system

Abstract

The system according to this embodiment aims to efficiently evaluate and improve the customer service skills of crew members. [Solution] The system according to the embodiment comprises a learning unit, an evaluation unit, and a feedback unit. The learning unit learns the know-how of high-productivity crew members. The evaluation unit evaluates the customer service skills of the crew members based on the know-how learned by the learning unit. The feedback unit provides feedback on areas for improvement in the customer service skills of the crew members based on the results evaluated by the evaluation unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the evaluation and improvement of the customer service skills of crew members have not been carried out efficiently, and there is room for improvement.

[0005] The system according to the embodiment aims to efficiently evaluate and improve the customer service skills of crew members.

Means for Solving the Problems

[0006] The system according to the embodiment includes a learning unit, an evaluation unit, and a feedback unit. The learning unit learns the know-how of highly productive crew members. The evaluation unit evaluates the customer service skills of crew members based on the know-how learned by the learning unit. The feedback unit provides feedback on the improvement points of the customer service skills of crew members based on the results evaluated by the evaluation unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently evaluate and improve the customer service skills of crew members. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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 service skill evaluation system according to an embodiment of the present invention is a system that aims to standardize and improve the skills and communication abilities of crew members by using AI to evaluate their customer service skills and providing feedback on areas for improvement. The customer service skill evaluation system trains the AI ​​with the know-how of highly productive crew members, and based on the know-how the AI ​​has learned, it evaluates the crew's customer service skills and provides feedback on areas for improvement. This enables the standardization and improvement of the skills and communication abilities of crew members. First, the AI ​​is trained with the know-how of highly productive crew members. In this process, the AI ​​analyzes examples of customer service and talk scripts from highly productive crew members to learn effective customer service methods. For example, it learns what kinds of questions highly productive crew members ask customers and how they close deals. This allows the AI ​​to understand effective customer service methods. Next, the AI ​​evaluates the crew's customer service skills based on the know-how it has learned. For example, when a crew member actually provides customer service, the AI ​​analyzes and evaluates the content of that service in real time. The evaluation criteria are set based on the know-how of highly productive crew members. This allows for an objective evaluation of the crew's customer service skills. Furthermore, based on the results of the AI ​​evaluation, feedback is provided on areas for improvement in the crew's customer service skills. For example, the system provides specific feedback to crew members on where their communication is ineffective and how they should improve. This allows crew members to understand and improve their customer service skills. This system enables the standardization and improvement of crew members' skills and communication abilities. For example, even if each department across the country conducts its own training, the AI ​​provides evaluation and feedback based on consistent standards, reducing variations in crew members' skills. It also enables theory-based training rather than relying on intuition, which is expected to improve crew members' customer service skills. As a concrete example, consider a scenario where the AI ​​learns from the customer service examples of high-productivity crew members and evaluates the customer service skills of other crew members. For example, if a customer asks, "How much does a smart device cost per month?", the AI ​​evaluates how the crew member should answer based on the know-how of a high-productivity crew member. A high-productivity crew member might answer, "You can use it for XX yen."By asking follow-up questions such as, "Which model and carrier are you currently using?", it's possible to elicit customer needs and close a deal. On the other hand, a low-productivity crew member might simply answer, "You can use it for XX yen," and that would not lead to a sale. In this way, by having AI evaluate the crew member's customer service skills and provide feedback on specific areas for improvement, improvements in the crew member's customer service skills can be expected. Thus, the customer service skill evaluation system can achieve standardization and improvement of skills and communication by evaluating the crew member's customer service skills and providing feedback on areas for improvement.

[0029] The customer service skills evaluation system according to this embodiment comprises a learning unit, an evaluation unit, and a feedback unit. The learning unit learns the know-how of high-productivity crew members. For example, the learning unit analyzes customer service examples and talk scripts of high-productivity crew members to learn effective customer service methods. For example, the learning unit can learn what kinds of questions high-productivity crew members ask customers and how they close deals. The learning unit can also use AI to analyze customer service examples of high-productivity crew members and learn effective customer service methods. For example, the learning unit inputs customer service examples of high-productivity crew members into the AI, and the AI ​​analyzes those examples to learn effective customer service methods. The evaluation unit evaluates the customer service skills of crew members based on the know-how learned by the learning unit. For example, the evaluation unit analyzes the content of customer service in real time when a crew member is actually providing customer service and performs an evaluation. The evaluation criteria are set based on the know-how of high-productivity crew members. For example, the evaluation unit can input the content of a crew member's customer service into the AI, and the AI ​​analyzes the content and performs an evaluation. The feedback unit provides feedback on areas for improvement in the crew member's customer service skills based on the evaluation results from the evaluation unit. The feedback unit provides specific feedback to crew members, for example, on areas where their communication is ineffective and how they should improve. For example, the feedback unit can provide specific improvement suggestions to crew members based on the results of the AI ​​evaluation. As a result, the customer service skill evaluation system according to this embodiment can achieve uniformity and improvement in skills and communication by evaluating the customer service skills of crew members and providing feedback on areas for improvement. For example, even if each department across the country conducts its own training, the AI ​​will evaluate and provide feedback based on consistent standards, thus reducing variations in crew members' skills. In addition, it enables theory-based training that does not rely on intuition, and is expected to improve the customer service skills of crew members. Furthermore, by using AI, the customer service skills of crew members can be evaluated objectively, improving the reliability of the evaluation. As a result, it is expected that the improvement of crew members' customer service skills will be promoted and contribute to improved customer satisfaction.

[0030] The learning department learns the know-how of high-productivity crew members. Specifically, it collects customer service examples and talk scripts from high-productivity crew members and analyzes them in detail to learn effective customer service methods. For example, the learning department can learn what questions high-productivity crew members ask customers and how they close deals. This includes specific phrases and timing to elicit customer responses and purchase intent. Furthermore, the learning department can also use AI to analyze customer service examples from high-productivity crew members and learn effective customer service methods. The AI ​​uses natural language processing technology to analyze talk scripts and extract patterns and commonalities of successful customer service. For example, the AI ​​can identify the optimal answers to customer questions and effective phrases for closing deals. This allows the learning department to accumulate scientific and data-driven customer service know-how, rather than relying solely on rules of thumb. In addition, by regularly collecting new customer service examples and training the AI, the learning department can always respond to the latest customer service trends and customer needs. This allows the learning department to provide a foundation for crew members to consistently maintain high customer service skills and improve customer satisfaction.

[0031] The evaluation department assesses the customer service skills of crew members based on the know-how learned by the learning department. Specifically, it analyzes and evaluates the content of customer service in real time as the crew members actually provide service. The evaluation criteria are set based on the know-how of high-productivity crew members. For example, the evaluation department can input the content of the crew members' customer service into an AI, which then analyzes and evaluates the content. The AI ​​uses speech recognition technology to transcribe the crew members' statements into text and natural language processing technology to analyze the content. This allows the evaluation department to assess how well the crew members' statements match the know-how of high-productivity crew members. Furthermore, the evaluation department can also incorporate customer reactions and purchasing behavior as part of the evaluation. For example, it can analyze how customers reacted to the crew members' service and how much their purchasing intent increased, and then make a comprehensive evaluation. This allows the evaluation department to evaluate the crew members' customer service skills from multiple perspectives and provide more accurate feedback. In addition, the evaluation department can accumulate past evaluation data and analyze improvements and trends in crew members' skills. This allows the evaluation department to continuously monitor the crew members' customer service skills and provide training and support as needed.

