system

Abstract

The system according to this embodiment aims to reduce stress and facilitate smooth communication by analyzing conversations between customers and employees, performing sentiment analysis, and intervening appropriately. [Solution] The system according to the embodiment comprises an analysis unit, an emotion analysis unit, an intervention unit, a recording unit, and a support unit. The analysis unit analyzes conversations between customers and employees in real time. The emotion analysis unit analyzes the emotions of the conversations analyzed by the analysis unit. The intervention unit intervenes in the conversation based on the analysis results obtained by the emotion analysis unit. The recording unit records the data obtained by the analysis unit and the emotion analysis unit. The support unit provides support to employees based on the results obtained by the emotion analysis unit and the intervention unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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 room for improvement in reducing the stress of employees and realizing smooth communication with customers in claim handling at a customer service center.

[0005] The system according to the embodiment aims to reduce stress and realize smooth communication by analyzing the conversation between a customer and an employee, performing sentiment analysis, and intervening appropriately.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, an emotion analysis unit, an intervention unit, a recording unit, and a support unit. The analysis unit analyzes conversations between customers and employees in real time. The emotion analysis unit analyzes the emotions of the conversations analyzed by the analysis unit. The intervention unit intervenes in the conversation based on the analysis results obtained by the emotion analysis unit. The recording unit records the data obtained by the analysis unit and the emotion analysis unit. The support unit provides support to employees based on the results obtained by the emotion analysis unit and the intervention unit. [Effects of the Invention]

[0007] The system according to this embodiment can reduce stress and facilitate smooth communication by analyzing conversations between customers and employees, performing sentiment analysis, and intervening appropriately. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), 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.[[ID=​​​​​​​​​​​​​​​​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 Customer Center Employee Stress Reduction System according to an embodiment of the present invention is a system for reducing stress among employees working in a customer center and lowering employee turnover. This system utilizes natural language processing (NLP) and sentiment analysis technology, with AI analyzing conversations from a neutral standpoint and intervening in conversations as needed to reduce stress for both customers and employees. For example, the Customer Center Employee Stress Reduction System uses AI to analyze conversations between customers and employees in real time. The AI ​​uses natural language processing technology to understand the content of the conversation and sentiment analysis technology to determine the tone and emotional shifts of the conversation. For example, if a customer is making a complaint unilaterally, the AI ​​detects this situation and makes a neutral statement such as, "Sir / Madam, you have been speaking unilaterally for 10 minutes. Is that a problem?" In this way, the AI ​​intervenes in the conversation from a third-party perspective, providing an opportunity for both the customer and the employee to calm down. Next, the AI ​​records the conversation and accumulates data for later analysis. This makes it possible to understand what situations increase stress and what responses are effective. For example, if certain phrases or tones amplify a customer's anger, this information can be used to improve the employee's response methods. Furthermore, the AI ​​provides real-time support to employees. For example, if a customer is emotional, the AI ​​will advise the employee to "remain calm." This allows employees to respond appropriately without feeling stressed. This system reduces stress for employees working in customer centers and lowers employee turnover. In addition, neutral responses to customers improve customer satisfaction. For example, even if a customer is making a one-sided complaint, the AI's neutral comments can help the customer calm down, enabling a constructive conversation toward problem resolution. Thus, an AI system utilizing natural language processing and sentiment analysis technology has the effect of reducing employee stress in customer centers, lowering employee turnover, and improving customer satisfaction. In summary, a customer center employee stress reduction system can reduce employee stress and lower employee turnover.

[0029] The customer center employee stress reduction system according to this embodiment comprises an analysis unit, an emotion analysis unit, an intervention unit, a recording unit, and a support unit. The analysis unit analyzes conversations between customers and employees in real time. The analysis unit understands the content of conversations using, for example, natural language processing technology. For example, the analysis unit breaks down words in conversations using morphological analysis and analyzes sentence structure using grammatical analysis. The analysis unit can also understand the meaning of conversations using semantic analysis. The emotion analysis unit analyzes the emotions of conversations analyzed by the analysis unit. The emotion analysis unit determines, for example, the tone of conversation and emotional shifts. For example, the emotion analysis unit analyzes the tone of conversation and determines emotional shifts using speech analysis technology. The emotion analysis unit can also estimate emotions from the content of conversations using text analysis technology. The intervention unit intervenes in conversations based on the analysis results obtained by the emotion analysis unit. For example, the intervention unit makes neutral statements when a customer is making unilateral complaints. For example, the intervention unit makes neutral statements such as, "Sir / Madam, you have been speaking unilaterally for 10 minutes. Is that a problem?" The intervention unit can also make statements encouraging the customer to calm down if they are becoming emotional. The recording unit records the data obtained by the analysis unit and the sentiment analysis unit. The recording unit, for example, records conversations and stores the data for later analysis. For example, the recording unit saves the audio and text data of conversations and stores it in a database for later analysis. The support unit provides support to employees based on the results obtained by the sentiment analysis unit and the intervention unit. For example, the support unit advises employees to "remain calm" if the customer is becoming emotional. For example, the support unit provides real-time advice to employees and provides support to take appropriate action. As a result, the customer center employee stress reduction system according to this embodiment can reduce employee stress and lower the turnover rate. Some or all of the above-described processes in the analysis unit, sentiment analysis unit, intervention unit, recording unit, and support unit may be performed using AI, for example, or not using AI.For example, the analysis unit can use an AI model employing natural language processing technology to analyze customer-employee conversations in real time. The sentiment analysis unit can use an AI model employing speech analysis technology to determine the tone and emotional shifts in conversations. The intervention unit can use an AI model that generates statements based on sentiment analysis results to intervene in conversations. The recording unit can use a database management system to record conversations and accumulate data. The support unit can use an advice generation AI model to provide real-time advice to employees.

[0030] The analysis unit analyzes customer-employee conversations in real time. For example, it uses natural language processing techniques to understand the content of conversations. Specifically, it uses morphological analysis to break down words in a conversation and grammatical analysis to analyze sentence structure. Morphological analysis breaks down each word in a conversation by part of speech, allowing for a more accurate understanding of sentence meaning. Grammatical analysis analyzes sentence structure, such as subject, predicate, and object, to understand the overall meaning of the sentence. It can also understand the meaning of conversations using semantic analysis. Semantic analysis analyzes the meaning of words and sentences based on context, grasping the intent and emotions behind the conversation. For example, if a customer says, "The product hasn't arrived," the analysis unit can understand from the context that the customer is dissatisfied. Furthermore, the analysis unit tracks the flow of the conversation and changes in topic, allowing it to grasp the overall picture of the conversation. This enables the analysis unit to analyze customer-employee conversations in detail and understand the situation in real time.

[0031] The Sentiment Analysis Department analyzes the emotions of conversations analyzed by the Analysis Department. For example, the Sentiment Analysis Department determines the tone of conversation and emotional shifts. Specifically, it uses speech analysis technology to analyze the tone of conversation and determine emotional shifts. Speech analysis technology analyzes features such as pitch, tempo, and volume of speech to estimate the speaker's emotional state. For example, if a customer's voice is high-pitched and fast, it is determined that the customer is likely angry. It is also possible to estimate emotions from the content of a conversation using text analysis technology. Text analysis technology extracts emotional expressions and keywords from the conversation to determine the type and intensity of the emotion. For example, from an expression such as "I am very dissatisfied," it can be estimated that the customer has strong dissatisfaction. Furthermore, the Sentiment Analysis Department can track changes in the emotions of conversations and grasp fluctuations in the customer's emotional state in real time. As a result, the Sentiment Analysis Department can analyze the emotions of conversations between customers and employees in detail and grasp emotional shifts in real time.

[0032] The intervention team intervenes in conversations based on the analysis results obtained by the emotion analysis team. For example, the intervention team makes neutral remarks when a customer is making a complaint unilaterally. Specifically, if a customer is talking unilaterally for a long time, the intervention team balances the conversation by making neutral remarks such as, "Sir / Madam, you've been talking unilaterally for 10 minutes. Is that a problem?" They can also make remarks to encourage customers to calm down if they are becoming emotional. For example, if a customer is clearly angry, the intervention team may say, "Sir / Madam, could you please speak calmly?" to soothe the customer's emotions. Furthermore, the intervention team can provide employees with advice on how to respond appropriately according to the customer's emotional state. In this way, the intervention team can appropriately intervene in conversations between customers and employees and support the smooth progress of the conversation.

[0033] The recording unit records data obtained by the analysis unit and the sentiment analysis unit. For example, the recording unit records conversations and stores data for later analysis. Specifically, it saves audio and text data of conversations and stores them in a database for later analysis. The audio data records the entire conversation between the customer and the employee, and the text data records a transcript of the conversation. This allows the recording unit to maintain a detailed record of conversations, which can then be used for analysis and training. Furthermore, the recording unit also records conversation metadata (e.g., date and time, participants, conversation topic, etc.), making it easier to search and filter the data. This allows the recording unit to maintain a detailed record of conversations, which can then be used for analysis and improvement.

[0034] The support department provides support to employees based on the results obtained by the emotion analysis and intervention departments. For example, if a customer is emotional, the support department will advise the employee to "remain calm." Specifically, it will display pop-up messages on the employee's screen to provide advice in real time. For example, it may display a message such as "The customer is angry. Please remain calm" to support the employee in taking an appropriate response. The support department can also monitor the employee's stress level and encourage breaks as needed. For example, if an employee is handling a situation for a long time continuously, it may display a message such as "Please take a short break" to reduce the employee's stress. Furthermore, the support department can provide employee training and feedback to support skill improvement. In this way, the support department can provide real-time advice and support to employees, reduce employee stress, and improve work efficiency.

