System

Abstract

An object of a system according to an embodiment is to appropriately manage customer satisfaction and improve overall service quality.SOLUTION: A system includes a customer satisfaction scoring unit, a store evaluation management unit, and a crew training support unit. The customer satisfaction scorer analyzes the customer feedback to score customer satisfaction. The store evaluation management unit manages the evaluation of each store using the customer satisfaction scored by the customer satisfaction scoring unit. The crew training support unit trains and supports the crew based on the evaluation managed by the store evaluation management unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, the management of customer satisfaction tends to be left to the agents, making it difficult to raise the overall level of service quality.

[0005] The system according to the embodiment aims to appropriately manage customer satisfaction and improve overall service quality. [Means for solving the problem]

[0006] The system according to the embodiment includes a customer satisfaction scoring unit, a store evaluation management unit, and a crew training support unit. The customer satisfaction scoring unit analyzes customer feedback and scores customer satisfaction. The store evaluation management unit manages the evaluation of each store using the customer satisfaction scored by the customer satisfaction scoring unit. The crew training support unit trains and supports crews based on the evaluations managed by the store evaluation management unit. [Effects of the Invention]

[0007] The system according to the embodiment can appropriately manage customer satisfaction and improve the overall service quality. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also 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. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The customer satisfaction improvement system according to the embodiment of the present invention is a system that scores customer satisfaction, manages the quality of customer service, and aims to raise the overall level. As a result, the customer satisfaction improvement system can improve customer satisfaction.

[0029] A customer satisfaction improvement system according to an embodiment includes a customer satisfaction scoring unit, a store evaluation management unit, and a crew training support unit. The customer satisfaction scoring unit analyzes customer feedback and scores customer satisfaction. For example, a generation AI analyzes customer responses to a questionnaire and assigns scores for each category, such as "customer service attitude," "waiting time," and "store cleanliness." The customer satisfaction scoring unit generates scores based on the customer feedback. For example, the generation AI analyzes the feedback using a text generation AI (e.g., LLM) and calculates a score. The store evaluation management unit manages the evaluation of each store using the customer satisfaction scores scored by the customer satisfaction scoring unit. For example, the generation AI compares the scores of each store and suggests improvements to stores with low ratings. The store evaluation management unit analyzes best practices of stores with high ratings and shares them with other stores. For example, the generation AI analyzes the customer service methods used by highly rated stores and provides this information to other stores. The crew training support unit trains and supports crew members based on the evaluations managed by the store evaluation management unit. For example, a training program is provided to improve the customer service attitude of crew members at stores with low ratings. Furthermore, the Crew Training Support Unit uses the generation AI to evaluate the effectiveness of crew training and suggest further improvements. For example, the system evaluates the effectiveness of crew training and suggests additional training. This allows the customer satisfaction improvement system according to the embodiment to improve customer satisfaction. For example, by incorporating customer feedback in real time, a quick response is possible, improving customer satisfaction. Furthermore, strengthening crew training and support can raise the overall customer service quality. Furthermore, by sharing best practices between stores, the overall service level can be standardized, improving customer satisfaction.

[0030] The customer satisfaction scoring unit can refer to the customer's feedback history and calculate a score taking into account long-term fluctuations in satisfaction. The customer satisfaction scoring unit, for example, refers to the customer's past feedback history and calculates a score taking into account long-term fluctuations in satisfaction. For example, it places emphasis on feedback from customers who have repeatedly given high ratings in the past. In addition, the customer satisfaction scoring unit uses a generation AI to analyze the customer's feedback history and grasp trends. For example, it analyzes how customer satisfaction fluctuates over time and reflects the results in the score. This makes it possible to perform scoring that takes into account long-term fluctuations in customer satisfaction.