[0032] The Feedback Department provides feedback on areas for improvement in crew members' customer service skills based on the evaluation results from the Evaluation Department. Specifically, it provides detailed feedback on which aspects of their communication are ineffective and how they should improve. For example, the Feedback Department can provide specific improvement feedback to crew members based on the results of AI evaluations. The AI ​​analyzes the evaluation results and identifies the crew members' strengths and weaknesses. For example, if a crew member is not able to answer a customer's question appropriately, the AI ​​will suggest specific phrases and approaches. It will also provide advice on improving effective phrases and timing during closing. Furthermore, the Feedback Department can re-evaluate the customer service content after the crew member has actually made improvements and provide continuous feedback. This allows crew members to continuously improve their skills. In addition, the Feedback Department can provide customized feedback tailored to the individual needs and skill levels of each crew member. For example, it can provide feedback aimed at improving basic customer service skills to novice crew members and feedback aimed at refining advanced skills to experienced crew members. In this way, the Feedback Department can standardize and improve the skill level and communication of crew members, contributing to increased customer satisfaction.

[0033] The evaluation unit can evaluate the crew's customer service skills in real time. For example, the evaluation unit can analyze and evaluate the content of customer service in real time as the crew actually provides service. For example, the evaluation unit can input the content of the crew's customer service into an AI, which can then analyze and evaluate the content in real time. The evaluation unit can also use an AI to analyze and evaluate the content of the crew's customer service in order to evaluate the crew's customer service skills in real time. For example, the evaluation unit can input the content of the crew's customer service into an AI in real time, which can then analyze and evaluate the content. This allows for immediate feedback by evaluating the crew's customer service skills in real time. Some or all of the above processes in the evaluation unit may be performed using an AI or not. For example, the evaluation unit can use an AI to analyze and evaluate the content of the crew's customer service in real time.

[0034] The feedback unit can provide specific feedback on areas for improvement. For example, the feedback unit can provide specific feedback on which parts of a crew member's communication are not effective and how they should improve. For example, the feedback unit can provide specific feedback on areas for improvement to a crew member based on the results of an AI evaluation. The feedback unit can also use AI to analyze a crew member's customer service and provide feedback on areas for improvement in order to provide specific feedback on the crew member's customer service skills. For example, the feedback unit can input the crew member's customer service content into the AI, which will then analyze the content and provide feedback on specific areas for improvement. This will promote the improvement of the crew member's skills by providing specific feedback on areas for improvement. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to analyze a crew member's customer service content and provide feedback on specific areas for improvement in order to analyze the crew member's customer service content and provide feedback on areas for improvement.

[0035] The learning unit can learn effective customer service methods by analyzing customer service examples and talk scripts of highly productive crew members. For example, the learning unit can learn what kinds of questions highly productive crew members ask customers and how they close deals. The learning unit can also learn effective customer service methods by analyzing customer service examples of highly productive crew members using AI. For example, the learning unit inputs customer service examples of highly productive crew members into the AI, which then analyzes those examples to learn effective customer service methods. This allows the learning unit to learn effective customer service methods by analyzing customer service examples and talk scripts of highly productive crew members. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can use AI to analyze customer service examples of highly productive crew members and learn effective customer service methods.

[0036] The learning unit can analyze customer service examples from high-productivity crew members by time of day and learn effective customer service methods for each time of day. For example, the learning unit can learn effective customer service methods for the morning and apply them to the morning shift. It can also learn effective customer service methods for the midday shift and apply them to the midday shift. Furthermore, it can learn effective customer service methods for the evening and apply them to the evening shift. By learning effective customer service methods for each time of day, it becomes possible to provide customer service appropriate for each time of day. Some or all of the above processing in the learning unit may be performed using AI or not. For example, in order to analyze customer service examples from high-productivity crew members by time of day and learn effective customer service methods for each time of day, the learning unit can use AI to analyze customer service examples from high-productivity crew members and learn effective customer service methods for each time of day.

[0037] The learning unit can analyze the voice of high-productivity crew members' customer service scripts and learn their voice tone and speaking patterns. For example, the learning unit can analyze the voice tone of high-productivity crew members and learn how to speak in the same tone. It can also analyze the rhythm of high-productivity crew members' speech and learn how to speak in the same rhythm. Furthermore, the learning unit can analyze the word choices of high-productivity crew members and learn how to use the same words. By learning voice tone and speaking patterns, more effective customer service becomes possible. Some or all of the above processing in the learning unit may be performed using AI or not. For example, in order to analyze the voice of high-productivity crew members' customer service scripts and learn their voice tone and speaking patterns, the learning unit can use AI to analyze the voice of high-productivity crew members' customer service scripts and learn their voice tone and speaking patterns.

[0038] The learning unit can analyze customer service examples from highly productive crew members by region and learn effective customer service methods for each region. For example, the learning unit can learn effective customer service methods in urban areas and apply them to stores in urban areas. It can also learn effective customer service methods in suburban areas and apply them to stores in suburban areas. Furthermore, it can learn effective customer service methods in tourist areas and apply them to stores in tourist areas. By learning effective customer service methods for each region, it becomes possible to provide customer service that is appropriate for each region. Some or all of the above processing in the learning unit may be performed using AI or not. For example, in order to analyze customer service examples from highly productive crew members by region and learn effective customer service methods for each region, the learning unit can use AI to analyze customer service examples from highly productive crew members and learn effective customer service methods for each region.

[0039] The learning unit can visually analyze the customer service scripts of high-productivity crew members and learn patterns of gestures and facial expressions. For example, the learning unit can analyze the gestures of high-productivity crew members and learn how to use the same gestures. It can also analyze the facial expressions of high-productivity crew members and learn how to use the same facial expressions. Furthermore, the learning unit can analyze the posture of high-productivity crew members and learn how to adopt the same posture. This allows for more effective customer service by learning patterns of gestures and facial expressions. Some or all of the above processing in the learning unit may be performed using AI or not. For example, in order to visually analyze the customer service scripts of high-productivity crew members and learn patterns of gestures and facial expressions, the learning unit can use AI to analyze the customer service scripts of high-productivity crew members and learn patterns of gestures and facial expressions.

[0040] The evaluation unit can analyze customer reactions in real time and incorporate them into the evaluation when assessing crew members' customer service skills. For example, the evaluation unit can analyze customer facial expressions to evaluate crew members' customer service skills. It can also analyze the tone of a customer's voice to evaluate crew members' customer service skills. Furthermore, the evaluation unit can analyze customer gestures to evaluate crew members' customer service skills. This allows for more accurate evaluations by analyzing customer reactions in real time. Some or all of the above processes in the evaluation unit may be performed using AI or not. For example, the evaluation unit can use AI to analyze customer reactions in real time and incorporate them into the evaluation.

