer to cases where similar claims were resolved in the past, and the AI ​​will advise on how to do so. For example, the advisory unit can refer to patterns of successful escalation cases in the past, and the AI ​​can advise on those patterns. For example, the advisory unit can have the AI ​​advise on the optimal solution based on past success cases. This allows for more appropriate advice by referring to past success cases. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0081] The advice unit can customize advice by considering the customer's current situation and background information. For example, if the customer provides a detailed explanation of their current situation, the AI ​​will customize the advice based on that information. The advice unit can also consider the customer's background information and have the AI ​​provide the most appropriate advice. The advice unit can also adjust the content of the advice according to the customer's current situation. This allows for more appropriate advice by considering the customer's current situation and background information. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0082] The advice unit can estimate the customer's emotions and prioritize advice based on those emotions. For example, if the customer is angry, the AI ​​will prioritize advice that requires immediate attention. If the customer is feeling anxious, the AI ​​can prioritize advice that provides reassurance. If the customer is satisfied, the AI ​​can prioritize positive feedback. By prioritizing advice based on the customer's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0083] The advice unit can provide optimal advice by considering the customer's geographical location. For example, if the customer is in a specific region, the AI ​​can provide advice based on information for that region. If the customer is in a different region, the AI ​​can also provide advice based on information for that region. If the customer is on the move, the AI ​​can also provide advice considering their movement pattern. This allows for more appropriate advice by considering the customer's geographical location. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0084] The advice unit can analyze the customer's social media activity and provide relevant advice when giving advice. For example, if the customer is very active on social media, the AI ​​can provide advice based on that activity. If the customer is inactive on social media, the AI ​​can also provide advice based on a simplified analysis of that activity. If the customer is active on a specific social media platform, the AI ​​can provide advice based on information from that platform. This allows for more appropriate advice by analyzing the customer's social media activity. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0085] The interaction history summarization unit can estimate the customer's emotions and adjust the method of summarizing the interaction history based on the estimated emotions. For example, if the customer is angry, the AI ​​can quickly summarize the interaction history and highlight areas requiring urgent attention. If the customer is feeling anxious, the AI ​​can also summarize the interaction history in detail and extract information to provide reassurance. If the customer is satisfied, the AI ​​can summarize the interaction history concisely and highlight positive feedback. This allows for a more appropriate response by adjusting the method of summarizing the interaction history based on the customer's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0086] The response history summarization unit can improve the accuracy of its summaries by referring to past response history when summarizing the response history. For example, the response history summarization unit can refer to cases where similar claims were resolved in the past, and the AI ​​reflects those methods in the summary. For example, the response history summarization unit can also have the AI ​​suggest the optimal summarization method based on past response history. For example, the response history summarization unit can have the AI ​​improve the accuracy of its summaries based on past success stories. In this way, the accuracy of the summaries is improved by referring to past response history. Sentiment estimation is achieved using sentiment estimation functions, for example, using a sentiment engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0087] The response history summary unit can estimate the customer's emotions and adjust how the summary results are displayed based on the estimated emotions. For example, if the customer is angry, the response history summary unit may display the summary results in red to indicate that urgent action is needed. For example, if the customer is feeling anxious, the response history summary unit may display the summary results in blue to highlight reassuring information. For example, if the customer is satisfied, the response history summary unit may display the summary results in green to highlight positive feedback. This allows for more appropriate responses by adjusting how the summary results are displayed 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 includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0088] The response history summarization unit can summarize the response history while considering the time of day and day of the week in which the response took place. For example, if the response was made on a weekday morning, the response history summarization unit can consider commuting stress in the summary. For example, if the response was made on a weekend evening, the response history summarization unit can consider weekend relaxation time in the summary. For example, if the response was made during the daytime on a weekday, the response history summarization unit can consider refreshment during work breaks in the summary. This allows for more appropriate responses by summarizing while considering the time of day and day of the week in which the response took place. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0089] The request analysis unit can estimate the customer's emotions and adjust the request analysis method based on the estimated emotions. For example, if the customer is angry, the AI ​​can quickly analyze the request and highlight areas requiring urgent attention. If the customer is feeling anxious, the AI ​​can analyze the request in detail and extract information to provide reassurance. If the customer is satisfied, the AI ​​can simplify the request and highlight positive feedback. This allows for a more appropriate response by adjusting the request analysis method based on the customer's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The request analysis unit can improve the accuracy of its analysis by referring to past request history when analyzing requests. For example, the request analysis unit can refer to past cases where similar requests were resolved, and the AI ​​can reflect those methods in the analysis. For example, the request analysis unit can also have the AI ​​propose the optimal analysis method based on past request history. For example, the request analysis unit can have the AI ​​improve the accuracy of its analysis based on past success stories. In this way, the accuracy of the analysis is improved by referring to past request history. Emotion estimation is achieved using emotion estimation functions, 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.