[0031] The customer satisfaction scoring unit can analyze multimodal data, including audio feedback and video feedback, to score customer satisfaction. For example, when scoring customer satisfaction, the customer satisfaction scoring unit analyzes audio feedback and evaluates emotions and content. For example, if a customer says "very satisfied" in audio, the audio data is analyzed and a score is assigned. The customer satisfaction scoring unit also analyzes video feedback and evaluates the customer's facial expressions and gestures. For example, the facial expression when a customer says "satisfied" in a video is analyzed and reflected in the score. Furthermore, the customer satisfaction scoring unit can also analyze text data, audio data, and video data in an integrated manner. For example, the entire customer feedback is comprehensively evaluated and a score is calculated. This makes it possible to analyze multimodal data including audio and video feedback.

[0032] The customer satisfaction scoring unit can refer to customer satisfaction scoring systems in different industries and introduce new scoring criteria that can be applied to the telecommunications industry. For example, the customer satisfaction scoring unit investigates customer satisfaction scoring systems in different industries and introduces new scoring criteria that can be applied to the telecommunications industry. For example, it refers to the scoring criteria of the hotel industry. In addition, the customer satisfaction scoring unit uses the generation AI to analyze best practices from different industries and apply them to the telecommunications industry. For example, it refers to the customer satisfaction scoring system of the food and beverage industry and applies it to the telecommunications industry. This makes it possible to create scores that incorporate best practices from different industries.

[0033] The store evaluation management unit can adjust the evaluation criteria by taking into account the geographical conditions of the store and the characteristics of the customer demographic. The store evaluation management unit adjusts the evaluation criteria by taking into account the geographical conditions of the store, for example. For example, different evaluation criteria are set for stores in urban and rural areas. The store evaluation management unit also adjusts the evaluation criteria by taking into account the characteristics of the customer demographic. For example, evaluation criteria are set based on age groups and purchasing behavior. Furthermore, the store evaluation management unit uses a generation AI to analyze the geographical conditions and the characteristics of the customer demographic and introduce the optimal evaluation criteria. For example, evaluation criteria are set for young people in urban areas. This makes it possible to adjust the evaluation criteria by taking into account the geographical conditions and the characteristics of the customer demographic.

[0034] The store evaluation management unit can integrate the evaluations of each store with data from other telecommunications industries to create benchmarks for the entire industry. For example, the store evaluation management unit can integrate the evaluations of each store with data from other telecommunications industries to create benchmarks for the entire industry. For example, it can collect store evaluation data from other companies and perform comparative analysis. In addition, the store evaluation management unit uses the generation AI to create benchmarks for the entire industry and evaluate the evaluations of each store relatively. For example, it can evaluate each store in comparison with the industry average. Furthermore, the store evaluation management unit uses the generation AI to suggest areas for improvement based on the benchmark data. For example, it can identify areas for improvement by comparing with the top store in the industry. This makes it possible to create benchmarks for the entire industry.

[0035] The store reputation management department can refer to reputation management systems from different industries and introduce new reputation management methods that can be applied to the telecommunications industry. For example, the store reputation management department refers to reputation management systems from different industries and introduces new reputation management methods that can be applied to the telecommunications industry. For example, it refers to reputation management systems from the hotel industry. In addition, the store reputation management department uses generative AI to analyze best practices from different industries and apply them to the telecommunications industry. For example, it refers to reputation management methods from the manufacturing industry and applies them to the telecommunications industry. This makes it possible to manage reputations by incorporating best practices from different industries.

[0036] The Crew Training Support Department can analyze past training history and fluctuations in customer satisfaction in crew training and propose optimal training content. For example, the Crew Training Support Department can analyze a crew's past training history and fluctuations in customer satisfaction and propose optimal training content. For example, it can re-implement training content that has received high praise in the past. The Crew Training Support Department also uses generative AI to analyze training history and optimize training programs. For example, it can customize training content based on specific skill sets. This makes it possible to propose optimal training content that takes into account past training history and fluctuations in customer satisfaction.