[0041] The evaluation department can improve the accuracy of its evaluations by referring to past evaluation data when assessing the customer service skills of its crew members. For example, the evaluation department can evaluate the customer service skills of its crew members based on past evaluation data. The evaluation department can also analyze past evaluation data and adjust the evaluation criteria. Furthermore, the evaluation department can maintain consistency in its evaluations by referring to past evaluation data. This improves the accuracy of the evaluations by referring to past evaluation data. Some or all of the above processes in the evaluation department may be performed using AI or not. For example, the evaluation department can use AI to analyze past evaluation data in order to improve the accuracy of its evaluations by referring to past evaluation data.

[0042] The evaluation unit can consider customer attribute information when evaluating the customer service skills of crew members. For example, the evaluation unit can evaluate the customer's customer service skills by considering the customer's age. It can also evaluate the customer's customer service skills by considering the customer's gender. Furthermore, the evaluation unit can evaluate the customer's customer service skills by considering the customer's purchase history. This allows for a more appropriate evaluation by considering customer attribute information. Some or all of the above processes in the evaluation unit may be performed using AI or not. For example, in order to perform an evaluation that takes customer attribute information into consideration, the evaluation unit can use AI to analyze customer attribute information and reflect it in the evaluation.

[0043] The evaluation unit can analyze background and ambient noise during customer service and incorporate this analysis into the evaluation of the crew's customer service skills. For example, if the background noise is loud, the evaluation unit can assess how easily the crew's voice can be heard. Furthermore, if the ambient noise is quiet, the evaluation unit can also assess the tone of the crew's voice. In addition, the evaluation unit can analyze background and ambient noise to evaluate the crew's customer service skills. This allows for a more accurate evaluation by analyzing background and ambient noise. Some or all of the above processing in the evaluation unit may be performed using AI, or not. For example, the evaluation unit can use AI to analyze background and ambient noise during customer service and incorporate this analysis into the evaluation.

[0044] The feedback unit can, during the feedback process, refer to the crew's past improvement history to suggest specific areas for improvement. For example, the feedback unit can suggest specific areas for improvement based on the crew's past improvement history. The feedback unit can also analyze the crew's past improvement history and propose areas for improvement. Furthermore, the feedback unit can refer to the crew's past improvement history to check the progress of improvements. This allows for the suggestion of more specific areas for improvement by referring to past improvement history. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to analyze past improvement history in order to suggest specific areas for improvement by referring to the crew's past improvement history.

[0045] The feedback unit can provide an indicator that quantitatively shows the degree of improvement in the crew's customer service skills during the feedback process. For example, the feedback unit can show the degree of improvement in the crew's customer service skills as a score. It can also show the degree of improvement in the crew's customer service skills as a graph. Furthermore, the feedback unit can show the degree of improvement in the crew's customer service skills as a numerical value. This quantitatively shows the degree of improvement in customer service skills, thereby improving the crew's motivation. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, in order to provide an indicator that quantitatively shows the degree of improvement in the crew's customer service skills, the feedback unit can use AI to analyze the degree of improvement in the crew's customer service skills and provide an indicator that quantitatively shows it.

[0046] The feedback unit can select the optimal feedback method by considering the crew's attribute information during the feedback process. For example, the feedback unit can select the optimal feedback method by considering the crew's age. It can also select the optimal feedback method by considering the crew's gender. Furthermore, the feedback unit can select the optimal feedback method by considering the crew's years of experience. This allows for more appropriate feedback by considering the crew's attribute information. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to analyze the crew's attribute information and select the optimal feedback method in order to consider the crew's attribute information.

[0047] The feedback department can provide training content to help improve the crew's customer service skills during the feedback process. For example, the feedback department can provide video training to help improve the crew's customer service skills. It can also provide online courses to help improve the crew's customer service skills. Furthermore, the feedback department can provide workshops to help improve the crew's customer service skills. In this way, providing training content promotes the improvement of the crew's customer service skills. Some or all of the above processes in the feedback department may be performed using AI or not. For example, the feedback department can use AI to analyze the crew's skill level and select appropriate training content to provide training content that helps improve the crew's customer service skills.

[0048] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0049] The customer service skills evaluation system can improve the accuracy of its evaluations by referring to the crew's past customer service history when assessing their customer service skills. For example, the evaluation unit evaluates the crew's current customer service skills based on their past customer service history. The evaluation unit can also analyze past customer service history and adjust the evaluation criteria. Furthermore, the evaluation unit can refer to past customer service history to maintain consistency in evaluations. This improves the accuracy of evaluations by referring to past customer service history. Some or all of the above processes in the evaluation unit may be performed using AI or not. For example, the evaluation unit can use AI to analyze past customer service history in order to improve the accuracy of evaluations by referring to past customer service history.

[0050] The customer service skills evaluation system can analyze customer reactions in real time and incorporate them into the evaluation when assessing the customer service skills of crew members. For example, the evaluation unit can analyze the customer's facial expressions to evaluate the crew's customer service skills. The evaluation unit can also analyze the customer's tone of voice to evaluate the crew's customer service skills. Furthermore, the evaluation unit can analyze the customer's gestures to evaluate the crew's customer service skills. This allows for more accurate evaluation by analyzing customer reactions in real time. Some or all of the above processes in the evaluation unit may be performed using AI or not. For example, the evaluation unit can use AI to analyze customer reactions in real time and incorporate them into the evaluation.

[0051] The customer service skills evaluation system can analyze background and ambient noise during customer service and incorporate this analysis into the evaluation. For example, if the background noise is loud, the evaluation unit can assess how easily the crew member's voice can be heard. The evaluation unit can also assess the tone of the crew member's voice if the ambient noise is quiet. Furthermore, the evaluation unit can analyze background and ambient noise to evaluate the crew member's customer service skills. This allows for a more accurate evaluation by analyzing background and ambient noise. Some or all of the above processing in the evaluation unit may be performed using AI, or not. For example, the evaluation unit can use AI to analyze background and ambient noise during customer service and incorporate this analysis into the evaluation.

[0052] The customer service skills evaluation system can evaluate crew members' customer service skills while taking customer attribute information into consideration. For example, the evaluation unit can evaluate crew members' customer service skills while considering the customer's age. The evaluation unit can also evaluate crew members' customer service skills while considering the customer's gender. Furthermore, the evaluation unit can evaluate crew members' customer service skills while considering the customer's purchase history. This allows for a more appropriate evaluation by considering customer attribute information. Some or all of the above processing in the evaluation unit may be performed using AI or not. For example, in order to perform an evaluation while considering customer attribute information, the evaluation unit can use AI to analyze customer attribute information and reflect it in the evaluation.