[0035] The intervention unit can make neutral statements when a customer is making a one-sided complaint. For example, if a customer is making a one-sided complaint, the intervention unit might make a neutral statement such as, "Sir / Madam, you have been speaking unilaterally for 10 minutes. Is that a problem?" The intervention unit can also make statements to encourage a customer to calm down if they are becoming emotional. For example, the intervention unit might say, "Sir / Madam, please speak calmly." Furthermore, if a customer is becoming emotional, the intervention unit can advise the employee to "handle the situation calmly." By making neutral statements when a customer is making a one-sided complaint, the intervention unit provides an opportunity for both the customer and the employee to calm down. Some or all of the above processes in the intervention unit may be performed using AI, for example, or not using AI. For example, the intervention unit could use an AI model that generates statements based on sentiment analysis results to generate neutral statements when a customer is making a one-sided complaint.

[0036] The recording unit can record conversations and store data for later analysis. For example, the recording unit can save audio and text data of conversations and store them in a database for later analysis. For example, the recording unit can record audio data of conversations, convert it to text data, and save it. The recording unit can also directly save text data of conversations. Furthermore, the recording unit can also record conversation metadata (e.g., date and time, participant information, etc.). This allows us to understand what situations increase stress and what responses are effective by recording conversations and accumulating data for later analysis. Some or all of the above processing in the recording unit may be performed using AI, for example, or not using AI. For example, the recording unit can use an AI model that employs speech recognition technology to record audio data of conversations and convert it to text data.

[0037] The support department can advise employees to "remain calm" when a customer is emotional. For example, the support department can advise employees to "remain calm" when a customer is emotional. The support department can also advise employees to "understand the customer's feelings and respond calmly" when a customer is angry. Furthermore, the support department can advise employees to "respond in a way that reassures the customer" when a customer is anxious. By providing advice to employees when customers are emotional, employees can respond appropriately without feeling stressed. Some or all of the above processes in the support department may be performed using AI, or not. For example, the support department could use an AI model that generates advice based on sentiment analysis results to provide advice to employees when a customer is emotional.

[0038] The sentiment analysis unit can determine the tone and emotional shifts of a conversation. For example, the sentiment analysis unit can analyze the tone of a conversation using speech analysis technology to determine emotional shifts. For example, the sentiment analysis unit can analyze the pitch and intensity of a voice to determine emotional shifts. The sentiment analysis unit can also estimate emotions from the content of a conversation using text analysis technology. For example, the sentiment analysis unit can analyze keywords and phrases in the text to determine emotional shifts. Furthermore, the sentiment analysis unit can determine emotional shifts more accurately by considering the context of the conversation. This allows for an accurate understanding of the emotional shifts of customers and employees by determining the tone and emotional shifts of a conversation. Some or all of the above-described processes in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can use an AI model that employs speech analysis technology to determine the tone and emotional shifts of a conversation.

[0039] The analysis unit can understand the content of a conversation using natural language processing techniques. For example, the analysis unit can break down the words of the conversation using morphological analysis and analyze the structure of sentences using grammatical analysis. For example, the analysis unit can identify the part of speech of words using morphological analysis and analyze the structure of sentences using grammatical analysis. The analysis unit can also understand the meaning of the conversation using semantic analysis. For example, the analysis unit can analyze the meaning of sentences using semantic analysis and understand the content of the conversation. In this way, by understanding the content of a conversation using natural language processing techniques, the content of the conversation can be accurately analyzed. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can understand the content of a conversation using an AI model that employs natural language processing techniques.

[0040] The analysis unit can improve the accuracy of its analysis by referring to the customer's past complaint history when analyzing a conversation. For example, the analysis unit can refer to what kind of complaints the customer has made in the past and detect and analyze similar patterns. For example, the analysis unit can refer to the customer's past complaint history and detect and analyze similar patterns. The analysis unit can also prioritize the analysis of specific issues from the customer's past complaint history. For example, the analysis unit prioritizes the analysis of specific issues from the customer's past complaint history. Furthermore, the analysis unit can also prioritize the analysis of specific phrases and wording based on the customer's past complaint history. For example, the analysis unit prioritizes the analysis of specific phrases and wording based on the customer's past complaint history. This improves the accuracy of the analysis by referring to the customer's past complaint history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use a complaint history analysis AI model to improve the accuracy of the analysis by referring to the customer's past complaint history.

[0041] The analysis unit can perform conversation analysis while considering specific phrases and vocabulary used by the customer. For example, the analysis unit can identify phrases that the customer frequently uses and perform analysis based on those phrases. The analysis unit can also estimate emotional shifts from the customer's vocabulary and reflect them in the analysis. Furthermore, if a specific phrase of the customer acts as an emotional trigger, the analysis unit can give more emphasis to that phrase. For example, if a specific phrase of the customer acts as an emotional trigger, the analysis unit will give more emphasis to that phrase. This improves the accuracy of the analysis by considering specific phrases and vocabulary used by the customer. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use a phrase analysis AI model to perform analysis while considering specific phrases and vocabulary used by the customer.

[0042] The analysis unit can perform highly relevant analysis by considering the customer's geographic location information when analyzing conversations. For example, the analysis unit can prioritize analyzing region-specific issues based on the customer's geographic location information. The analysis unit can also analyze information related to a specific service area from the customer's geographic location information. Furthermore, the analysis unit can perform analysis to propose the optimal solution by considering the customer's geographic location information. This makes it possible to analyze region-specific issues by considering the customer's geographic location information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use a geographic information analysis AI model to perform highly relevant analysis by considering the customer's geographic location information.

[0043] The analysis unit can analyze the customer's social media activity and obtain relevant information when analyzing a conversation. For example, the analysis unit can analyze the customer's social media posts, estimate their current emotional state, and reflect this in the analysis. The analysis unit can also obtain and analyze information about specific issues from the customer's social media activity. For example, the analysis unit can obtain and analyze information about specific issues from the customer's social media activity. Furthermore, the analysis unit can prioritize the analysis of relevant topics based on the customer's social media activity. For example, the analysis unit prioritizes the analysis of relevant topics based on the customer's social media activity. This allows for the acquisition of more relevant information by analyzing the customer's social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use a social media analysis AI model to analyze the customer's social media activity and obtain relevant information.

[0044] The sentiment analysis unit can more accurately determine emotional shifts by considering the context of the conversation during sentiment analysis. For example, the sentiment analysis unit can accurately determine changes in a customer's emotions by considering the context before and after the conversation. The sentiment analysis unit can also determine emotional shifts by considering specific phrases and wording used in the conversation. For example, the sentiment analysis unit can determine emotional shifts by considering specific phrases and wording used in the conversation. Furthermore, the sentiment analysis unit can more accurately determine emotional shifts by considering the tone and pace of the conversation. For example, the sentiment analysis unit can more accurately determine emotional shifts by considering the context of the conversation. This allows for a more accurate determination of emotional shifts by considering the context of the conversation. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can use a contextual analysis AI model to more accurately determine emotional shifts by considering the context of the conversation.

[0045] The sentiment analysis unit can improve the accuracy of its analysis by referring to the customer's past emotional patterns during sentiment analysis. For example, the sentiment analysis unit can refer to the customer's past emotional patterns, detect similar patterns, and analyze them. The sentiment analysis unit can also prioritize the analysis of specific emotional shifts from the customer's past emotional patterns. For example, the sentiment analysis unit can prioritize the analysis of specific emotional shifts from the customer's past emotional patterns. Furthermore, the sentiment analysis unit can also prioritize the analysis of specific phrases or wording based on the customer's past emotional patterns. For example, the sentiment analysis unit can prioritize the analysis of specific phrases or wording based on the customer's past emotional patterns. This improves the accuracy of the analysis by referring to the customer's past emotional patterns. Some or all of the above processes in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can use an emotional pattern analysis AI model to improve the accuracy of its analysis by referring to the customer's past emotional patterns.

[0046] The sentiment analysis unit can perform sentiment analysis while considering attribute information such as the customer's age and gender. For example, the sentiment analysis unit can prioritize the analysis of specific sentiment patterns by considering the customer's age. For example, the sentiment analysis unit can prioritize the analysis of specific sentiment patterns by considering the customer's gender. For example, the sentiment analysis unit can prioritize the analysis of specific sentiment patterns by considering the customer's gender. Furthermore, the sentiment analysis unit can prioritize the analysis of specific sentiment patterns based on the customer's attribute information. For example, the sentiment analysis unit can prioritize the analysis of specific sentiment patterns based on the customer's attribute information. This improves the accuracy of sentiment analysis by considering the customer's attribute information. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can use an attribute information analysis AI model to perform analysis while considering attribute information such as the customer's age and gender.

[0047] The sentiment analysis unit can improve the accuracy of its analysis by referring to relevant customer literature during sentiment analysis. For example, the sentiment analysis unit can refer to relevant customer literature to detect and analyze specific sentiment patterns. The sentiment analysis unit can also prioritize the analysis of specific emotional shifts from relevant customer literature. Furthermore, the sentiment analysis unit can prioritize the analysis of specific phrases and wording based on relevant customer literature. This improves the accuracy of the analysis by referring to relevant customer literature. Some or all of the above processes in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can use a literature analysis AI model to improve the accuracy of its analysis by referring to relevant customer literature.