[0037] The Crew Training Support Department can incorporate best practices from different industries into crew training programs and introduce new training methods that are applicable to the telecommunications industry. For example, the Crew Training Support Department incorporates best practices from different industries and introduces new training methods that are applicable to the telecommunications industry. For example, it uses customer service training methods from the hotel industry as reference. The Crew Training Support Department also uses generative AI to analyze training methods from different industries and apply them to the telecommunications industry. For example, it uses training methods from the manufacturing industry as reference and applies them to the telecommunications industry. This makes it possible to introduce new training methods that incorporate best practices from different industries.

[0038] The crew training support department can integrate the effectiveness of crew training with other data sets (e.g., customer satisfaction data and performance data) and comprehensively evaluate it. The crew training support department, for example, integrates the effectiveness of crew training with customer satisfaction data and comprehensively evaluates it. For example, it analyzes changes in customer satisfaction after training. In addition, in the crew training support department, the generation AI analyzes performance data and evaluates the training effectiveness. For example, it analyzes changes in sales after training. In addition, in the crew training support department, the generation AI integrates multiple data sets and performs a comprehensive evaluation. For example, it integrates customer satisfaction data and performance data for evaluation. This makes it possible to integrate the training effectiveness with other data sets and comprehensively evaluate it.

[0039] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0040] The customer satisfaction improvement system can further analyze customer purchasing history and provide personalized services to individual customers. For example, it can suggest related new products and services based on products and services that the customer has purchased in the past. The customer satisfaction scoring unit can also analyze customer purchasing history and evaluate satisfaction with specific products and services. For example, it can analyze feedback from customers who have purchased a specific product and score their satisfaction with that product. Furthermore, the store evaluation management unit can optimize the sales strategy of each store based on customer purchasing history. For example, it can suggest to stores that are selling a particular product that they should focus on promoting that product. This makes it possible to provide personalized services that utilize customer purchasing history.

[0041] The customer satisfaction improvement system can further optimize store layout and design based on customer feedback. For example, if a customer provides feedback that "the store layout is difficult to understand," the system makes suggestions to improve the layout based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on the store layout and design and generate a satisfaction score. For example, if a customer provides feedback that "the store design is great," the system analyzes that feedback and generates a satisfaction score. The store evaluation management unit can further optimize the evaluation of each store based on feedback on the store layout and design. For example, if the layout of a particular store is highly rated, the system can make suggestions to introduce that layout to other stores. This makes it possible to improve customer satisfaction by optimizing store layout and design.

[0042] The customer satisfaction improvement system can further optimize store business hours based on customer feedback. For example, if a customer provides feedback that the business hours are "short," a proposal to extend the business hours is made based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on store business hours and generate a satisfaction score. For example, if a customer provides feedback that the business hours are "long and convenient," the feedback is analyzed and a satisfaction score is generated. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on store business hours. For example, if the business hours of a particular store are highly rated, a proposal can be made to introduce those business hours to other stores. This makes it possible to improve customer satisfaction by optimizing store business hours.

[0043] The customer satisfaction improvement system can further optimize a store's promotion strategy based on customer feedback. For example, if a customer provides feedback that "the promotion is not attractive," the system makes suggestions to improve the promotion strategy based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on the promotion strategy and generate a satisfaction score. For example, if a customer provides feedback that "the promotion is great," the system analyzes that feedback and generates a satisfaction score. The store evaluation management unit can further optimize the evaluation of each store based on feedback on the promotion strategy. For example, if a particular promotion is highly rated, the system can make suggestions to introduce that promotion to other stores as well. This makes it possible to improve customer satisfaction by optimizing the promotion strategy.

[0044] The customer satisfaction improvement system can further optimize store staff allocation based on customer feedback. For example, if a customer provides feedback that "there are not enough staff," a proposal to increase staff allocation is made based on that feedback. The customer satisfaction scoring unit can also analyze customer feedback on staff allocation and generate a satisfaction score. For example, if a customer provides feedback that "there are many staff members and they respond quickly," the feedback can be analyzed and a satisfaction score generated. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on staff allocation. For example, if the staff allocation of a particular store is highly rated, a proposal can be made to introduce that allocation to other stores. This makes it possible to improve customer satisfaction by optimizing staff allocation.