[0091] The request analysis unit can estimate the customer's emotions and adjust how the request analysis results are displayed based on the estimated emotions. For example, if the customer is angry, the request analysis unit can display the analysis results in red to indicate that urgent action is needed. For example, if the customer is feeling anxious, the request analysis unit can display the analysis results in blue to highlight reassuring information. For example, if the customer is satisfied, the request analysis unit can display the analysis results in green to highlight positive feedback. This allows for more appropriate responses by adjusting how the analysis results are displayed 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 includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The request analysis unit can perform requests while considering the timing and frequency of their submission. For example, in the case of a customer who frequently submits requests, the AI ​​can analyze their history in detail and extract patterns. For example, in the case of a customer who submits requests at a specific time, the AI ​​can also consider that time when performing the analysis. For example, in the case of a customer who submits requests infrequently, the AI ​​can also perform a simplified analysis of their history and extract important information. This allows for more appropriate responses by considering the timing and frequency of requests during the analysis. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0093] The personality analysis unit can estimate the customer's emotions and adjust the personality analysis method based on the estimated emotions. For example, if the customer is angry, the AI ​​can quickly analyze their personality and highlight areas requiring urgent attention. If the customer is feeling anxious, the AI ​​can analyze their personality in detail and extract information to provide reassurance. If the customer is satisfied, the AI ​​can simplify the personality analysis and highlight positive feedback. This allows for a more appropriate response by adjusting the personality analysis method based on the customer's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0094] The personality analysis unit can improve the accuracy of its analysis by referring to past inquiry history during personality analysis. For example, the personality analysis unit can refer to cases where similar inquiries were resolved in the past, and the AI ​​can reflect those methods in the analysis. For example, the personality analysis unit can also have the AI ​​suggest the optimal analysis method based on past inquiry history. For example, the personality analysis unit can have the AI ​​improve the accuracy of its analysis based on past success stories. In this way, the accuracy of the analysis is improved by referring to past inquiry history. Emotion estimation is achieved using emotion estimation functions, 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.

[0095] The personality analysis unit can estimate the customer's emotions and adjust how the personality analysis results are displayed based on the estimated emotions. For example, if the customer is angry, the personality analysis unit can display the analysis results in red to indicate that urgent action is needed. For example, if the customer is feeling anxious, the personality analysis unit can display the analysis results in blue to highlight reassuring information. For example, if the customer is satisfied, the personality analysis unit can display the analysis results in green to highlight positive feedback. This allows for more appropriate responses by adjusting how the analysis results are displayed 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 includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The personality analysis unit can analyze a customer's social media activity and analyze relevant personality information during personality analysis. For example, if a customer is very active on social media, the AI ​​can analyze their personality based on that activity. If a customer is inactive on social media, the AI ​​can also perform a simplified analysis of their activity and analyze their personality. If a customer is active on a specific social media platform, the AI ​​can analyze their personality based on information from that platform. This allows for more appropriate responses by analyzing the customer's social media activity. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0097] The solution suggestion unit can estimate the customer's emotions and adjust its solution suggestion method based on those emotions. For example, if the customer is angry, the AI ​​can quickly suggest solutions and highlight areas requiring urgent attention. If the customer is feeling anxious, the AI ​​can suggest solutions in detail and extract information to provide reassurance. If the customer is satisfied, the AI ​​can suggest solutions concisely and highlight positive feedback. This allows for a more appropriate response by adjusting the solution suggestion method based on the customer's emotions. Emotion estimation is achieved using emotion estimation functions, 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.