[0048] The intervention unit can select the optimal intervention method by referring to the customer's past complaint history at the time of intervention. For example, the intervention unit can refer to the customer's past complaint history and select the optimal intervention method for similar patterns. The intervention unit can also select the optimal intervention method for a specific problem from the customer's past complaint history. For example, the intervention unit can select the optimal intervention method for a specific problem from the customer's past complaint history. Furthermore, the intervention unit can select an intervention method by emphasizing specific phrases or wording based on the customer's past complaint history. For example, the intervention unit can select an intervention method by emphasizing specific phrases or wording based on the customer's past complaint history. This allows the optimal intervention method to be selected by referring to the customer's past complaint history. Some or all of the above processing in the intervention unit may be performed using AI, for example, or without AI. For example, the intervention unit can use a complaint history analysis AI model to select the optimal intervention method by referring to the customer's past complaint history.

[0049] The intervention unit can take into account specific phrases and vocabulary used by the customer when intervening. For example, the intervention unit can identify phrases that the customer frequently uses and intervene based on those phrases. The intervention unit can also estimate emotional shifts from the customer's vocabulary and reflect them in the intervention. Furthermore, if a specific phrase of the customer acts as an emotional trigger, the intervention unit can prioritize that phrase when intervening. This improves the accuracy of the intervention by taking into account specific phrases and vocabulary used by the customer. Some or all of the above processing in the intervention unit may be performed using AI, for example, or not. For example, the intervention unit can use a phrase analysis AI model to take into account specific phrases and vocabulary used by the customer when intervening.

[0050] The intervention unit can take into account the customer's geographic location information to perform highly relevant interventions. For example, the intervention unit can intervene in region-specific issues based on the customer's geographic location information. The intervention unit can also intervene based on information related to a specific service area, derived from the customer's geographic location information. Furthermore, the intervention unit can take into account the customer's geographic location information to perform interventions to propose the optimal solution. This makes it possible to intervene in region-specific issues by taking into account the customer's geographic location information. Some or all of the above processing in the intervention unit may be performed using AI, for example, or without AI. For example, the intervention unit can use a geographic information analysis AI model to perform highly relevant interventions, derived from the customer's geographic location information.

[0051] The intervention unit can analyze the customer's social media activity and make interventions based on relevant information. For example, the intervention unit can analyze the customer's social media posts, estimate their current emotional state, and reflect this in the intervention. The intervention unit can also make interventions based on information about specific issues derived from the customer's social media activity. Furthermore, the intervention unit can prioritize interventions on relevant topics based on the customer's social media activity. This allows for interventions based on more relevant information by analyzing the customer's social media activity. Some or all of the above processing in the intervention unit may be performed using AI, for example, or not. For example, the intervention unit can use a social media analysis AI model to analyze the customer's social media activity and make interventions based on relevant information.

[0052] The recording unit can prioritize recording important information by considering the context of the conversation during recording. For example, the recording unit can prioritize recording important information by considering the context before and after the conversation. The recording unit can also prioritize recording important information by considering specific phrases and wording used in the conversation. For example, the recording unit can prioritize recording important information by considering specific phrases and wording used in the conversation. Furthermore, the recording unit can prioritize recording important information by considering the tone and pace of the conversation. For example, the recording unit can prioritize recording important information by considering the tone and pace of the conversation. This allows for the priority recording of important information by considering the context of the conversation. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can use a contextual analysis AI model to prioritize recording important information by considering the context of the conversation.

[0053] The recording unit can improve the accuracy of recordings by referring to the customer's past complaint history during the recording process. For example, the recording unit can refer to the customer's past complaint history, detect similar patterns, and record them. The recording unit can also prioritize recording specific issues from the customer's past complaint history. For example, the recording unit can prioritize recording specific issues from the customer's past complaint history. Furthermore, the recording unit can prioritize recording specific phrases or wording based on the customer's past complaint history. For example, the recording unit can prioritize recording specific phrases or wording based on the customer's past complaint history. This improves the accuracy of recordings by referring to the customer's past complaint history. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can use a complaint history analysis AI model to improve the accuracy of recordings by referring to the customer's past complaint history.

[0054] The recording unit can prioritize recording highly relevant information by considering the customer's geographic location information during recording. For example, the recording unit can prioritize recording information related to region-specific issues based on the customer's geographic location information. The recording unit can also prioritize recording information related to a specific service area based on the customer's geographic location information. Furthermore, the recording unit can prioritize recording information that will help suggest the optimal solution by considering the customer's geographic location information. This allows for the priority recording of information related to region-specific issues by considering the customer's geographic location information. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can use a geographic information analysis AI model to prioritize recording highly relevant information by considering the customer's geographic location information.

[0055] The recording unit can analyze the customer's social media activity and record relevant information during recording. For example, the recording unit can analyze the customer's social media posts, estimate their current emotional state, and reflect it in the record. The recording unit can also record information about specific issues from the customer's social media activity. For example, the recording unit can record information about specific issues from the customer's social media activity. Furthermore, the recording unit can prioritize recording relevant topics based on the customer's social media activity. For example, the recording unit prioritizes recording relevant topics based on the customer's social media activity. This allows for the recording of more relevant information by analyzing the customer's social media activity. Some or all of the above processing in the recording unit may be performed using AI, for example, or not using AI. For example, the recording unit can use a social media analysis AI model to analyze the customer's social media activity and record relevant information.

[0056] The support department can select the optimal support method by referring to the employee's past interaction history when providing support. For example, the support department can refer to the employee's past interaction history and select the optimal support method for similar patterns. The support department can also select the optimal support method for a specific problem based on the employee's past interaction history. For example, the support department can select the optimal support method for a specific problem based on the employee's past interaction history. Furthermore, the support department can select a support method by emphasizing specific phrases or wording based on the employee's past interaction history. For example, the support department can select a support method by emphasizing specific phrases or wording based on the employee's past interaction history. This allows the support department to select the optimal support method by referring to the employee's past interaction history. Some or all of the above processes in the support department may be performed using AI, for example, or not. For example, the support department can use an interaction history analysis AI model to select the optimal support method by referring to the employee's past interaction history.

[0057] The support department can customize the means of support when providing assistance, taking into account the employee's current situation. For example, if the employee is tired, the support department can provide concise and effective support. For example, if the employee is tired, the support department can provide concise and effective support. The support department can also provide relaxing support if the employee is stressed. For example, if the support department is stressed, the support department can provide relaxing support. Furthermore, if the employee is busy, the support department can provide support that can be responded to quickly. For example, if the support department is busy, the support department can provide support that can be responded to quickly. This allows for the provision of more appropriate support by taking into account the employee's current situation. Some or all of the above processes in the support department may be performed using AI, for example, or not using AI. For example, the support department can use a situational analysis AI model to customize the means of support by taking into account the employee's current situation.

[0058] The support department can select the optimal support method by considering the geographical location of employees when providing support. For example, the support department can provide support for region-specific issues based on the geographical location of employees. For example, the support department can provide support for region-specific issues based on the geographical location of employees. The support department can also provide support based on information related to a specific service area based on the geographical location of employees. For example, the support department can provide support based on information related to a specific service area based on the geographical location of employees. Furthermore, the support department can provide support to propose the optimal solution by considering the geographical location of employees. For example, the support department can provide support to propose the optimal solution by considering the geographical location of employees. This makes it possible to provide support for region-specific issues by considering the geographical location of employees. Some or all of the above processing in the support department may be performed using AI, for example, or not using AI. For example, the support department can use a geographic information analysis AI model to select the optimal support method by considering the geographical location of employees.

[0059] The support department can analyze an employee's social media activity and propose support measures when providing assistance. For example, the support department can analyze an employee's social media posts, estimate their current emotional state, and reflect this in the support. The support department can also provide support based on information about specific issues derived from an employee's social media activity. Furthermore, the support department can prioritize support on relevant topics based on an employee's social media activity. This allows the support department to provide support based on more relevant information by analyzing an employee's social media activity. Some or all of the above processes in the support department may be performed using AI, for example, or not. For example, the support department can use a social media analysis AI model to analyze an employee's social media activity and propose support measures.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The customer center employee stress reduction system can be enhanced with features to optimize employee work schedules to reduce employee stress. For example, it can analyze an employee's past work history and stress levels to suggest optimal working hours and break times. It can adjust schedules to include appropriate breaks to avoid employees working long hours continuously. Furthermore, if an employee's stress level is high, the system can suggest taking an earlier break. It can also coordinate employee work schedules with other employees to distribute stress evenly across the entire team. By optimizing employee work schedules, it can reduce stress and provide a more comfortable working environment.

[0062] A customer service employee stress reduction system can be enhanced with features to evaluate employee performance and provide feedback to reduce employee stress. For example, it can evaluate employee response time and customer satisfaction, and provide positive feedback to employees who demonstrate excellent performance. When an employee performs well, the system can display a message such as "That was a great response." It can also provide specific advice if improvement is needed, such as "Please explain things more clearly next time." Furthermore, by recording employee performance data over the long term and visualizing the process of growth, motivation can be improved. In this way, by evaluating employee performance and providing appropriate feedback, stress can be reduced and job satisfaction can be improved.

[0063] The customer center employee stress reduction system can be enhanced with features to monitor employee health and support health management in order to reduce employee stress. For example, it can record employees' meals and exercise to promote healthy lifestyle habits. It can also provide advice to employees on eating balanced meals. Furthermore, it can record exercise to encourage regular exercise and support goal achievement. In addition, it can monitor employees' sleep patterns and provide advice on getting enough rest. By monitoring employees' health and supporting their health management, it is possible to reduce stress and provide a more comfortable working environment.