[0045] The customer satisfaction improvement system can further optimize the service menu of a store based on customer feedback. For example, if a customer gives feedback that "the service menu is limited," a proposal to expand the service menu is made based on that feedback. The customer satisfaction scoring unit can also analyze customer feedback on the service menu and score the satisfaction level. For example, if a customer gives feedback that "the service menu is extensive and I'm satisfied," the feedback is analyzed and a satisfaction level is scored. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on the service menu. For example, if a specific service menu is highly rated, a proposal is made to introduce that menu in other stores as well. This makes it possible to improve customer satisfaction by optimizing the service menu.

[0046] The customer satisfaction improvement system can further optimize waiting times at stores based on customer feedback. For example, if a customer provides feedback that the waiting time is long, the system makes suggestions to shorten the waiting time based on that feedback. The customer satisfaction scoring unit can also analyze customer feedback on waiting times and generate a score for satisfaction. For example, if a customer provides feedback that the waiting time is short and comfortable, the system can analyze that feedback and generate a score for satisfaction. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on waiting times. For example, if the waiting time at a particular store is highly rated, the system can make suggestions to introduce that waiting time at other stores. This makes it possible to improve customer satisfaction by optimizing waiting times.

[0047] The customer satisfaction improvement system can further optimize a store's customer service attitude based on customer feedback. For example, if a customer provides feedback that the customer service attitude is "bad," the system makes suggestions to improve the customer service attitude based on that feedback. The customer satisfaction scoring unit can also analyze customer feedback on the customer service attitude and generate a satisfaction score. For example, if a customer provides feedback that the customer service attitude is "excellent," the system analyzes that feedback and generates a satisfaction score. The store evaluation management unit can also optimize the evaluation of each store based on feedback on the customer service attitude. For example, if the customer service attitude of a particular store is highly rated, the system can make suggestions to introduce that customer service attitude to other stores. This makes it possible to improve customer satisfaction by optimizing the customer service attitude.

[0048] The customer satisfaction improvement system can further optimize store cleanliness based on customer feedback. For example, if a customer provides feedback that "the store is dirty," a suggestion to increase cleaning frequency is made based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on store cleanliness and score satisfaction. For example, if a customer provides feedback that "the store is clean and comfortable," that feedback is analyzed and a satisfaction score is made. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on store cleanliness. For example, if the cleanliness of a particular store is highly rated, a suggestion is made to introduce that cleanliness to other stores. This makes it possible to improve customer satisfaction by optimizing store cleanliness.

[0049] The customer satisfaction improvement system can further optimize the store atmosphere based on customer feedback. For example, if a customer provides feedback that "the store atmosphere is bad," the system makes suggestions to improve the atmosphere based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on the store atmosphere and generate a satisfaction score. For example, if a customer provides feedback that "the store atmosphere is great," the system analyzes that feedback and generates a satisfaction score. The store evaluation management unit can further optimize the evaluation of each store based on feedback on the store atmosphere. For example, if the atmosphere of a particular store is highly rated, the system can make suggestions to introduce that atmosphere to other stores. This makes it possible to improve customer satisfaction by optimizing the store atmosphere.

[0050] The customer satisfaction improvement system can further optimize the music and lighting in a store based on customer feedback. For example, if a customer gives feedback that "the music is too loud," the system makes a suggestion to adjust the music volume based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on music and lighting and generate a score for satisfaction. For example, if a customer gives feedback that "the lighting is bright and comfortable," the system analyzes that feedback and generates a score for satisfaction. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on music and lighting. For example, if the music and lighting in a particular store are highly rated, the system can make a suggestion to introduce those settings in other stores. This makes it possible to improve customer satisfaction by optimizing music and lighting.