[0098] The solution direction proposal unit can make optimal proposals by referring to past successful cases when proposing solutions. For example, the solution direction proposal unit can refer to cases where similar claims were resolved in the past, and the AI ​​will reflect those methods in the proposal. For example, the solution direction proposal unit can also have the AI ​​propose the optimal solution direction based on past successful cases. For example, the solution direction proposal unit can also have the AI ​​improve the accuracy of the proposal based on past successful cases. Thus, the accuracy of the proposal is improved by referring to past successful cases. Sentiment estimation is achieved using sentiment estimation functions, 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.

[0099] The solution suggestion unit can estimate the customer's emotions and adjust how the suggested solutions are displayed based on those emotions. For example, if the customer is angry, the solution suggestion unit might display the suggested solutions in red to indicate that urgent action is needed. For example, if the customer is feeling anxious, the solution suggestion unit might display the suggested solutions in blue to highlight reassuring information. For example, if the customer is satisfied, the solution suggestion unit might display the suggested solutions in green to highlight positive feedback. By adjusting how the suggested solutions are displayed based on the customer's emotions, a more appropriate response becomes possible. 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.

[0100] The solution direction proposal unit can make optimal suggestions by considering the customer's geographical location information when proposing solutions. For example, if the customer is in a specific region, the AI ​​will make suggestions based on information for that region. For example, if the customer is in a different region, the AI ​​can make suggestions based on information for that region. For example, if the customer is on the move, the AI ​​can make suggestions considering the customer's movement pattern. This makes it possible to make more appropriate suggestions by considering the customer's geographical location information. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[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 call center system can also be equipped with a background sound analysis unit that analyzes background noise during customer calls. The background sound analysis unit analyzes the ambient noise during a call to understand the call situation. For example, if the background noise is loud, it can notify the operator that the call is difficult and prompt them to take appropriate action. It can also estimate the customer's location from the background noise and provide appropriate advice. For example, if traffic noise is heard during a call, it can estimate that the customer is on the move and provide concise advice that can be used even while moving. This enables responses that take background noise into account, allowing for the provision of more appropriate service.

[0103] The call center system can also be equipped with a speech rate analysis unit that analyzes the customer's speaking speed during a call. The speech rate analysis unit analyzes the customer's speaking speed and estimates their emotions and level of urgency. For example, if the customer speaks quickly, it can be estimated that the situation is urgent, and prompt action can be encouraged. Conversely, if the customer speaks slowly, it can be estimated that the customer is calm, and a detailed explanation can be provided. Furthermore, by analyzing changes in speech speed, it is possible to grasp changes in the customer's emotions in real time. This enables responses that take speech speed into consideration, allowing for the provision of more appropriate service.

[0104] The call center system can also be equipped with a word choice analysis unit that analyzes the customer's choice of words during a call. The word choice analysis unit analyzes the words and phrases used by the customer and estimates their emotions and personality. For example, if the customer uses polite language, it can be estimated that they are calm, and a detailed explanation can be provided. Conversely, if they use aggressive language, it can be estimated that they are angry, and a quick response can be prompted. Furthermore, by analyzing specific keywords and phrases, it can quickly grasp the customer's requests and problems. This enables responses that take word choice into consideration, allowing for the provision of more appropriate service.

[0105] The call center system can also be equipped with a tone analysis unit that analyzes the tone of the customer's voice during a call. The tone analysis unit analyzes the tone of the customer's voice and estimates their emotions and level of urgency. For example, if the customer's voice tone is high, it can be estimated that the situation is urgent, and prompt action can be encouraged. Conversely, if the voice tone is low, it can be estimated that the customer is calm, and a more detailed explanation can be provided. Furthermore, by analyzing changes in voice tone, it is possible to grasp changes in the customer's emotions in real time. This enables responses that take voice tone into consideration, allowing for the provision of more appropriate service.