[0064] The customer center employee stress reduction system can add features to support employee skill development in order to reduce employee stress. For example, it can provide online training programs for employees to acquire new skills. By receiving training on specific skills, employees can work with confidence. It can also assess employees' skill levels and suggest the most suitable training programs for each individual employee. Furthermore, it can provide regular feedback so that employees can feel the results of their skill development. In this way, by supporting employee skill development, stress can be reduced and job satisfaction can be improved.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The analysis unit analyzes the conversation between the customer and the employee in real time. The analysis unit uses natural language processing technology to understand the content of the conversation and performs morphological analysis, grammatical analysis, and semantic analysis. Step 2: The emotion analysis unit analyzes the emotions of the conversation analyzed by the analysis unit. The emotion analysis unit uses speech analysis technology and text analysis technology to determine the tone and emotional shifts of the conversation. Step 3: The intervention team intervenes in the conversation based on the analysis results obtained by the emotion analysis team. The intervention team makes neutral statements when the customer is making a one-sided complaint and makes statements to encourage the customer to calm down when they are becoming emotional. Step 4: The recording unit records the data obtained by the analysis unit and the sentiment analysis unit. The recording unit saves the audio and text data of the conversation and stores it in a database for later analysis. Step 5: The support department provides support to employees based on the results obtained by the emotion analysis department and the intervention department. The support department provides real-time advice to employees and provides support to help them take appropriate action.

[0067] (Example of form 2) The Customer Center Employee Stress Reduction System according to an embodiment of the present invention is a system for reducing stress among employees working in a customer center and lowering employee turnover. This system utilizes natural language processing (NLP) and sentiment analysis technology, with AI analyzing conversations from a neutral standpoint and intervening in conversations as needed to reduce stress for both customers and employees. For example, the Customer Center Employee Stress Reduction System uses AI to analyze conversations between customers and employees in real time. The AI ​​uses natural language processing technology to understand the content of the conversation and sentiment analysis technology to determine the tone and emotional shifts of the conversation. For example, if a customer is making a complaint unilaterally, the AI ​​detects this situation and makes a neutral statement such as, "Sir / Madam, you have been speaking unilaterally for 10 minutes. Is that a problem?" In this way, the AI ​​intervenes in the conversation from a third-party perspective, providing an opportunity for both the customer and the employee to calm down. Next, the AI ​​records the conversation and accumulates data for later analysis. This makes it possible to understand what situations increase stress and what responses are effective. For example, if certain phrases or tones amplify a customer's anger, this information can be used to improve the employee's response methods. Furthermore, the AI ​​provides real-time support to employees. For example, if a customer is emotional, the AI ​​will advise the employee to "remain calm." This allows employees to respond appropriately without feeling stressed. This system reduces stress for employees working in customer centers and lowers employee turnover. In addition, neutral responses to customers improve customer satisfaction. For example, even if a customer is making a one-sided complaint, the AI's neutral comments can help the customer calm down, enabling a constructive conversation toward problem resolution. Thus, an AI system utilizing natural language processing and sentiment analysis technology has the effect of reducing employee stress in customer centers, lowering employee turnover, and improving customer satisfaction. In summary, a customer center employee stress reduction system can reduce employee stress and lower employee turnover.

[0068] The customer center employee stress reduction system according to this embodiment comprises an analysis unit, an emotion analysis unit, an intervention unit, a recording unit, and a support unit. The analysis unit analyzes conversations between customers and employees in real time. The analysis unit understands the content of conversations using, for example, natural language processing technology. For example, the analysis unit breaks down words in conversations using morphological analysis and analyzes sentence structure using grammatical analysis. The analysis unit can also understand the meaning of conversations using semantic analysis. The emotion analysis unit analyzes the emotions of conversations analyzed by the analysis unit. The emotion analysis unit determines, for example, the tone of conversation and emotional shifts. For example, the emotion analysis unit analyzes the tone of conversation and determines emotional shifts using speech analysis technology. The emotion analysis unit can also estimate emotions from the content of conversations using text analysis technology. The intervention unit intervenes in conversations based on the analysis results obtained by the emotion analysis unit. For example, the intervention unit makes neutral statements when a customer is making unilateral complaints. For example, the intervention unit makes neutral statements such as, "Sir / Madam, you have been speaking unilaterally for 10 minutes. Is that a problem?" The intervention unit can also make statements encouraging the customer to calm down if they are becoming emotional. The recording unit records the data obtained by the analysis unit and the sentiment analysis unit. The recording unit, for example, records conversations and stores the data for later analysis. For example, the recording unit saves the audio and text data of conversations and stores it in a database for later analysis. The support unit provides support to employees based on the results obtained by the sentiment analysis unit and the intervention unit. For example, the support unit advises employees to "remain calm" if the customer is becoming emotional. For example, the support unit provides real-time advice to employees and provides support to take appropriate action. As a result, the customer center employee stress reduction system according to this embodiment can reduce employee stress and lower the turnover rate. Some or all of the above-described processes in the analysis unit, sentiment analysis unit, intervention unit, recording unit, and support unit may be performed using AI, for example, or not using AI.For example, the analysis unit can use an AI model employing natural language processing technology to analyze customer-employee conversations in real time. The sentiment analysis unit can use an AI model employing speech analysis technology to determine the tone and emotional shifts in conversations. The intervention unit can use an AI model that generates statements based on sentiment analysis results to intervene in conversations. The recording unit can use a database management system to record conversations and accumulate data. The support unit can use an advice generation AI model to provide real-time advice to employees.

[0069] The analysis unit analyzes customer-employee conversations in real time. For example, it uses natural language processing techniques to understand the content of conversations. Specifically, it uses morphological analysis to break down words in a conversation and grammatical analysis to analyze sentence structure. Morphological analysis breaks down each word in a conversation by part of speech, allowing for a more accurate understanding of sentence meaning. Grammatical analysis analyzes sentence structure, such as subject, predicate, and object, to understand the overall meaning of the sentence. It can also understand the meaning of conversations using semantic analysis. Semantic analysis analyzes the meaning of words and sentences based on context, grasping the intent and emotions behind the conversation. For example, if a customer says, "The product hasn't arrived," the analysis unit can understand from the context that the customer is dissatisfied. Furthermore, the analysis unit tracks the flow of the conversation and changes in topic, allowing it to grasp the overall picture of the conversation. This enables the analysis unit to analyze customer-employee conversations in detail and understand the situation in real time.

[0070] The Sentiment Analysis Department analyzes the emotions of conversations analyzed by the Analysis Department. For example, the Sentiment Analysis Department determines the tone of conversation and emotional shifts. Specifically, it uses speech analysis technology to analyze the tone of conversation and determine emotional shifts. Speech analysis technology analyzes features such as pitch, tempo, and volume of speech to estimate the speaker's emotional state. For example, if a customer's voice is high-pitched and fast, it is determined that the customer is likely angry. It is also possible to estimate emotions from the content of a conversation using text analysis technology. Text analysis technology extracts emotional expressions and keywords from the conversation to determine the type and intensity of the emotion. For example, from an expression such as "I am very dissatisfied," it can be estimated that the customer has strong dissatisfaction. Furthermore, the Sentiment Analysis Department can track changes in the emotions of conversations and grasp fluctuations in the customer's emotional state in real time. As a result, the Sentiment Analysis Department can analyze the emotions of conversations between customers and employees in detail and grasp emotional shifts in real time.

[0071] The intervention team intervenes in conversations based on the analysis results obtained by the emotion analysis team. For example, the intervention team makes neutral remarks when a customer is making a complaint unilaterally. Specifically, if a customer is talking unilaterally for a long time, the intervention team balances the conversation by making neutral remarks such as, "Sir / Madam, you've been talking unilaterally for 10 minutes. Is that a problem?" They can also make remarks to encourage customers to calm down if they are becoming emotional. For example, if a customer is clearly angry, the intervention team may say, "Sir / Madam, could you please speak calmly?" to soothe the customer's emotions. Furthermore, the intervention team can provide employees with advice on how to respond appropriately according to the customer's emotional state. In this way, the intervention team can appropriately intervene in conversations between customers and employees and support the smooth progress of the conversation.

[0072] The recording unit records data obtained by the analysis unit and the sentiment analysis unit. For example, the recording unit records conversations and stores data for later analysis. Specifically, it saves audio and text data of conversations and stores them in a database for later analysis. The audio data records the entire conversation between the customer and the employee, and the text data records a transcript of the conversation. This allows the recording unit to maintain a detailed record of conversations, which can then be used for analysis and training. Furthermore, the recording unit also records conversation metadata (e.g., date and time, participants, conversation topic, etc.), making it easier to search and filter the data. This allows the recording unit to maintain a detailed record of conversations, which can then be used for analysis and improvement.

[0073] The support department provides support to employees based on the results obtained by the emotion analysis and intervention departments. For example, if a customer is emotional, the support department will advise the employee to "remain calm." Specifically, it will display pop-up messages on the employee's screen to provide advice in real time. For example, it may display a message such as "The customer is angry. Please remain calm" to support the employee in taking an appropriate response. The support department can also monitor the employee's stress level and encourage breaks as needed. For example, if an employee is handling a situation for a long time continuously, it may display a message such as "Please take a short break" to reduce the employee's stress. Furthermore, the support department can provide employee training and feedback to support skill improvement. In this way, the support department can provide real-time advice and support to employees, reduce employee stress, and improve work efficiency.