[0051] The customer satisfaction improvement system can further optimize the music and lighting in a store based on customer feedback. For example, if a customer gives feedback that "the music is too loud," the system makes a suggestion to adjust the music volume based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on music and lighting and generate a score for satisfaction. For example, if a customer gives feedback that "the lighting is bright and comfortable," the system analyzes that feedback and generates a score for satisfaction. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on music and lighting. For example, if the music and lighting in a particular store are highly rated, the system can make a suggestion to introduce those settings in other stores. This makes it possible to improve customer satisfaction by optimizing music and lighting.

[0052] The customer satisfaction improvement system can further optimize store service times based on customer feedback. For example, if a customer provides feedback that "service times are long," the system makes a proposal to shorten service times based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on service times and generate a satisfaction score. For example, if a customer provides feedback that "service times are short and I'm satisfied," the system analyzes that feedback and generates a satisfaction score. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on service times. For example, if the service times of a particular store are highly rated, the system can propose introducing those times to other stores. This makes it possible to improve customer satisfaction by optimizing service times.

[0053] The customer satisfaction improvement system can further optimize the expertise of store staff based on customer feedback. For example, if a customer provides feedback that "the staff lacks knowledge," the system can make suggestions to strengthen staff training based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on staff expertise and generate a satisfaction score. For example, if a customer provides feedback that "the staff was very knowledgeable and helpful," the system can analyze that feedback and generate a satisfaction score. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on staff expertise. For example, if the expertise of staff at a particular store is highly rated, the system can make a suggestion to share that knowledge with other stores. This makes it possible to improve customer satisfaction by optimizing staff expertise.

[0054] The customer satisfaction improvement system can also monitor waiting times at stores in real time based on customer feedback and work to reduce waiting times. For example, if a customer provides feedback that the waiting time is long, the system can monitor waiting times in real time based on that feedback and make suggestions to adjust staff deployment. The customer satisfaction scoring unit can also analyze customer feedback on waiting times and generate a satisfaction score. For example, if a customer provides feedback that the waiting time is short and comfortable, the system can analyze that feedback and generate a satisfaction score. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on waiting times. For example, if the waiting time at a particular store is highly rated, the system can make suggestions to introduce that waiting time at other stores. This makes it possible to monitor and reduce waiting times in real time.

[0055] The customer satisfaction improvement system can further optimize the service provision process of a store based on customer feedback. For example, if a customer provides feedback that the "service provision process is complicated," the system can make suggestions to simplify the process based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on the service provision process and generate a satisfaction score. For example, if a customer provides feedback that the "service provision process was smooth and satisfying," the system can analyze that feedback and generate a satisfaction score. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on the service provision process. For example, if the service provision process of a particular store has received high evaluations, the system can make suggestions to introduce that process to other stores. This makes it possible to improve customer satisfaction by optimizing the service provision process.

[0056] The customer satisfaction improvement system can further optimize the communication skills of store staff based on customer feedback. For example, if a customer provides feedback that "the staff's communication is insufficient," the system makes suggestions to improve the staff's communication skills based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on the staff's communication skills and generate a satisfaction score. For example, if a customer provides feedback that "the staff's communication is good and I'm satisfied," the system analyzes that feedback and generates a satisfaction score. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on the staff's communication skills. For example, if the communication skills of the staff at a particular store are highly rated, the system can make a suggestion to share those skills with other stores. This makes it possible to improve customer satisfaction by optimizing the staff's communication skills.