[0053] A customer service skills evaluation system can improve the accuracy of evaluations by referring to past evaluation data when assessing the customer service skills of crew members. For example, the evaluation unit evaluates the customer service skills of crew members based on past evaluation data. The evaluation unit can also analyze past evaluation data and adjust the evaluation criteria. Furthermore, the evaluation unit can refer to past evaluation data to maintain consistency in evaluations. This improves the accuracy of evaluations by referring to past evaluation data. Some or all of the above processes in the evaluation unit may be performed using AI or not. For example, the evaluation unit can use AI to analyze past evaluation data in order to improve the accuracy of evaluations by referring to past evaluation data.

[0054] The following briefly describes the processing flow for example form 1.

[0055] Step 1: The learning unit learns the know-how of high-productivity crew members. For example, it analyzes customer service examples and talk scripts of high-productivity crew members to learn effective customer service methods. The learning unit can also use AI to analyze customer service examples of high-productivity crew members and learn effective customer service methods. Step 2: The evaluation unit evaluates the crew's customer service skills based on the know-how learned by the learning unit. For example, it analyzes and evaluates the content of customer service in real time as the crew actually provides service. The evaluation criteria are set based on the know-how of high-productivity crew members. The evaluation unit can use AI to analyze and evaluate the crew's customer service. Step 3: The Feedback Department provides feedback on areas for improvement in the crew's customer service skills based on the evaluation results from the Evaluation Department. For example, it provides specific feedback on which parts of the crew's communication are not effective and how they should improve. The Feedback Department can provide specific feedback on areas for improvement to the crew based on the results evaluated by the AI.

[0056] (Example of form 2) The customer service skill evaluation system according to an embodiment of the present invention is a system that aims to standardize and improve the skills and communication abilities of crew members by using AI to evaluate their customer service skills and providing feedback on areas for improvement. The customer service skill evaluation system trains the AI ​​with the know-how of highly productive crew members, and based on the know-how the AI ​​has learned, it evaluates the crew's customer service skills and provides feedback on areas for improvement. This enables the standardization and improvement of the skills and communication abilities of crew members. First, the AI ​​is trained with the know-how of highly productive crew members. In this process, the AI ​​analyzes examples of customer service and talk scripts from highly productive crew members to learn effective customer service methods. For example, it learns what kinds of questions highly productive crew members ask customers and how they close deals. This allows the AI ​​to understand effective customer service methods. Next, the AI ​​evaluates the crew's customer service skills based on the know-how it has learned. For example, when a crew member actually provides customer service, the AI ​​analyzes and evaluates the content of that service in real time. The evaluation criteria are set based on the know-how of highly productive crew members. This allows for an objective evaluation of the crew's customer service skills. Furthermore, based on the results of the AI ​​evaluation, feedback is provided on areas for improvement in the crew's customer service skills. For example, the system provides specific feedback to crew members on where their communication is ineffective and how they should improve. This allows crew members to understand and improve their customer service skills. This system enables the standardization and improvement of crew members' skills and communication abilities. For example, even if each department across the country conducts its own training, the AI ​​provides evaluation and feedback based on consistent standards, reducing variations in crew members' skills. It also enables theory-based training rather than relying on intuition, which is expected to improve crew members' customer service skills. As a concrete example, consider a scenario where the AI ​​learns from the customer service examples of high-productivity crew members and evaluates the customer service skills of other crew members. For example, if a customer asks, "How much does a smart device cost per month?", the AI ​​evaluates how the crew member should answer based on the know-how of a high-productivity crew member. A high-productivity crew member might answer, "You can use it for XX yen."By asking follow-up questions such as, "Which model and carrier are you currently using?", it's possible to elicit customer needs and close a deal. On the other hand, a low-productivity crew member might simply answer, "You can use it for XX yen," and that would not lead to a sale. In this way, by having AI evaluate the crew member's customer service skills and provide feedback on specific areas for improvement, improvements in the crew member's customer service skills can be expected. Thus, the customer service skill evaluation system can achieve standardization and improvement of skills and communication by evaluating the crew member's customer service skills and providing feedback on areas for improvement.

[0057] The customer service skills evaluation system according to this embodiment comprises a learning unit, an evaluation unit, and a feedback unit. The learning unit learns the know-how of high-productivity crew members. For example, the learning unit analyzes customer service examples and talk scripts of high-productivity crew members to learn effective customer service methods. For example, the learning unit can learn what kinds of questions high-productivity crew members ask customers and how they close deals. The learning unit can also use AI to analyze customer service examples of high-productivity crew members and learn effective customer service methods. For example, the learning unit inputs customer service examples of high-productivity crew members into the AI, and the AI ​​analyzes those examples to learn effective customer service methods. The evaluation unit evaluates the customer service skills of crew members based on the know-how learned by the learning unit. For example, the evaluation unit analyzes the content of customer service in real time when a crew member is actually providing customer service and performs an evaluation. The evaluation criteria are set based on the know-how of high-productivity crew members. For example, the evaluation unit can input the content of a crew member's customer service into the AI, and the AI ​​analyzes the content and performs an evaluation. The feedback unit provides feedback on areas for improvement in the crew member's customer service skills based on the evaluation results from the evaluation unit. The feedback unit provides specific feedback to crew members, for example, on areas where their communication is ineffective and how they should improve. For example, the feedback unit can provide specific improvement suggestions to crew members based on the results of the AI ​​evaluation. As a result, the customer service skill evaluation system according to this embodiment can achieve uniformity and improvement in skills and communication by evaluating the customer service skills of crew members and providing feedback on areas for improvement. For example, even if each department across the country conducts its own training, the AI ​​will evaluate and provide feedback based on consistent standards, thus reducing variations in crew members' skills. In addition, it enables theory-based training that does not rely on intuition, and is expected to improve the customer service skills of crew members. Furthermore, by using AI, the customer service skills of crew members can be evaluated objectively, improving the reliability of the evaluation. As a result, it is expected that the improvement of crew members' customer service skills will be promoted and contribute to improved customer satisfaction.

[0058] The learning department learns the know-how of high-productivity crew members. Specifically, it collects customer service examples and talk scripts from high-productivity crew members and analyzes them in detail to learn effective customer service methods. For example, the learning department can learn what questions high-productivity crew members ask customers and how they close deals. This includes specific phrases and timing to elicit customer responses and purchase intent. Furthermore, the learning department can also use AI to analyze customer service examples from high-productivity crew members and learn effective customer service methods. The AI ​​uses natural language processing technology to analyze talk scripts and extract patterns and commonalities of successful customer service. For example, the AI ​​can identify the optimal answers to customer questions and effective phrases for closing deals. This allows the learning department to accumulate scientific and data-driven customer service know-how, rather than relying solely on rules of thumb. In addition, by regularly collecting new customer service examples and training the AI, the learning department can always respond to the latest customer service trends and customer needs. This allows the learning department to provide a foundation for crew members to consistently maintain high customer service skills and improve customer satisfaction.