[0106] The call center system can also include a silence analysis unit that analyzes the duration of silence during a customer's call. This unit analyzes the silence during a call to estimate the customer's emotions and level of urgency. For example, if a customer remains silent for a long time, it can be estimated that they are confused, allowing the operator to proactively provide support. Conversely, if short silences occur frequently, it can be estimated that the customer is anxious, prompting a quick response. Furthermore, by analyzing changes in the duration of silence, the system can grasp changes in the customer's emotions in real time. This enables responses that take silence into account, resulting in more appropriate service.

[0107] The call center system can also be equipped with a background sound analysis unit that analyzes background noise during customer calls. The background sound analysis unit analyzes the ambient noise during a call to understand the call situation. For example, if the background noise is loud, it can notify the operator that the call is difficult and prompt them to take appropriate action. It can also estimate the customer's location from the background noise and provide appropriate advice. For example, if traffic noise is heard during a call, it can estimate that the customer is on the move and provide concise advice that can be used even while moving. This enables responses that take background noise into account, allowing for the provision of more appropriate service.

[0108] The call center system can also be equipped with a speech rate analysis unit that analyzes the customer's speaking speed during a call. The speech rate analysis unit analyzes the customer's speaking speed and estimates their emotions and level of urgency. For example, if the customer speaks quickly, it can be estimated that the situation is urgent, and prompt action can be encouraged. Conversely, if the customer speaks slowly, it can be estimated that the customer is calm, and a detailed explanation can be provided. Furthermore, by analyzing changes in speech speed, it is possible to grasp changes in the customer's emotions in real time. This enables responses that take speech speed into consideration, allowing for the provision of more appropriate service.

[0109] The call center system can also be equipped with a word choice analysis unit that analyzes the customer's choice of words during a call. The word choice analysis unit analyzes the words and phrases used by the customer and estimates their emotions and personality. For example, if the customer uses polite language, it can be estimated that they are calm, and a detailed explanation can be provided. Conversely, if they use aggressive language, it can be estimated that they are angry, and a quick response can be prompted. Furthermore, by analyzing specific keywords and phrases, it can quickly grasp the customer's requests and problems. This enables responses that take word choice into consideration, allowing for the provision of more appropriate service.

[0110] The call center system can also be equipped with a tone analysis unit that analyzes the tone of the customer's voice during a call. The tone analysis unit analyzes the tone of the customer's voice and estimates their emotions and level of urgency. For example, if the customer's voice tone is high, it can be estimated that the situation is urgent, and prompt action can be encouraged. Conversely, if the voice tone is low, it can be estimated that the customer is calm, and a more detailed explanation can be provided. Furthermore, by analyzing changes in voice tone, it is possible to grasp changes in the customer's emotions in real time. This enables responses that take voice tone into consideration, allowing for the provision of more appropriate service.

[0111] The call center system can also include a silence analysis unit that analyzes the duration of silence during a customer's call. This unit analyzes the silence during a call to estimate the customer's emotions and level of urgency. For example, if a customer remains silent for a long time, it can be estimated that they are confused, allowing the operator to proactively provide support. Conversely, if short silences occur frequently, it can be estimated that the customer is anxious, prompting a quick response. Furthermore, by analyzing changes in the duration of silence, the system can grasp changes in the customer's emotions in real time. This enables responses that take silence into account, resulting in more appropriate service.

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

[0113] Step 1: The emotion analysis unit analyzes the current call content. The emotion analysis unit uses voice analysis technology to estimate the customer's emotions during the call. For example, it can analyze the tone and speed of the voice, the choice of words, etc., to estimate whether the customer is angry, satisfied, or anxious. It can also use voice recognition technology to convert the call content into text data and analyze that text data. Step 2: The history analysis unit learns from past inquiry history and analyzes the customer's personality and inquiry tendencies. The history analysis unit stores past call history and inquiry content in a database and analyzes that data. For example, it can understand the customer's personality and what kinds of inquiries they frequently make from past call history. Furthermore, machine learning algorithms can be used to model the customer's personality and inquiry tendencies. Step 3: The advice unit provides advice during escalation based on the analysis results obtained by the emotion analysis unit and the history analysis unit. The advice unit includes a response history summary unit that summarizes the response history, a request analysis unit that analyzes the request, a personality analysis unit that analyzes the personality, and a solution direction proposal unit that suggests the best course of action. As a result, the call center system can improve the complaint resolution rate by analyzing the current call content and past inquiry history and providing appropriate advice during escalation.