[0057] The customer satisfaction improvement system can further optimize the motivation of store staff based on customer feedback. For example, if a customer provides feedback that "the staff's motivation is low," the system makes suggestions to improve staff motivation based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on staff motivation and generate a score for satisfaction. For example, if a customer provides feedback that "the staff's motivation is high and I'm satisfied," the system analyzes that feedback and generates a score for satisfaction. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on staff motivation. For example, if the staff motivation of a particular store is highly rated, the system can make a suggestion to share that motivation with other stores. This makes it possible to improve customer satisfaction by optimizing staff motivation.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The customer satisfaction scoring unit analyzes customer feedback and generates a score for customer satisfaction. For example, the generation AI analyzes the customer's responses to a questionnaire and assigns a score for each item, such as "customer service attitude," "waiting time," and "store cleanliness." The generation AI also uses a text generation AI (e.g., LLM) to analyze the feedback and calculate a score. Step 2: The store evaluation management department manages the evaluation of each store using the customer satisfaction scores generated by the customer satisfaction scoring department. For example, the generation AI compares the scores of each store and suggests improvements to stores with low ratings. It also analyzes best practices from stores with good ratings and shares them with other stores. Step 3: The Crew Training Support Department trains and supports crew members based on the evaluations managed by the Store Evaluation Management Department. For example, for crew members at stores with low evaluations, the department provides them with a training program to improve their customer service attitude. In addition, the generative AI evaluates the effectiveness of the crew members' training and suggests areas for further improvement.

[0060] (Example 2) The customer satisfaction improvement system according to the embodiment of the present invention is a system that scores customer satisfaction, manages the quality of customer service, and aims to raise the overall level. As a result, the customer satisfaction improvement system can improve customer satisfaction.

[0061] A customer satisfaction improvement system according to an embodiment includes a customer satisfaction scoring unit, a store evaluation management unit, and a crew training support unit. The customer satisfaction scoring unit analyzes customer feedback and scores customer satisfaction. For example, a generation AI analyzes customer responses to a questionnaire and assigns scores for each category, such as "customer service attitude," "waiting time," and "store cleanliness." The customer satisfaction scoring unit generates scores based on the customer feedback. For example, the generation AI analyzes the feedback using a text generation AI (e.g., LLM) and calculates a score. The store evaluation management unit manages the evaluation of each store using the customer satisfaction scores scored by the customer satisfaction scoring unit. For example, the generation AI compares the scores of each store and suggests improvements to stores with low ratings. The store evaluation management unit analyzes best practices of stores with high ratings and shares them with other stores. For example, the generation AI analyzes the customer service methods used by highly rated stores and provides this information to other stores. The crew training support unit trains and supports crew members based on the evaluations managed by the store evaluation management unit. For example, a training program is provided to improve the customer service attitude of crew members at stores with low ratings. Furthermore, the Crew Training Support Unit uses the generation AI to evaluate the effectiveness of crew training and suggest further improvements. For example, the system evaluates the effectiveness of crew training and suggests additional training. This allows the customer satisfaction improvement system according to the embodiment to improve customer satisfaction. For example, by incorporating customer feedback in real time, a quick response is possible, improving customer satisfaction. Furthermore, strengthening crew training and support can raise the overall customer service quality. Furthermore, by sharing best practices between stores, the overall service level can be standardized, improving customer satisfaction.

[0062] The customer satisfaction scoring unit can analyze the emotions contained in customer feedback and adjust the score based on the intensity and type of emotion. For example, the customer satisfaction scoring unit uses a generation AI to analyze the emotions contained in customer feedback and quantify the intensity and type of emotion. For example, if a customer responds "very satisfied," the intensity of that emotion is highly rated and reflected in the score. The customer satisfaction scoring unit also uses a generation AI to analyze the type of emotion and distinguish between positive and negative emotions. For example, feedback with strong positive emotions is assigned a high score, and feedback with strong negative emotions is assigned a low score. This makes it possible to perform scoring that takes customer emotions into consideration.

[0063] The customer satisfaction scoring unit can refer to the customer's feedback history and calculate a score taking into account long-term fluctuations in satisfaction. The customer satisfaction scoring unit, for example, refers to the customer's past feedback history and calculates a score taking into account long-term fluctuations in satisfaction. For example, it places emphasis on feedback from customers who have repeatedly given high ratings in the past. In addition, the customer satisfaction scoring unit uses a generation AI to analyze the customer's feedback history and grasp trends. For example, it analyzes how customer satisfaction fluctuates over time and reflects the results in the score. This makes it possible to perform scoring that takes into account long-term fluctuations in customer satisfaction.