[0074] The intervention unit can make neutral statements when a customer is making a one-sided complaint. For example, if a customer is making a one-sided complaint, the intervention unit might make a neutral statement such as, "Sir / Madam, you have been speaking unilaterally for 10 minutes. Is that a problem?" The intervention unit can also make statements to encourage a customer to calm down if they are becoming emotional. For example, the intervention unit might say, "Sir / Madam, please speak calmly." Furthermore, if a customer is becoming emotional, the intervention unit can advise the employee to "handle the situation calmly." By making neutral statements when a customer is making a one-sided complaint, the intervention unit provides an opportunity for both the customer and the employee to calm down. Some or all of the above processes in the intervention unit may be performed using AI, for example, or not using AI. For example, the intervention unit could use an AI model that generates statements based on sentiment analysis results to generate neutral statements when a customer is making a one-sided complaint.

[0075] The recording unit can record conversations and store data for later analysis. For example, the recording unit can save audio and text data of conversations and store them in a database for later analysis. For example, the recording unit can record audio data of conversations, convert it to text data, and save it. The recording unit can also directly save text data of conversations. Furthermore, the recording unit can also record conversation metadata (e.g., date and time, participant information, etc.). This allows us to understand what situations increase stress and what responses are effective by recording conversations and accumulating data for later analysis. Some or all of the above processing in the recording unit may be performed using AI, for example, or not using AI. For example, the recording unit can use an AI model that employs speech recognition technology to record audio data of conversations and convert it to text data.

[0076] The support department can advise employees to "remain calm" when a customer is emotional. For example, the support department can advise employees to "remain calm" when a customer is emotional. The support department can also advise employees to "understand the customer's feelings and respond calmly" when a customer is angry. Furthermore, the support department can advise employees to "respond in a way that reassures the customer" when a customer is anxious. By providing advice to employees when customers are emotional, employees can respond appropriately without feeling stressed. Some or all of the above processes in the support department may be performed using AI, or not. For example, the support department could use an AI model that generates advice based on sentiment analysis results to provide advice to employees when a customer is emotional.

[0077] The sentiment analysis unit can determine the tone and emotional shifts of a conversation. For example, the sentiment analysis unit can analyze the tone of a conversation using speech analysis technology to determine emotional shifts. For example, the sentiment analysis unit can analyze the pitch and intensity of a voice to determine emotional shifts. The sentiment analysis unit can also estimate emotions from the content of a conversation using text analysis technology. For example, the sentiment analysis unit can analyze keywords and phrases in the text to determine emotional shifts. Furthermore, the sentiment analysis unit can determine emotional shifts more accurately by considering the context of the conversation. This allows for an accurate understanding of the emotional shifts of customers and employees by determining the tone and emotional shifts of a conversation. Some or all of the above-described processes in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can use an AI model that employs speech analysis technology to determine the tone and emotional shifts of a conversation.

[0078] The analysis unit can understand the content of a conversation using natural language processing techniques. For example, the analysis unit can break down the words of the conversation using morphological analysis and analyze the structure of sentences using grammatical analysis. For example, the analysis unit can identify the part of speech of words using morphological analysis and analyze the structure of sentences using grammatical analysis. The analysis unit can also understand the meaning of the conversation using semantic analysis. For example, the analysis unit can analyze the meaning of sentences using semantic analysis and understand the content of the conversation. In this way, by understanding the content of a conversation using natural language processing techniques, the content of the conversation can be accurately analyzed. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can understand the content of a conversation using an AI model that employs natural language processing techniques.

[0079] The analysis unit can estimate the customer's emotions and adjust the conversation analysis method based on the estimated emotions. For example, if the customer is angry, the analysis unit will prioritize calm language in order to calm the tone of the conversation. The analysis unit can also prioritize positive phrases in order to reassure the customer if they are feeling anxious. Furthermore, if the customer is agitated, the analysis unit can perform a slower analysis to slow down the pace of the conversation. By adjusting the conversation analysis method based on the customer's emotions, a more appropriate analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not. For example, the analysis unit can use an emotion estimation AI model to estimate the customer's emotions and adjust the conversation analysis method based on the estimated emotions.

[0080] The analysis unit can improve the accuracy of its analysis by referring to the customer's past complaint history when analyzing a conversation. For example, the analysis unit can refer to what kind of complaints the customer has made in the past and detect and analyze similar patterns. For example, the analysis unit can refer to the customer's past complaint history and detect and analyze similar patterns. The analysis unit can also prioritize the analysis of specific issues from the customer's past complaint history. For example, the analysis unit prioritizes the analysis of specific issues from the customer's past complaint history. Furthermore, the analysis unit can also prioritize the analysis of specific phrases and wording based on the customer's past complaint history. For example, the analysis unit prioritizes the analysis of specific phrases and wording based on the customer's past complaint history. This improves the accuracy of the analysis by referring to the customer's past complaint history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use a complaint history analysis AI model to improve the accuracy of the analysis by referring to the customer's past complaint history.

[0081] The analysis unit can perform conversation analysis while considering specific phrases and vocabulary used by the customer. For example, the analysis unit can identify phrases that the customer frequently uses and perform analysis based on those phrases. The analysis unit can also estimate emotional shifts from the customer's vocabulary and reflect them in the analysis. Furthermore, if a specific phrase of the customer acts as an emotional trigger, the analysis unit can give more emphasis to that phrase. For example, if a specific phrase of the customer acts as an emotional trigger, the analysis unit will give more emphasis to that phrase. This improves the accuracy of the analysis by considering specific phrases and vocabulary used by the customer. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use a phrase analysis AI model to perform analysis while considering specific phrases and vocabulary used by the customer.

[0082] The analysis unit can estimate the customer's emotions and prioritize the analysis results based on the estimated emotions. For example, if the customer is angry, the analysis unit will prioritize analyzing urgent issues. The analysis unit can also prioritize analyzing information that will provide reassurance if the customer is feeling anxious. Furthermore, if the customer is agitated, the analysis unit can prioritize analyzing information that will help them regain their composure. By prioritizing the analysis results based on the customer's emotions, more important information can be prioritized. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use an emotion estimation AI model to estimate the customer's emotions and prioritize the analysis results based on the estimated emotions.

[0083] The analysis unit can perform highly relevant analysis by considering the customer's geographic location information when analyzing conversations. For example, the analysis unit can prioritize analyzing region-specific issues based on the customer's geographic location information. The analysis unit can also analyze information related to a specific service area from the customer's geographic location information. Furthermore, the analysis unit can perform analysis to propose the optimal solution by considering the customer's geographic location information. This makes it possible to analyze region-specific issues by considering the customer's geographic location information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use a geographic information analysis AI model to perform highly relevant analysis by considering the customer's geographic location information.

[0084] The analysis unit can analyze the customer's social media activity and obtain relevant information when analyzing a conversation. For example, the analysis unit can analyze the customer's social media posts, estimate their current emotional state, and reflect this in the analysis. The analysis unit can also obtain and analyze information about specific issues from the customer's social media activity. For example, the analysis unit can obtain and analyze information about specific issues from the customer's social media activity. Furthermore, the analysis unit can prioritize the analysis of relevant topics based on the customer's social media activity. For example, the analysis unit prioritizes the analysis of relevant topics based on the customer's social media activity. This allows for the acquisition of more relevant information by analyzing the customer's social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can use a social media analysis AI model to analyze the customer's social media activity and obtain relevant information.

[0085] The emotion analysis unit can estimate the customer's emotions and adjust the emotion analysis algorithm based on the estimated emotions. For example, if the customer is angry, the emotion analysis unit can adjust the emotion analysis algorithm to accurately determine the degree of anger. The emotion analysis unit can also adjust the emotion analysis algorithm to accurately determine the degree of anxiety if the customer is feeling anxious. Furthermore, if the customer is excited, the emotion analysis unit can adjust the emotion analysis algorithm to accurately determine the degree of excitement. In this way, the accuracy of emotion analysis is improved by adjusting the emotion analysis algorithm based on the customer's emotions. Some or all of the above processing in the emotion analysis unit may be performed using AI, for example, or without using AI. For example, the sentiment analysis department can use an emotion estimation AI model to estimate customer emotions and adjust the sentiment analysis algorithm based on the estimated customer emotions.

[0086] The sentiment analysis unit can more accurately determine emotional shifts by considering the context of the conversation during sentiment analysis. For example, the sentiment analysis unit can accurately determine changes in a customer's emotions by considering the context before and after the conversation. The sentiment analysis unit can also determine emotional shifts by considering specific phrases and wording used in the conversation. For example, the sentiment analysis unit can determine emotional shifts by considering specific phrases and wording used in the conversation. Furthermore, the sentiment analysis unit can more accurately determine emotional shifts by considering the tone and pace of the conversation. For example, the sentiment analysis unit can more accurately determine emotional shifts by considering the context of the conversation. This allows for a more accurate determination of emotional shifts by considering the context of the conversation. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can use a contextual analysis AI model to more accurately determine emotional shifts by considering the context of the conversation.