[0059] The evaluation department assesses the customer service skills of crew members based on the know-how learned by the learning department. Specifically, it analyzes and evaluates the content of customer service in real time as the crew members actually provide service. The evaluation criteria are set based on the know-how of high-productivity crew members. For example, the evaluation department can input the content of the crew members' customer service into an AI, which then analyzes and evaluates the content. The AI ​​uses speech recognition technology to transcribe the crew members' statements into text and natural language processing technology to analyze the content. This allows the evaluation department to assess how well the crew members' statements match the know-how of high-productivity crew members. Furthermore, the evaluation department can also incorporate customer reactions and purchasing behavior as part of the evaluation. For example, it can analyze how customers reacted to the crew members' service and how much their purchasing intent increased, and then make a comprehensive evaluation. This allows the evaluation department to evaluate the crew members' customer service skills from multiple perspectives and provide more accurate feedback. In addition, the evaluation department can accumulate past evaluation data and analyze improvements and trends in crew members' skills. This allows the evaluation department to continuously monitor the crew members' customer service skills and provide training and support as needed.

[0060] The Feedback Department provides feedback on areas for improvement in crew members' customer service skills based on the evaluation results from the Evaluation Department. Specifically, it provides detailed feedback on which aspects of their communication are ineffective and how they should improve. For example, the Feedback Department can provide specific improvement feedback to crew members based on the results of AI evaluations. The AI ​​analyzes the evaluation results and identifies the crew members' strengths and weaknesses. For example, if a crew member is not able to answer a customer's question appropriately, the AI ​​will suggest specific phrases and approaches. It will also provide advice on improving effective phrases and timing during closing. Furthermore, the Feedback Department can re-evaluate the customer service content after the crew member has actually made improvements and provide continuous feedback. This allows crew members to continuously improve their skills. In addition, the Feedback Department can provide customized feedback tailored to the individual needs and skill levels of each crew member. For example, it can provide feedback aimed at improving basic customer service skills to novice crew members and feedback aimed at refining advanced skills to experienced crew members. In this way, the Feedback Department can standardize and improve the skill level and communication of crew members, contributing to increased customer satisfaction.

[0061] The evaluation unit can evaluate the crew's customer service skills in real time. For example, the evaluation unit can analyze and evaluate the content of customer service in real time as the crew actually provides service. For example, the evaluation unit can input the content of the crew's customer service into an AI, which can then analyze and evaluate the content in real time. The evaluation unit can also use an AI to analyze and evaluate the content of the crew's customer service in order to evaluate the crew's customer service skills in real time. For example, the evaluation unit can input the content of the crew's customer service into an AI in real time, which can then analyze and evaluate the content. This allows for immediate feedback by evaluating the crew's customer service skills in real time. Some or all of the above processes in the evaluation unit may be performed using an AI or not. For example, the evaluation unit can use an AI to analyze and evaluate the content of the crew's customer service in real time.

[0062] The feedback unit can provide specific feedback on areas for improvement. For example, the feedback unit can provide specific feedback on which parts of a crew member's communication are not effective and how they should improve. For example, the feedback unit can provide specific feedback on areas for improvement to a crew member based on the results of an AI evaluation. The feedback unit can also use AI to analyze a crew member's customer service and provide feedback on areas for improvement in order to provide specific feedback on the crew member's customer service skills. For example, the feedback unit can input the crew member's customer service content into the AI, which will then analyze the content and provide feedback on specific areas for improvement. This will promote the improvement of the crew member's skills by providing specific feedback on areas for improvement. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to analyze a crew member's customer service content and provide feedback on specific areas for improvement in order to analyze the crew member's customer service content and provide feedback on areas for improvement.

[0063] The learning unit can learn effective customer service methods by analyzing customer service examples and talk scripts of highly productive crew members. For example, the learning unit can learn what kinds of questions highly productive crew members ask customers and how they close deals. The learning unit can also learn effective customer service methods by analyzing customer service examples of highly productive crew members using AI. For example, the learning unit inputs customer service examples of highly productive crew members into the AI, which then analyzes those examples to learn effective customer service methods. This allows the learning unit to learn effective customer service methods by analyzing customer service examples and talk scripts of highly productive crew members. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can use AI to analyze customer service examples of highly productive crew members and learn effective customer service methods.

[0064] The learning unit can estimate the crew's emotions and select training data based on the estimated emotions. For example, if a crew member is stressed, the learning unit can prioritize training on relaxing customer service examples. If a crew member is highly motivated, the learning unit can also train on challenging customer service examples. Furthermore, if a crew member is tired, the learning unit can train on simple and effective customer service examples. This allows for more effective learning by selecting training data based on the crew member's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can use AI to analyze the crew member's emotions and select training data in order to estimate their emotions and select training data based on the estimated emotions.

[0065] The learning unit can analyze customer service examples from high-productivity crew members by time of day and learn effective customer service methods for each time of day. For example, the learning unit can learn effective customer service methods for the morning and apply them to the morning shift. It can also learn effective customer service methods for the midday shift and apply them to the midday shift. Furthermore, it can learn effective customer service methods for the evening and apply them to the evening shift. By learning effective customer service methods for each time of day, it becomes possible to provide customer service appropriate for each time of day. Some or all of the above processing in the learning unit may be performed using AI or not. For example, in order to analyze customer service examples from high-productivity crew members by time of day and learn effective customer service methods for each time of day, the learning unit can use AI to analyze customer service examples from high-productivity crew members and learn effective customer service methods for each time of day.

[0066] The learning unit can analyze the voice of high-productivity crew members' customer service scripts and learn their voice tone and speaking patterns. For example, the learning unit can analyze the voice tone of high-productivity crew members and learn how to speak in the same tone. It can also analyze the rhythm of high-productivity crew members' speech and learn how to speak in the same rhythm. Furthermore, the learning unit can analyze the word choices of high-productivity crew members and learn how to use the same words. By learning voice tone and speaking patterns, more effective customer service becomes possible. Some or all of the above processing in the learning unit may be performed using AI or not. For example, in order to analyze the voice of high-productivity crew members' customer service scripts and learn their voice tone and speaking patterns, the learning unit can use AI to analyze the voice of high-productivity crew members' customer service scripts and learn their voice tone and speaking patterns.

[0067] The learning unit can estimate the crew's emotions and adjust the learning frequency based on the estimated emotions. For example, if a crew member is stressed, the learning unit can reduce the learning frequency. Conversely, if a crew member is highly motivated, the learning unit can increase the learning frequency. Furthermore, if a crew member is tired, the learning unit can adjust the learning frequency. This allows for more effective learning by adjusting the learning frequency based on the crew member's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can use AI to analyze the crew member's emotions and adjust the learning frequency in order to estimate the crew member's emotions and adjust the learning frequency based on the estimated emotions.