[0064] The customer satisfaction scoring unit can use the generation AI's emotion estimation function to estimate customer emotions based on customer feedback and generate a score according to those emotions. For example, the customer satisfaction scoring unit can use the generation AI's emotion estimation function to estimate emotions from customer feedback and generate a score according to those emotions. For example, the generation AI can estimate positive emotions from feedback such as "very satisfied" and assign a high score. The generation AI can also estimate negative emotions and assign a low score. For example, the generation AI can estimate negative emotions from feedback such as "dissatisfied" and assign a low score. This makes it possible to perform scoring based on customer emotions.

[0065] The customer satisfaction scoring unit can analyze multimodal data, including audio feedback and video feedback, to score customer satisfaction. For example, when scoring customer satisfaction, the customer satisfaction scoring unit analyzes audio feedback and evaluates emotions and content. For example, if a customer says "very satisfied" in audio, the audio data is analyzed and a score is assigned. The customer satisfaction scoring unit also analyzes video feedback and evaluates the customer's facial expressions and gestures. For example, the facial expression when a customer says "satisfied" in a video is analyzed and reflected in the score. Furthermore, the customer satisfaction scoring unit can also analyze text data, audio data, and video data in an integrated manner. For example, the entire customer feedback is comprehensively evaluated and a score is calculated. This makes it possible to analyze multimodal data including audio and video feedback.

[0066] The customer satisfaction scoring unit can refer to customer satisfaction scoring systems in different industries and introduce new scoring criteria that can be applied to the telecommunications industry. For example, the customer satisfaction scoring unit investigates customer satisfaction scoring systems in different industries and introduces new scoring criteria that can be applied to the telecommunications industry. For example, it refers to the scoring criteria of the hotel industry. In addition, the customer satisfaction scoring unit uses the generation AI to analyze best practices from different industries and apply them to the telecommunications industry. For example, it refers to the customer satisfaction scoring system of the food and beverage industry and applies it to the telecommunications industry. This makes it possible to create scores that incorporate best practices from different industries.

[0067] The customer satisfaction scoring unit can use a generative AI to estimate a customer's emotions in real time and make suggestions that will elicit positive emotions when providing feedback. The customer satisfaction scoring unit, for example, uses a generative AI to estimate a customer's emotions in real time and make suggestions that will elicit positive emotions when providing feedback. For example, when a customer states that they are "satisfied," the unit makes suggestions to further elicit positive emotions. The customer satisfaction scoring unit also uses a generative AI to analyze a customer's emotions and promote positive feedback. For example, when a customer states that they are "very satisfied," the unit makes suggestions that will reinforce that emotion. This makes it possible to estimate a customer's emotions in real time and make suggestions that will elicit positive emotions.

[0068] The store evaluation management unit can use the generation AI to analyze customers' emotional responses to each store's evaluation and prioritize emotionally positive evaluations. For example, the store evaluation management unit can use the generation AI to analyze customers' emotional responses to each store's evaluation and prioritize evaluations that express strong positive emotions. For example, it can place emphasis on evaluations such as "very satisfied." The store evaluation management unit also uses the generation AI to analyze customers' emotional responses and appropriately handle evaluations that express strong negative emotions. For example, it can analyze evaluations that express "dissatisfied" and identify the cause. This makes it possible to prioritize emotionally positive evaluations.