[0087] The sentiment analysis unit can improve the accuracy of its analysis by referring to the customer's past emotional patterns during sentiment analysis. For example, the sentiment analysis unit can refer to the customer's past emotional patterns, detect similar patterns, and analyze them. The sentiment analysis unit can also prioritize the analysis of specific emotional shifts from the customer's past emotional patterns. For example, the sentiment analysis unit can prioritize the analysis of specific emotional shifts from the customer's past emotional patterns. Furthermore, the sentiment analysis unit can also prioritize the analysis of specific phrases or wording based on the customer's past emotional patterns. For example, the sentiment analysis unit can prioritize the analysis of specific phrases or wording based on the customer's past emotional patterns. This improves the accuracy of the analysis by referring to the customer's past emotional patterns. Some or all of the above processes in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can use an emotional pattern analysis AI model to improve the accuracy of its analysis by referring to the customer's past emotional patterns.

[0088] The emotion analysis unit can estimate the customer's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the customer is angry, the emotion analysis unit can prioritize displaying information that helps the customer regain their composure. Similarly, if the customer is feeling anxious, the emotion analysis unit can prioritize displaying information that provides reassurance. Furthermore, if the customer is agitated, the emotion analysis unit can prioritize displaying information that helps the customer regain their composure. This allows for the provision of more appropriate information by adjusting how the analysis results are displayed based on the customer's emotions. Some or all of the above processing in the emotion analysis unit may be performed using AI, for example, or without AI. For example, the emotion analysis unit can use an emotion estimation AI model to estimate the customer's emotions and adjust how the analysis results are displayed based on the estimated emotions.

[0089] The sentiment analysis unit can perform sentiment analysis while considering attribute information such as the customer's age and gender. For example, the sentiment analysis unit can prioritize the analysis of specific sentiment patterns by considering the customer's age. For example, the sentiment analysis unit can prioritize the analysis of specific sentiment patterns by considering the customer's gender. For example, the sentiment analysis unit can prioritize the analysis of specific sentiment patterns by considering the customer's gender. Furthermore, the sentiment analysis unit can prioritize the analysis of specific sentiment patterns based on the customer's attribute information. For example, the sentiment analysis unit can prioritize the analysis of specific sentiment patterns based on the customer's attribute information. This improves the accuracy of sentiment analysis by considering the customer's attribute information. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can use an attribute information analysis AI model to perform analysis while considering attribute information such as the customer's age and gender.

[0090] The sentiment analysis unit can improve the accuracy of its analysis by referring to relevant customer literature during sentiment analysis. For example, the sentiment analysis unit can refer to relevant customer literature to detect and analyze specific sentiment patterns. The sentiment analysis unit can also prioritize the analysis of specific emotional shifts from relevant customer literature. Furthermore, the sentiment analysis unit can prioritize the analysis of specific phrases and wording based on relevant customer literature. This improves the accuracy of the analysis by referring to relevant customer literature. Some or all of the above processes in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can use a literature analysis AI model to improve the accuracy of its analysis by referring to relevant customer literature.

[0091] The intervention unit can estimate the customer's emotions and adjust the timing of the intervention based on the estimated emotions. For example, if the customer is angry, the intervention unit can intervene early to help them calm down. For example, if the customer is angry, the intervention unit can intervene early to help them calm down. For example, if the customer is feeling anxious, the intervention unit can intervene early to help them feel reassured. For example, if the customer is feeling anxious, the intervention unit can intervene early to help them calm down. Furthermore, if the customer is agitated, the intervention unit can intervene early to help them calm down. For example, if the customer is agitated, the intervention unit can intervene early to help them calm down. This allows for intervention at a more appropriate time by adjusting the timing of the intervention based on the customer's emotions. Some or all of the above processing in the intervention unit may be performed using AI, for example, or not using AI. For example, the intervention unit can use an emotion estimation AI model to estimate the customer's emotions and adjust the timing of the intervention based on the estimated emotions.

[0092] The intervention unit can select the optimal intervention method by referring to the customer's past complaint history at the time of intervention. For example, the intervention unit can refer to the customer's past complaint history and select the optimal intervention method for similar patterns. The intervention unit can also select the optimal intervention method for a specific problem from the customer's past complaint history. For example, the intervention unit can select the optimal intervention method for a specific problem from the customer's past complaint history. Furthermore, the intervention unit can select an intervention method by emphasizing specific phrases or wording based on the customer's past complaint history. For example, the intervention unit can select an intervention method by emphasizing specific phrases or wording based on the customer's past complaint history. This allows the optimal intervention method to be selected by referring to the customer's past complaint history. Some or all of the above processing in the intervention unit may be performed using AI, for example, or without AI. For example, the intervention unit can use a complaint history analysis AI model to select the optimal intervention method by referring to the customer's past complaint history.

[0093] The intervention unit can take into account specific phrases and vocabulary used by the customer when intervening. For example, the intervention unit can identify phrases that the customer frequently uses and intervene based on those phrases. The intervention unit can also estimate emotional shifts from the customer's vocabulary and reflect them in the intervention. Furthermore, if a specific phrase of the customer acts as an emotional trigger, the intervention unit can prioritize that phrase when intervening. This improves the accuracy of the intervention by taking into account specific phrases and vocabulary used by the customer. Some or all of the above processing in the intervention unit may be performed using AI, for example, or not. For example, the intervention unit can use a phrase analysis AI model to take into account specific phrases and vocabulary used by the customer when intervening.

[0094] The intervention unit can estimate the customer's emotions and adjust the content of the intervention based on the estimated emotions. For example, if the customer is angry, the intervention unit will prioritize interventions that help the customer regain their composure. The intervention unit can also prioritize interventions that provide reassurance if the customer is feeling anxious. Furthermore, if the customer is agitated, the intervention unit can prioritize interventions that help the customer regain their composure. By adjusting the content of the intervention based on the customer's emotions, the intervention can be more appropriate. Some or all of the above processing in the intervention unit may be performed using AI, for example, or not. For example, the intervention unit can use an emotion estimation AI model to estimate the customer's emotions and adjust the content of the intervention based on the estimated emotions.

[0095] The intervention unit can take into account the customer's geographic location information to perform highly relevant interventions. For example, the intervention unit can intervene in region-specific issues based on the customer's geographic location information. The intervention unit can also intervene based on information related to a specific service area, derived from the customer's geographic location information. Furthermore, the intervention unit can take into account the customer's geographic location information to perform interventions to propose the optimal solution. This makes it possible to intervene in region-specific issues by taking into account the customer's geographic location information. Some or all of the above processing in the intervention unit may be performed using AI, for example, or without AI. For example, the intervention unit can use a geographic information analysis AI model to perform highly relevant interventions, derived from the customer's geographic location information.

[0096] The intervention unit can analyze the customer's social media activity and make interventions based on relevant information. For example, the intervention unit can analyze the customer's social media posts, estimate their current emotional state, and reflect this in the intervention. The intervention unit can also make interventions based on information about specific issues derived from the customer's social media activity. Furthermore, the intervention unit can prioritize interventions on relevant topics based on the customer's social media activity. This allows for interventions based on more relevant information by analyzing the customer's social media activity. Some or all of the above processing in the intervention unit may be performed using AI, for example, or not. For example, the intervention unit can use a social media analysis AI model to analyze the customer's social media activity and make interventions based on relevant information.

[0097] The recording unit can estimate the customer's emotions and adjust the recording method based on the estimated emotions. For example, if the customer is angry, the recording unit will prioritize recording information that will help them regain their composure. The recording unit can also prioritize recording information that will provide reassurance if the customer is feeling anxious. Furthermore, if the customer is agitated, the recording unit can prioritize recording information that will help them regain their composure. By adjusting the recording method based on the customer's emotions, more appropriate information can be recorded. Some or all of the above processing in the recording unit may be performed using AI, for example, or not. For example, the recording unit can use an emotion estimation AI model to estimate the customer's emotions and adjust the recording method based on the estimated emotions.

[0098] The recording unit can prioritize recording important information by considering the context of the conversation during recording. For example, the recording unit can prioritize recording important information by considering the context before and after the conversation. The recording unit can also prioritize recording important information by considering specific phrases and wording used in the conversation. For example, the recording unit can prioritize recording important information by considering specific phrases and wording used in the conversation. Furthermore, the recording unit can prioritize recording important information by considering the tone and pace of the conversation. For example, the recording unit can prioritize recording important information by considering the tone and pace of the conversation. This allows for the priority recording of important information by considering the context of the conversation. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can use a contextual analysis AI model to prioritize recording important information by considering the context of the conversation.

[0099] The recording unit can improve the accuracy of recordings by referring to the customer's past complaint history during the recording process. For example, the recording unit can refer to the customer's past complaint history, detect similar patterns, and record them. The recording unit can also prioritize recording specific issues from the customer's past complaint history. For example, the recording unit can prioritize recording specific issues from the customer's past complaint history. Furthermore, the recording unit can prioritize recording specific phrases or wording based on the customer's past complaint history. For example, the recording unit can prioritize recording specific phrases or wording based on the customer's past complaint history. This improves the accuracy of recordings by referring to the customer's past complaint history. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can use a complaint history analysis AI model to improve the accuracy of recordings by referring to the customer's past complaint history.

[0100] The recording unit can estimate the customer's emotions and determine the priority of recordings based on the estimated emotions. For example, if the customer is angry, the recording unit will prioritize recording urgent issues. For example, if the customer is anxious, the recording unit will prioritize recording information that will provide reassurance. For example, if the customer is anxious, the recording unit will prioritize recording information that will provide reassurance. For example, if the customer is agitated, the recording unit will prioritize recording information that will help the customer regain composure. For example, if the customer is agitated, the recording unit will prioritize recording information that will help the customer regain composure. In this way, by determining the priority of recordings based on the customer's emotions, more important information can be prioritized. Some or all of the above processing in the recording unit may be performed using AI, for example, or not using AI. For example, the recording unit can use an emotion estimation AI model to estimate the customer's emotions and determine the priority of recordings based on the estimated emotions.