[0068] The learning unit can analyze customer service examples from highly productive crew members by region and learn effective customer service methods for each region. For example, the learning unit can learn effective customer service methods in urban areas and apply them to stores in urban areas. It can also learn effective customer service methods in suburban areas and apply them to stores in suburban areas. Furthermore, it can learn effective customer service methods in tourist areas and apply them to stores in tourist areas. By learning effective customer service methods for each region, it becomes possible to provide customer service that is appropriate for each region. Some or all of the above processing in the learning unit may be performed using AI or not. For example, in order to analyze customer service examples from highly productive crew members by region and learn effective customer service methods for each region, the learning unit can use AI to analyze customer service examples from highly productive crew members and learn effective customer service methods for each region.

[0069] The learning unit can visually analyze the customer service scripts of high-productivity crew members and learn patterns of gestures and facial expressions. For example, the learning unit can analyze the gestures of high-productivity crew members and learn how to use the same gestures. It can also analyze the facial expressions of high-productivity crew members and learn how to use the same facial expressions. Furthermore, the learning unit can analyze the posture of high-productivity crew members and learn how to adopt the same posture. This allows for more effective customer service by learning patterns of gestures and facial expressions. Some or all of the above processing in the learning unit may be performed using AI or not. For example, in order to visually analyze the customer service scripts of high-productivity crew members and learn patterns of gestures and facial expressions, the learning unit can use AI to analyze the customer service scripts of high-productivity crew members and learn patterns of gestures and facial expressions.

[0070] The evaluation unit can estimate the crew's emotions and adjust the evaluation criteria based on the estimated emotions. For example, if a crew member is stressed, the evaluation unit may relax the evaluation criteria. Conversely, if a crew member is relaxed, the evaluation unit may tighten the evaluation criteria. Furthermore, if a crew member is tired, the evaluation unit may adjust the evaluation criteria. This allows for more appropriate evaluations by adjusting the evaluation criteria based on the crew member's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using AI or not. For example, the evaluation unit can use AI to analyze the crew member's emotions and adjust the evaluation criteria in order to estimate the crew member's emotions and adjust the evaluation criteria based on the estimated emotions.

[0071] The evaluation unit can analyze customer reactions in real time and incorporate them into the evaluation when assessing crew members' customer service skills. For example, the evaluation unit can analyze customer facial expressions to evaluate crew members' customer service skills. It can also analyze the tone of a customer's voice to evaluate crew members' customer service skills. Furthermore, the evaluation unit can analyze customer gestures to evaluate crew members' customer service skills. This allows for more accurate evaluations by analyzing customer reactions in real time. Some or all of the above processes in the evaluation unit may be performed using AI or not. For example, the evaluation unit can use AI to analyze customer reactions in real time and incorporate them into the evaluation.

[0072] The evaluation department can improve the accuracy of its evaluations by referring to past evaluation data when assessing the customer service skills of its crew members. For example, the evaluation department can evaluate the customer service skills of its crew members based on past evaluation data. The evaluation department can also analyze past evaluation data and adjust the evaluation criteria. Furthermore, the evaluation department can maintain consistency in its evaluations by referring to past evaluation data. This improves the accuracy of the evaluations by referring to past evaluation data. Some or all of the above processes in the evaluation department may be performed using AI or not. For example, the evaluation department can use AI to analyze past evaluation data in order to improve the accuracy of its evaluations by referring to past evaluation data.

[0073] The evaluation unit can estimate the crew's emotions and adjust how the evaluation results are displayed based on the estimated emotions. For example, if a crew member is tense, the evaluation unit may display the evaluation results simply. If a crew member is relaxed, the evaluation unit may also display detailed evaluation results. Furthermore, if a crew member is tired, the evaluation unit may adjust the display of the evaluation results. This allows for more appropriate feedback by adjusting how the evaluation results are displayed based on the crew member's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using AI or not. For example, the evaluation unit may use AI to analyze the crew member's emotions and adjust how the evaluation results are displayed in order to estimate the crew member's emotions and adjust how the evaluation results are displayed based on the estimated emotions.

[0074] The evaluation unit can consider customer attribute information when evaluating the customer service skills of crew members. For example, the evaluation unit can evaluate the customer's customer service skills by considering the customer's age. It can also evaluate the customer's customer service skills by considering the customer's gender. Furthermore, the evaluation unit can evaluate the customer's customer service skills by considering the customer's purchase history. This allows for a more appropriate evaluation by considering customer attribute information. Some or all of the above processes in the evaluation unit may be performed using AI or not. For example, in order to perform an evaluation that takes customer attribute information into consideration, the evaluation unit can use AI to analyze customer attribute information and reflect it in the evaluation.

[0075] The evaluation unit can analyze background and ambient noise during customer service and incorporate this analysis into the evaluation of the crew's customer service skills. For example, if the background noise is loud, the evaluation unit can assess how easily the crew's voice can be heard. Furthermore, if the ambient noise is quiet, the evaluation unit can also assess the tone of the crew's voice. In addition, the evaluation unit can analyze background and ambient noise to evaluate the crew's customer service skills. This allows for a more accurate evaluation by analyzing background and ambient noise. Some or all of the above processing in the evaluation unit may be performed using AI, or not. For example, the evaluation unit can use AI to analyze background and ambient noise during customer service and incorporate this analysis into the evaluation.

[0076] The feedback unit can estimate the crew's emotions and adjust the way feedback is expressed based on the estimated emotions. For example, if a crew member is tense, the feedback unit can provide feedback in gentle terms. It can also provide detailed feedback if the crew member is relaxed. Furthermore, if the crew member is tired, the feedback unit can provide concise feedback. This allows for more effective feedback by adjusting the expression of feedback based on the crew member's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to analyze the crew member's emotions and adjust the expression of feedback based on the estimated emotions.

[0077] The feedback unit can, during the feedback process, refer to the crew's past improvement history to suggest specific areas for improvement. For example, the feedback unit can suggest specific areas for improvement based on the crew's past improvement history. The feedback unit can also analyze the crew's past improvement history and propose areas for improvement. Furthermore, the feedback unit can refer to the crew's past improvement history to check the progress of improvements. This allows for the suggestion of more specific areas for improvement by referring to past improvement history. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to analyze past improvement history in order to suggest specific areas for improvement by referring to the crew's past improvement history.

[0078] The feedback unit can provide an indicator that quantitatively shows the degree of improvement in the crew's customer service skills during the feedback process. For example, the feedback unit can show the degree of improvement in the crew's customer service skills as a score. It can also show the degree of improvement in the crew's customer service skills as a graph. Furthermore, the feedback unit can show the degree of improvement in the crew's customer service skills as a numerical value. This quantitatively shows the degree of improvement in customer service skills, thereby improving the crew's motivation. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, in order to provide an indicator that quantitatively shows the degree of improvement in the crew's customer service skills, the feedback unit can use AI to analyze the degree of improvement in the crew's customer service skills and provide an indicator that quantitatively shows it.

[0079] The feedback unit can estimate the crew's emotions and adjust the timing of feedback based on the estimated emotions. For example, if the crew is tense, the feedback unit may delay the timing of feedback. Conversely, if the crew is relaxed, the feedback unit may speed up the timing of feedback. Furthermore, if the crew is tired, the feedback unit may adjust the timing of feedback. This allows for more effective feedback by adjusting the timing of feedback based on the crew's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to analyze the crew's emotions and adjust the timing of feedback in order to estimate the crew's emotions and adjust the timing of feedback based on the estimated emotions.