[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 emotion analysis unit, history analysis unit, and advice unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the emotion analysis unit estimates the customer's emotions during a call using the microphone 38B of the smart device 14, and this is analyzed by the control unit 46A. The history analysis unit learns past inquiry history using the identification processing unit 290 of the data processing unit 12 and analyzes the customer's personality and inquiry tendencies. The advice unit is implemented by the identification processing unit 290 of the data processing unit 12 and provides advice when handling escalations based on the analysis results of the emotion analysis unit and the history analysis unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[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 emotion analysis unit, history analysis unit, and advice unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the emotion analysis unit estimates the customer's emotions during a call using the microphone 238 of the smart glasses 214, and this is analyzed by the control unit 46A. The history analysis unit learns past inquiry history using the identification processing unit 290 of the data processing unit 12 and analyzes the customer's personality and inquiry tendencies. The advice unit is implemented by the identification processing unit 290 of the data processing unit 12 and provides advice when escalating based on the analysis results of the emotion analysis unit and the history analysis unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[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 emotion analysis unit, history analysis unit, and advice unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the emotion analysis unit estimates the customer's emotions during a call using the microphone 238 of the headset terminal 314, and this is analyzed by the control unit 46A. The history analysis unit learns past inquiry history using the identification processing unit 290 of the data processing unit 12 and analyzes the customer's personality and inquiry tendencies. The advice unit is implemented by the identification processing unit 290 of the data processing unit 12 and provides advice when handling escalations based on the analysis results of the emotion analysis unit and the history analysis unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[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 emotion analysis unit, history analysis unit, and advice unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the emotion analysis unit estimates the customer's emotions during a call using the microphone 238 of the robot 414, and this is analyzed by the control unit 46A. The history analysis unit learns past inquiry history using the identification processing unit 290 of the data processing unit 12 and analyzes the customer's personality and inquiry tendencies. The advice unit is implemented by the identification processing unit 290 of the data processing unit 12 and provides advice when handling escalations based on the analysis results of the emotion analysis unit and the history analysis unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[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 emotion analysis unit analyzes the current call content, The history analysis department learns from past inquiry history and analyzes customer personalities and inquiry trends, The system includes an advice unit that provides advice when responding to an escalation, based on the analysis results obtained by the emotion analysis unit and the history analysis unit. A system characterized by the following features. (Note 2) It includes a section for summarizing the history of the response. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a requirements analysis unit to analyze customer requests. The system described in Appendix 1, characterized by the features described herein. (Note 4) It is equipped with a personality analysis unit that analyzes personality. The system described in Appendix 1, characterized by the features described herein. (Note 5) We have a solution proposal department that proposes the best possible solutions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned emotion analysis unit, We estimate the customer's emotions and adjust the call content analysis method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned emotion analysis unit, When analyzing call content, the operator's emotions are also analyzed simultaneously, taking into account the interaction of emotions between both parties. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned emotion analysis unit, When analyzing call content, changes in emotion are detected based on specific keywords or phrases. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned emotion analysis unit, We estimate the customer's emotions and adjust how the call content analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned emotion analysis unit, When analyzing call content, the time of day and day of the week are taken into consideration to analyze changes in emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned emotion analysis unit, When analyzing call content, background noise and noise levels are taken into consideration to improve the accuracy of emotion analysis. The system described in Appendix 1, characterized by the features described herein. (Note 12) The history analysis unit, We estimate the customer's emotions and adjust the analysis method of past inquiry history based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The history analysis unit, When analyzing past inquiry history, the frequency and time of day of inquiries are taken into consideration during the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 14) The history analysis unit, When analyzing past inquiry history, different analysis algorithms are applied to each category of inquiry content. The system described in Appendix 1, characterized by the features described herein. (Note 15) The history analysis unit, We estimate the customer's emotions and adjust how the analysis results of past inquiry history are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The history analysis unit, When analyzing past inquiry history, the analysis will take into account the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 17) The history analysis unit, When analyzing past inquiry history, we analyze the customer's social media activity and analyze related inquiry history. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned advice section, We estimate the customer's emotions and adjust the way we express advice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned advice section, When providing advice, we refer to past successful escalation cases to offer the most appropriate guidance. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned advice section, When providing advice, we customize it by taking into account the client's current situation and background information. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned advice section, We estimate the customer's emotions and prioritize advice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned advice section, When providing advice, we take the customer's geographical location into consideration to provide the most appropriate advice. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned advice section, When providing advice, we analyze the client's social media activity and offer relevant advice. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned summary of the response history section is: We estimate the customer's emotions and adjust the method of summarizing the interaction history based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 25) The aforementioned summary of the response history section is: When summarizing the history of the response, we refer to past response records to improve the accuracy of the summary. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned summary of the response history section is: We estimate the customer's emotions and adjust how the summary of the interaction history is displayed based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned summary of the response history section is: When summarizing the response process, take into account the time of day and day of the week the response took place. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned requirements analysis unit, We estimate the customer's emotions and adjust the method of analyzing their requests based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 29) The aforementioned requirements analysis unit, When analyzing requests, we improve the accuracy of the analysis by referring to past request history. The system described in Appendix 3, characterized by the features described herein. (Note 30) The aforementioned requirements analysis unit, We estimate the customer's emotions and adjust how the analysis results of their requests are displayed based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 31) The aforementioned requirements analysis unit, When analyzing requests, the timing and frequency of requests will be taken into consideration. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned personality analysis unit, We estimate the customer's emotions and adjust the personality analysis method based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 33) The aforementioned personality analysis unit, When analyzing personality traits, past inquiry history is referenced to improve the accuracy of the analysis. The system described in Appendix 4, characterized by the features described herein. (Note 34) The aforementioned personality analysis unit, We estimate the customer's emotions and adjust how the personality analysis results are displayed based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 35) The aforementioned personality analysis unit, During personality analysis, we analyze the customer's social media activity and analyze relevant personality information. The system described in Appendix 4, characterized by the features described herein. (Note 36) The aforementioned solution direction proposal unit We estimate the customer's emotions and adjust the approach to suggesting solutions based on those estimated emotions. The system described in Appendix 5, characterized by the features described herein. (Note 37) The aforementioned solution direction proposal unit When proposing solutions, we refer to past success stories to make the most appropriate proposals. The system described in Appendix 5, characterized by the features described herein. (Note 38) The aforementioned solution direction proposal unit We estimate the customer's emotions and adjust how the suggested solutions are displayed based on those estimated emotions. The system described in Appendix 5, characterized by the features described herein. (Note 39) The aforementioned solution direction proposal unit When proposing solutions, we will consider the customer's geographical location to provide the most suitable proposal. The system described in Appendix 5, 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 emotion analysis unit analyzes the current call content, The history analysis department learns from past inquiry history and analyzes customer personalities and inquiry trends, The system includes an advice unit that provides advice when responding to an escalation, based on the analysis results obtained by the emotion analysis unit and the history analysis unit. A system characterized by the following features.

2. It includes a section for summarizing the history of the response. The system according to feature 1.

3. It includes a requirements analysis unit to analyze customer requests. The system according to feature 1.

4. It is equipped with a personality analysis unit that analyzes personality. The system according to feature 1.

5. We have a solution proposal department that proposes the best possible solutions. The system according to feature 1.

6. The aforementioned emotion analysis unit, We estimate the customer's emotions and adjust the call content analysis method based on the estimated emotions. The system according to feature 1.

7. The aforementioned emotion analysis unit, When analyzing call content, the operator's emotions are also analyzed simultaneously, taking into account the interaction of emotions between both parties. The system according to feature 1.

8. The aforementioned emotion analysis unit, When analyzing call content, changes in emotion are detected based on specific keywords or phrases. The system according to feature 1.

9. The aforementioned emotion analysis unit, We estimate the customer's emotions and adjust how the call content analysis results are displayed based on those estimated emotions. The system according to feature 1.

10. The aforementioned emotion analysis unit, When analyzing call content, the time of day and day of the week are taken into consideration to analyze changes in emotions. The system according to feature 1.

Images