[0101] The recording unit can prioritize recording highly relevant information by considering the customer's geographic location information during recording. For example, the recording unit can prioritize recording information related to region-specific issues based on the customer's geographic location information. The recording unit can also prioritize recording information related to a specific service area based on the customer's geographic location information. Furthermore, the recording unit can prioritize recording information that will help suggest the optimal solution by considering the customer's geographic location information. This allows for the priority recording of information related to region-specific issues by considering the customer's geographic location information. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can use a geographic information analysis AI model to prioritize recording highly relevant information by considering the customer's geographic location information.

[0102] The recording unit can analyze the customer's social media activity and record relevant information during recording. For example, the recording unit can analyze the customer's social media posts, estimate their current emotional state, and reflect it in the record. The recording unit can also record information about specific issues from the customer's social media activity. For example, the recording unit can record information about specific issues from the customer's social media activity. Furthermore, the recording unit can prioritize recording relevant topics based on the customer's social media activity. For example, the recording unit prioritizes recording relevant topics based on the customer's social media activity. This allows for the recording of more relevant information by analyzing the customer's social media activity. Some or all of the above processing in the recording unit may be performed using AI, for example, or not using AI. For example, the recording unit can use a social media analysis AI model to analyze the customer's social media activity and record relevant information.

[0103] The support department can estimate the customer's emotions and adjust the support content based on the estimated emotions. For example, if the customer is angry, the support department can prioritize providing support to help the customer regain their composure. The support department can also prioritize providing support to reassure the customer if they are feeling anxious. The support department can also prioritize providing support to reassure the customer if they are feeling agitated. In addition, the support department can prioritize providing support to help the customer regain their composure if they are agitated. By adjusting the support content based on the customer's emotions, more appropriate support can be provided. Some or all of the above processing in the support department may be performed using AI, for example, or not. For example, the support department can use an emotion estimation AI model to estimate the customer's emotions and adjust the support content based on the estimated emotions.

[0104] The support department can select the optimal support method by referring to the employee's past interaction history when providing support. For example, the support department can refer to the employee's past interaction history and select the optimal support method for similar patterns. The support department can also select the optimal support method for a specific problem based on the employee's past interaction history. For example, the support department can select the optimal support method for a specific problem based on the employee's past interaction history. Furthermore, the support department can select a support method by emphasizing specific phrases or wording based on the employee's past interaction history. For example, the support department can select a support method by emphasizing specific phrases or wording based on the employee's past interaction history. This allows the support department to select the optimal support method by referring to the employee's past interaction history. Some or all of the above processes in the support department may be performed using AI, for example, or not. For example, the support department can use an interaction history analysis AI model to select the optimal support method by referring to the employee's past interaction history.

[0105] The support department can customize the means of support when providing assistance, taking into account the employee's current situation. For example, if the employee is tired, the support department can provide concise and effective support. For example, if the employee is tired, the support department can provide concise and effective support. The support department can also provide relaxing support if the employee is stressed. For example, if the support department is stressed, the support department can provide relaxing support. Furthermore, if the employee is busy, the support department can provide support that can be responded to quickly. For example, if the support department is busy, the support department can provide support that can be responded to quickly. This allows for the provision of more appropriate support by taking into account the employee's current situation. Some or all of the above processes in the support department may be performed using AI, for example, or not using AI. For example, the support department can use a situational analysis AI model to customize the means of support by taking into account the employee's current situation.

[0106] The support department can estimate the customer's emotions and prioritize support based on those emotions. For example, if the customer is angry, the support department can prioritize providing urgent support. For example, if the customer is anxious, the support department can prioritize providing reassuring support. For example, if the customer is anxious, the support department can prioritize providing reassuring support. Furthermore, if the customer is agitated, the support department can prioritize providing support to help them regain their composure. For example, if the customer is agitated, the support department can prioritize providing support to help them regain their composure. This allows for prioritizing support based on the customer's emotions, thereby prioritizing the most important support. Some or all of the above processes in the support department may be performed using AI, for example, or not. For example, the support department can use an emotion estimation AI model to estimate the customer's emotions and prioritize support based on those estimated emotions.

[0107] The support department can select the optimal support method by considering the geographical location of employees when providing support. For example, the support department can provide support for region-specific issues based on the geographical location of employees. For example, the support department can provide support for region-specific issues based on the geographical location of employees. The support department can also provide support based on information related to a specific service area based on the geographical location of employees. For example, the support department can provide support based on information related to a specific service area based on the geographical location of employees. Furthermore, the support department can provide support to propose the optimal solution by considering the geographical location of employees. For example, the support department can provide support to propose the optimal solution by considering the geographical location of employees. This makes it possible to provide support for region-specific issues by considering the geographical location of employees. Some or all of the above processing in the support department may be performed using AI, for example, or not using AI. For example, the support department can use a geographic information analysis AI model to select the optimal support method by considering the geographical location of employees.

[0108] The support department can analyze an employee's social media activity and propose support measures when providing assistance. For example, the support department can analyze an employee's social media posts, estimate their current emotional state, and reflect this in the support. The support department can also provide support based on information about specific issues derived from an employee's social media activity. Furthermore, the support department can prioritize support on relevant topics based on an employee's social media activity. This allows the support department to provide support based on more relevant information by analyzing an employee's social media activity. Some or all of the above processes in the support department may be performed using AI, for example, or not. For example, the support department can use a social media analysis AI model to analyze an employee's social media activity and propose support measures.

[0109] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0110] The customer center employee stress reduction system can be enhanced with features to monitor employee physiological data in real time to reduce employee stress. For example, it can measure employee heart rate and skin electrical activity to estimate stress levels. If an employee's heart rate suddenly increases, the system can provide advice on how to relax. Similarly, if skin electrical activity increases, the system can display a message encouraging the employee to take deep breaths. Furthermore, by recording employee physiological data over the long term and analyzing stress trends, the system can suggest the most suitable stress reduction methods for each individual employee. This allows for more effective stress reduction by utilizing employee physiological data.

[0111] The customer center employee stress reduction system can be enhanced with features to optimize employee work schedules to reduce employee stress. For example, it can analyze an employee's past work history and stress levels to suggest optimal working hours and break times. It can adjust schedules to include appropriate breaks to avoid employees working long hours continuously. Furthermore, if an employee's stress level is high, the system can suggest taking an earlier break. It can also coordinate employee work schedules with other employees to distribute stress evenly across the entire team. By optimizing employee work schedules, it can reduce stress and provide a more comfortable working environment.

[0112] A customer service employee stress reduction system can be enhanced with features to evaluate employee performance and provide feedback to reduce employee stress. For example, it can evaluate employee response time and customer satisfaction, and provide positive feedback to employees who demonstrate excellent performance. When an employee performs well, the system can display a message such as "That was a great response." It can also provide specific advice if improvement is needed, such as "Please explain things more clearly next time." Furthermore, by recording employee performance data over the long term and visualizing the process of growth, motivation can be improved. In this way, by evaluating employee performance and providing appropriate feedback, stress can be reduced and job satisfaction can be improved.

[0113] The customer center employee stress reduction system can include features to promote communication among employees in order to reduce employee stress. For example, it can provide a chat function for employees to support each other. If an employee faces a difficult situation, they can consult with other employees. It can also hold regular online meetings for team building to deepen bonds among employees. Furthermore, it can provide a messaging function for employees to express gratitude, promoting a positive work environment. For example, employees can send messages such as "thank you." In this way, by promoting communication among employees, stress can be reduced and the workplace atmosphere can be improved.

[0114] The customer center employee stress reduction system can be enhanced with features to monitor employee health and support health management in order to reduce employee stress. For example, it can record employees' meals and exercise to promote healthy lifestyle habits. It can also provide advice to employees on eating balanced meals. Furthermore, it can record exercise to encourage regular exercise and support goal achievement. In addition, it can monitor employees' sleep patterns and provide advice on getting enough rest. By monitoring employees' health and supporting their health management, it is possible to reduce stress and provide a more comfortable working environment.

[0115] The customer center employee stress reduction system can be enhanced with features that estimate employee emotions and provide customized relaxation content based on those emotions to reduce employee stress. For example, if an employee is feeling stressed, the system can provide relaxing music or meditation guides. If an employee is feeling anxious, the system can provide relaxation videos to help them feel at ease. If an employee is feeling angry, the system can introduce breathing exercises to help them regain their composure. Furthermore, the system can record employee emotional data over the long term and suggest the most suitable relaxation methods for each individual employee. This allows for stress reduction and a more comfortable working environment by providing customized relaxation content based on employee emotions.

[0116] The customer center employee stress reduction system can add features to support employee skill development in order to reduce employee stress. For example, it can provide online training programs for employees to acquire new skills. By receiving training on specific skills, employees can work with confidence. It can also assess employees' skill levels and suggest the most suitable training programs for each individual employee. Furthermore, it can provide regular feedback so that employees can feel the results of their skill development. In this way, by supporting employee skill development, stress can be reduced and job satisfaction can be improved.