[0080] The feedback unit can select the optimal feedback method by considering the crew's attribute information during the feedback process. For example, the feedback unit can select the optimal feedback method by considering the crew's age. It can also select the optimal feedback method by considering the crew's gender. Furthermore, the feedback unit can select the optimal feedback method by considering the crew's years of experience. This allows for more appropriate feedback by considering the crew's attribute information. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to analyze the crew's attribute information and select the optimal feedback method in order to consider the crew's attribute information.

[0081] The feedback department can provide training content to help improve the crew's customer service skills during the feedback process. For example, the feedback department can provide video training to help improve the crew's customer service skills. It can also provide online courses to help improve the crew's customer service skills. Furthermore, the feedback department can provide workshops to help improve the crew's customer service skills. In this way, providing training content promotes the improvement of the crew's customer service skills. Some or all of the above processes in the feedback department may be performed using AI or not. For example, the feedback department can use AI to analyze the crew's skill level and select appropriate training content to provide training content that helps improve the crew's customer service skills.

[0082] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0083] The customer service skills evaluation system can improve the accuracy of its evaluations by referring to the crew's past customer service history when assessing their customer service skills. For example, the evaluation unit evaluates the crew's current customer service skills based on their past customer service history. The evaluation unit can also analyze past customer service history and adjust the evaluation criteria. Furthermore, the evaluation unit can refer to past customer service history to maintain consistency in evaluations. This improves the accuracy of evaluations by referring to past customer service history. Some or all of the above processes in the evaluation unit may be performed using AI or not. For example, the evaluation unit can use AI to analyze past customer service history in order to improve the accuracy of evaluations by referring to past customer service history.

[0084] The customer service skills evaluation system can analyze customer reactions in real time and incorporate them into the evaluation when assessing the customer service skills of crew members. For example, the evaluation unit can analyze the customer's facial expressions to evaluate the crew's customer service skills. The evaluation unit can also analyze the customer's tone of voice to evaluate the crew's customer service skills. Furthermore, the evaluation unit can analyze the customer's gestures to evaluate the crew's customer service skills. This allows for more accurate evaluation by analyzing customer reactions in real time. Some or all of the above processes in the evaluation unit may be performed using AI or not. For example, the evaluation unit can use AI to analyze customer reactions in real time and incorporate them into the evaluation.

[0085] The customer service skills evaluation system can analyze background and ambient noise during customer service and incorporate this analysis into the evaluation. For example, if the background noise is loud, the evaluation unit can assess how easily the crew member's voice can be heard. The evaluation unit can also assess the tone of the crew member's voice if the ambient noise is quiet. Furthermore, the evaluation unit can analyze background and ambient noise to evaluate the crew member's customer service skills. This allows for a more accurate evaluation by analyzing background and ambient noise. Some or all of the above processing in the evaluation unit may be performed using AI, or not. For example, the evaluation unit can use AI to analyze background and ambient noise during customer service and incorporate this analysis into the evaluation.

[0086] The customer service skills evaluation system can evaluate crew members' customer service skills while taking customer attribute information into consideration. For example, the evaluation unit can evaluate crew members' customer service skills while considering the customer's age. The evaluation unit can also evaluate crew members' customer service skills while considering the customer's gender. Furthermore, the evaluation unit can evaluate crew members' customer service skills while considering the customer's purchase history. This allows for a more appropriate evaluation by considering customer attribute information. Some or all of the above processing in the evaluation unit may be performed using AI or not. For example, in order to perform an evaluation while considering customer attribute information, the evaluation unit can use AI to analyze customer attribute information and reflect it in the evaluation.

[0087] A customer service skills evaluation system can improve the accuracy of evaluations by referring to past evaluation data when assessing the customer service skills of crew members. For example, the evaluation unit evaluates the customer service skills of crew members based on past evaluation data. The evaluation unit can also analyze past evaluation data and adjust the evaluation criteria. Furthermore, the evaluation unit can refer to past evaluation data to maintain consistency in evaluations. This improves the accuracy of evaluations by referring to past evaluation data. Some or all of the above processes in the evaluation unit may be performed using AI or not. For example, the evaluation unit can use AI to analyze past evaluation data in order to improve the accuracy of evaluations by referring to past evaluation data.

[0088] The customer service skills evaluation system can estimate the crew's emotions and adjust the evaluation criteria based on those estimated emotions. For example, the evaluation unit can relax the evaluation criteria if the crew is tense. Conversely, it can tighten the evaluation criteria if the crew is relaxed. Furthermore, it can adjust the evaluation criteria if the crew is tired. This allows for more appropriate evaluations by adjusting the evaluation criteria based on the crew's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using AI or not. For example, the evaluation unit can use AI to analyze the crew's emotions and adjust the evaluation criteria in order to estimate the crew's emotions and adjust the evaluation criteria based on those estimated emotions.

[0089] The customer service skills evaluation system can estimate the crew's emotions and adjust how the evaluation results are displayed based on the estimated emotions. For example, if the crew is tense, the evaluation unit will display the evaluation results simply. If the crew is relaxed, the evaluation unit can also display detailed evaluation results. Furthermore, if the crew is tired, the evaluation unit can adjust the display of the evaluation results. This allows for more appropriate feedback by adjusting how the evaluation results are displayed based on the crew's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using AI or not. For example, the evaluation unit can use AI to analyze the crew's emotions and adjust how the evaluation results are displayed in order to estimate the crew's emotions and adjust how the evaluation results are displayed based on the estimated emotions.

[0090] The customer service skills evaluation system can estimate the crew's emotions and adjust the way feedback is expressed based on those emotions. For example, if a crew member is tense, the feedback unit can provide gentle feedback. If the crew member is relaxed, the feedback unit can provide more detailed feedback. Furthermore, if the crew member is tired, the feedback unit can provide concise feedback. This allows for more effective feedback by adjusting the expression of feedback based on the crew member's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to analyze the crew member's emotions and adjust the way feedback is expressed in order to estimate the crew member's emotions and adjust the expression of feedback based on those emotions.

[0091] The customer service skills evaluation system can estimate the crew's emotions and adjust the timing of feedback based on those emotions. For example, the feedback unit can delay the timing of feedback if the crew is tense. Conversely, it can also speed up the timing of feedback if the crew is relaxed. Furthermore, it can adjust the timing of feedback if the crew is tired. This allows for more effective feedback by adjusting the timing of feedback based on the crew's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to analyze the crew's emotions and adjust the timing of feedback based on those estimated emotions.

[0092] The customer service skills evaluation system can estimate the emotions of crew members and select training data based on those estimated emotions. For example, if a crew member is feeling stressed, the training unit can prioritize training on relaxing customer service examples. If a crew member is highly motivated, the training unit can also train on challenging customer service examples. Furthermore, if a crew member is tired, the training unit can train on simple and effective customer service examples. This allows for more effective learning by selecting training data based on the crew member's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the training unit may be performed using AI or not. For example, the training unit can use AI to analyze the crew member's emotions and select training data in order to estimate their emotions and select training data based on those estimated emotions.