[0117] The customer center employee stress reduction system can be enhanced with features that estimate employee emotions and provide customized break plans based on those emotions to reduce employee stress. For example, if an employee is feeling stressed, the system can suggest a short break and provide relaxing activities. If an employee is feeling anxious, the system can suggest deep breathing or stretching. If an employee is feeling angry, the system can suggest a walk to help them regain their composure. Furthermore, the system can record employee emotional data over the long term and suggest the most suitable break plan for each individual employee. This allows for stress reduction and a more comfortable working environment by providing customized break plans based on employee emotions.

[0118] The customer center employee stress reduction system can be enhanced with features to estimate employee emotions and provide customized mental health support based on those emotions, thereby reducing employee stress. For example, if an employee is feeling stressed, the system can suggest online counseling with a mental health professional. If an employee is feeling anxious, the system can also introduce relaxation techniques. Furthermore, if an employee is feeling angry, the system can provide anger management advice. In addition, it can record employee emotional data over the long term and suggest the most suitable mental health support for each individual employee. This allows for stress reduction and a more comfortable work environment by providing customized mental health support based on employee emotions.

[0119] The customer center employee stress reduction system can be enhanced with features that estimate employee emotions and provide a customized reward system based on those emotions to reduce employee stress. For example, if an employee performs well, the system can provide a message of appreciation or a special reward. If an employee is feeling stressed, the system can suggest a refreshing vacation. Furthermore, if an employee is feeling anxious, the system can provide special support to reassure them. In addition, it can record employee emotional data over the long term and suggest the most suitable reward system for each individual employee. This allows for stress reduction and improved job satisfaction by providing a customized reward system based on employee emotions.

[0120] The following briefly describes the processing flow for example form 2.

[0121] Step 1: The analysis unit analyzes the conversation between the customer and the employee in real time. The analysis unit uses natural language processing technology to understand the content of the conversation and performs morphological analysis, grammatical analysis, and semantic analysis. Step 2: The emotion analysis unit analyzes the emotions of the conversation analyzed by the analysis unit. The emotion analysis unit uses speech analysis technology and text analysis technology to determine the tone and emotional shifts of the conversation. Step 3: The intervention team intervenes in the conversation based on the analysis results obtained by the emotion analysis team. The intervention team makes neutral statements when the customer is making a one-sided complaint and makes statements to encourage the customer to calm down when they are becoming emotional. Step 4: The recording unit records the data obtained by the analysis unit and the sentiment analysis unit. The recording unit saves the audio and text data of the conversation and stores it in a database for later analysis. Step 5: The support department provides support to employees based on the results obtained by the emotion analysis department and the intervention department. The support department provides real-time advice to employees and provides support to help them take appropriate action.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] Each of the multiple elements described above, including the analysis unit, sentiment analysis unit, intervention unit, recording unit, and support unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 and analyzes the conversation between the customer and the employee in real time. The sentiment analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines the tone and emotional shifts of the conversation. The intervention unit is implemented by the control unit 46A of the smart device 14 and makes neutral statements when the customer is making a complaint unilaterally. The recording unit stores the conversation record in the database 24 of the data processing unit 12. The support unit is implemented by the control unit 46A of the smart device 14 and provides advice to the employee in real time. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0126] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.).

[0138] 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.

[0139] 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.

[0140] 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.

[0141] Each of the multiple elements described above, including the analysis unit, sentiment analysis unit, intervention unit, recording unit, and support unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 and analyzes the conversation between the customer and the employee in real time. The sentiment analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines the tone and emotional shifts of the conversation. The intervention unit is implemented by the control unit 46A of the smart glasses 214 and makes neutral statements when the customer is making a complaint unilaterally. The recording unit stores the conversation record in the database 24 of the data processing unit 12. The support unit is implemented by the control unit 46A of the smart glasses 214 and provides advice to the employee in real time. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0142] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] Each of the multiple elements described above, including the analysis unit, sentiment analysis unit, intervention unit, recording unit, and support unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 and analyzes the conversation between the customer and the employee in real time. The sentiment analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines the tone and emotional shifts of the conversation. The intervention unit is implemented by the control unit 46A of the headset terminal 314 and makes neutral statements when the customer is making a complaint unilaterally. The recording unit stores the conversation record in the database 24 of the data processing unit 12. The support unit is implemented by the control unit 46A of the headset terminal 314 and provides advice to the employee in real time. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0158] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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).

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.).

[0171] 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.

[0172] 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.

[0173] 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.

[0174] Each of the multiple elements described above, including the analysis unit, sentiment analysis unit, intervention unit, recording unit, and support unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 and analyzes the conversation between the customer and the employee in real time. The sentiment analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines the tone and emotional shifts of the conversation. The intervention unit is implemented by the control unit 46A of the robot 414 and makes neutral statements when the customer is making a complaint unilaterally. The recording unit stores the conversation record in the database 24 of the data processing unit 12. The support unit is implemented by the control unit 46A of the robot 414 and provides advice to the employee in real time. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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."

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] (Note 1) The analysis unit analyzes customer-employee conversations in real time, An emotion analysis unit analyzes the emotions of the conversation analyzed by the aforementioned analysis unit, An intervention unit intervenes in the conversation based on the analysis results obtained by the emotion analysis unit, A recording unit for recording the data obtained by the analysis unit and the emotion analysis unit, The system includes a support unit that provides support to employees based on the results obtained by the emotion analysis unit and the intervention unit. A system characterized by the following features. (Note 2) The aforementioned intervention unit is To make neutral statements when a customer is making a complaint unilaterally. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned recording unit is Record conversations and accumulate data for later analysis. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned support unit is When a customer is emotional, advise the employee to "remain calm." The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned emotion analysis unit, Determining the tone and emotional shifts of the conversation The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, Understanding the content of a conversation using natural language processing technology The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, We estimate customer emotions and adjust the conversation analysis method based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When analyzing conversations, we improve the accuracy of the analysis by referring to the customer's past complaint history. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, When analyzing conversations, the analysis takes into account specific phrases and word choices used by the customer. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, The system estimates customer emotions and prioritizes analysis results based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When analyzing conversations, we take into account the customer's geographical location to perform more relevant analysis. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During conversation analysis, we analyze the customer's social media activity and obtain relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned emotion analysis unit, It estimates customer emotions and adjusts the emotion analysis algorithm based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned emotion analysis unit, When performing sentiment analysis, consider the context of the conversation to more accurately determine the emotional shifts. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned emotion analysis unit, When performing sentiment analysis, referencing the customer's past emotional patterns improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned emotion analysis unit, It estimates customer emotions and adjusts how the analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned emotion analysis unit, When performing sentiment analysis, the analysis takes into account attribute information such as the customer's age and gender. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned emotion analysis unit, When performing sentiment analysis, referencing relevant literature on the customer improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned intervention unit is We estimate the customer's emotions and adjust the timing of interventions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned intervention unit is During intervention, the optimal intervention method is selected by referring to the customer's past complaint history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned intervention unit is When intervening, take into consideration the specific phrases and language used by the customer. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned intervention unit is We estimate the customer's emotions and adjust the intervention based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned intervention unit is When intervening, consider the customer's geographical location to ensure the intervention is highly relevant. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned intervention unit is During intervention, we analyze the customer's social media activity and conduct interventions based on relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned recording unit is We estimate customer emotions and adjust the recording methods based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned recording unit is When recording, prioritize recording important information while considering the context of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned recording unit is When recording, refer to the customer's past complaint history to improve the accuracy of the record. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned recording unit is The system estimates customer emotions and prioritizes recordings based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned recording unit is When recording data, the system prioritizes recording highly relevant information, taking into account the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned recording unit is During recording, analyze the customer's social media activity and record relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned support unit is We estimate the customer's emotions and adjust the support content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned support unit is When providing support, refer to the employee's past support history to select the most appropriate support method. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned support unit is When providing support, customize the support methods to take into account the employee's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned support unit is We estimate customer emotions and prioritize support based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned support unit is When providing support, the most suitable support method will be selected considering the geographical location of the employee. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned support unit is During support, we analyze employees' social media activity and suggest support methods. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0194] 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 analysis unit analyzes customer-employee conversations in real time, An emotion analysis unit analyzes the emotions of the conversation analyzed by the aforementioned analysis unit, An intervention unit intervenes in the conversation based on the analysis results obtained by the emotion analysis unit, A recording unit for recording the data obtained by the analysis unit and the emotion analysis unit, The system includes a support unit that provides support to employees based on the results obtained by the emotion analysis unit and the intervention unit. A system characterized by the following features.

2. The aforementioned intervention unit is To make neutral statements when a customer is making a complaint unilaterally. The system according to feature 1.

3. The aforementioned recording unit is Record conversations and accumulate data for later analysis. The system according to feature 1.

4. The aforementioned support unit is Provide advice to employees when customers are emotional. The system according to feature 1.

5. The aforementioned emotion analysis unit, Determining the tone and emotional shifts of the conversation The system according to feature 1.

6. The aforementioned analysis unit, Understanding the content of a conversation using natural language processing technology The system according to feature 1.

7. The aforementioned analysis unit, We estimate customer emotions and adjust the conversation analysis method based on the estimated customer emotions. The system according to feature 1.

8. The aforementioned analysis unit, When analyzing conversations, we improve the accuracy of the analysis by referring to the customer's past complaint history. The system according to feature 1.

9. The aforementioned analysis unit, When analyzing conversations, the analysis takes into account specific phrases and word choices used by the customer. The system according to feature 1.

Images