[0093] The following briefly describes the processing flow for example form 2.

[0094] Step 1: The learning unit learns the know-how of high-productivity crew members. For example, it analyzes customer service examples and talk scripts of high-productivity crew members to learn effective customer service methods. The learning unit can also use AI to analyze customer service examples of high-productivity crew members and learn effective customer service methods. Step 2: The evaluation unit evaluates the crew's customer service skills based on the know-how learned by the learning unit. For example, it analyzes and evaluates the content of customer service in real time as the crew actually provides service. The evaluation criteria are set based on the know-how of high-productivity crew members. The evaluation unit can use AI to analyze and evaluate the crew's customer service. Step 3: The Feedback Department provides feedback on areas for improvement in the crew's customer service skills based on the evaluation results from the Evaluation Department. For example, it provides specific feedback on which parts of the crew's communication are not effective and how they should improve. The Feedback Department can provide specific feedback on areas for improvement to the crew based on the results evaluated by the AI.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] Each of the multiple elements described above, including the learning unit, evaluation unit, and feedback unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the smart device 14 and analyzes customer service examples and talk scripts of highly productive crew members. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes and evaluates the customer service content of the crew members in real time. The feedback unit is implemented by the control unit 46A of the smart device 14 and provides specific feedback on areas for improvement to the crew members. 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.

[0099] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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).

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] Each of the multiple elements described above, including the learning unit, evaluation unit, and feedback unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the smart glasses 214 and analyzes customer service examples and talk scripts of highly productive crew members. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes and evaluates the customer service content of the crew members in real time. The feedback unit is implemented by the control unit 46A of the smart glasses 214 and provides specific feedback on areas for improvement to the crew members. 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.

[0115] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0116] 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.

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

[0118] The 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.

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

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

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

[0122] Figure 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.

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

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

[0125] In the 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.

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

[0127] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0129] The data processing system 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.

[0130] Each of the multiple elements described above, including the learning unit, evaluation unit, and feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the headset terminal 314 and analyzes customer service examples and talk scripts of highly productive crew members. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes and evaluates the customer service content of the crew members in real time. The feedback unit is implemented by the control unit 46A of the headset terminal 314 and provides specific feedback on areas for improvement to the crew members. 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.

[0131] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0132] 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.

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

[0134] The 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.

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

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS 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).

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

[0138] 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.

[0139] 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.

[0140] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0141] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0142] In 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.

[0143] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0144] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0145] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0146] The data processing system 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.

[0147] Each of the multiple elements, including the learning unit, evaluation unit, and feedback unit described above, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the robot 414 and analyzes customer service examples and talk scripts of high-productivity crew members. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes and evaluates the customer service content of the crew members in real time. The feedback unit is implemented by the control unit 46A of the robot 414 and provides specific feedback on areas for improvement to the crew members. 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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."

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] (Note 1) A learning department where you can learn the know-how of highly productive crews, An evaluation unit that evaluates the customer service skills of the crew based on the know-how learned by the aforementioned learning unit, The system includes a feedback unit that provides feedback on areas for improvement in the crew's customer service skills based on the results evaluated by the aforementioned evaluation unit. A system characterized by the following features. (Note 2) The evaluation unit, Evaluate crew members' customer service skills in real time. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned feedback unit is Provide specific areas for improvement. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned learning unit, We will analyze customer service examples and talk scripts from highly productive crew members to learn effective customer service methods. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, The system estimates the emotions of the crew and selects training data based on the estimated emotions of the crew. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned learning unit, By analyzing customer service examples from highly productive crew members by time of day, we can learn effective customer service methods for each time slot. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, The system analyzes the customer service scripts of highly productive crew members via voice analysis to learn their voice tone and speaking patterns. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, The system estimates the crew's emotions and adjusts the learning frequency based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, We will analyze examples of customer service provided by highly productive crew members by region to learn effective customer service methods specific to each area. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, Visually analyze the customer service scripts of highly productive crew members to learn their gesture and facial expression patterns. The system described in Appendix 1, characterized by the features described herein. (Note 11) The evaluation unit, The system estimates the crew's emotions and adjusts the evaluation criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The evaluation unit, When evaluating crew members' customer service skills, customer reactions are analyzed in real time and reflected in the evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 13) The evaluation unit, When evaluating crew members' customer service skills, we refer to past evaluation data to improve the accuracy of the evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 14) The evaluation unit, The system estimates the crew's emotions and adjusts how the evaluation results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The evaluation unit, When evaluating the customer service skills of crew members, the evaluation should take into account customer attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The evaluation unit, When evaluating the customer service skills of crew members, the background sounds and ambient noises during customer service will be analyzed and incorporated into the evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned feedback unit is The system estimates the crew's emotions and adjusts how feedback is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned feedback unit is When providing feedback, refer to the crew's past improvement history to suggest specific areas for improvement. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned feedback unit is During feedback, provide metrics that quantitatively show the degree of improvement in the crew's customer service skills. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned feedback unit is The system estimates the crew's emotions and adjusts the timing of feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned feedback unit is When providing feedback, the optimal feedback method will be selected by considering the crew's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned feedback unit is During feedback sessions, we provide training content that helps improve the crew's customer service skills. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0167] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A learning department where you can learn the know-how of highly productive crews, An evaluation unit that evaluates the customer service skills of the crew based on the know-how learned by the aforementioned learning unit, The system includes a feedback unit that provides feedback on areas for improvement in the crew's customer service skills based on the results evaluated by the aforementioned evaluation unit. A system characterized by the following features.

2. The evaluation unit, Evaluate crew members' customer service skills in real time. The system according to feature 1.

3. The aforementioned feedback unit is Provide specific areas for improvement. The system according to feature 1.

4. The aforementioned learning unit, We will analyze customer service examples and talk scripts from highly productive crew members to learn effective customer service methods. The system according to feature 1.

5. The aforementioned learning unit, The system estimates the emotions of the crew and selects training data based on the estimated emotions of the crew. The system according to feature 1.

6. The aforementioned learning unit, By analyzing customer service examples from highly productive crew members by time of day, we can learn effective customer service methods for each time slot. The system according to feature 1.

7. The aforementioned learning unit, The system analyzes the customer service scripts of highly productive crew members via voice analysis to learn their voice tone and speaking patterns. The system according to feature 1.

8. The aforementioned learning unit, The system estimates the crew's emotions and adjusts the learning frequency based on the estimated emotions. The system according to feature 1.

9. The aforementioned learning unit, We will analyze examples of customer service provided by highly productive crew members by region to learn effective customer service methods specific to each area. The system according to feature 1.

10. The aforementioned learning unit, Visually analyze the customer service scripts of highly productive crew members to learn their gesture and facial expression patterns. The system according to feature 1.

Images