[0069] The store evaluation management unit can adjust the evaluation criteria by taking into account the geographical conditions of the store and the characteristics of the customer demographic. The store evaluation management unit adjusts the evaluation criteria by taking into account the geographical conditions of the store, for example. For example, different evaluation criteria are set for stores in urban and rural areas. The store evaluation management unit also adjusts the evaluation criteria by taking into account the characteristics of the customer demographic. For example, evaluation criteria are set based on age groups and purchasing behavior. Furthermore, the store evaluation management unit uses a generation AI to analyze the geographical conditions and the characteristics of the customer demographic and introduce the optimal evaluation criteria. For example, evaluation criteria are set for young people in urban areas. This makes it possible to adjust the evaluation criteria by taking into account the geographical conditions and the characteristics of the customer demographic.

[0070] The store evaluation management unit can use the generation AI to make improvement proposals that are easy to empathize with emotionally for stores with low ratings. For example, the generation AI in the store evaluation management unit uses an emotion estimation function to make improvement proposals that are easy to empathize with emotionally for stores with low ratings. For example, it may suggest that "improvement in customer service attitudes is necessary." In addition, the store evaluation management unit uses the generation AI to analyze the causes of low ratings and propose specific improvement measures. For example, it may suggest that "waiting times need to be shortened." This makes it possible to make improvement proposals that are easy to empathize with emotionally.

[0071] The store evaluation management unit can integrate the evaluations of each store with data from other telecommunications industries to create benchmarks for the entire industry. For example, the store evaluation management unit can integrate the evaluations of each store with data from other telecommunications industries to create benchmarks for the entire industry. For example, it can collect store evaluation data from other companies and perform comparative analysis. In addition, the store evaluation management unit uses the generation AI to create benchmarks for the entire industry and evaluate the evaluations of each store relatively. For example, it can evaluate each store in comparison with the industry average. Furthermore, the store evaluation management unit uses the generation AI to suggest areas for improvement based on the benchmark data. For example, it can identify areas for improvement by comparing with the top store in the industry. This makes it possible to create benchmarks for the entire industry.

[0072] The store reputation management department can refer to reputation management systems from different industries and introduce new reputation management methods that can be applied to the telecommunications industry. For example, the store reputation management department refers to reputation management systems from different industries and introduces new reputation management methods that can be applied to the telecommunications industry. For example, it refers to reputation management systems from the hotel industry. In addition, the store reputation management department uses generative AI to analyze best practices from different industries and apply them to the telecommunications industry. For example, it refers to reputation management methods from the manufacturing industry and applies them to the telecommunications industry. This makes it possible to manage reputations by incorporating best practices from different industries.

[0073] The store evaluation management department uses generative AI to monitor customers' emotional reactions to the evaluations of each store in real time and can make prompt improvement suggestions. The store evaluation management department, for example, uses generative AI to monitor customers' emotional reactions to the evaluations of each store in real time and can make prompt improvement suggestions. For example, it can instantly analyze feedback such as "long waiting times" and make improvement suggestions. The store evaluation management department also uses generative AI to analyze customers' emotional reactions and propose appropriate improvement measures. For example, it can propose that "improvements to customer service attitude are necessary." This makes it possible to monitor customers' emotional reactions in real time and make prompt improvement suggestions.

[0074] The crew training support unit can use the generative AI to evaluate the effectiveness of the crew's training with an emotion estimation function and provide a training program that elicits a positive emotional response. The crew training support unit, for example, uses the generative AI to evaluate the effectiveness of the crew's training with an emotion estimation function and provide a training program that elicits a positive emotional response. For example, if the crew shows positive emotions during training, the training content is strengthened. The crew training support unit also uses the generative AI to analyze the crew's emotional responses and adjust the training program. For example, if the crew shows negative emotions, the training content is changed. This makes it possible to provide a training program that elicits a positive emotional response.

[0075] The Crew Training Support Department can analyze past training history and fluctuations in customer satisfaction in crew training and propose optimal training content. For example, the Crew Training Support Department can analyze a crew's past training history and fluctuations in customer satisfaction and propose optimal training content. For example, it can re-implement training content that has received high praise in the past. The Crew Training Support Department also uses generative AI to analyze training history and optimize training programs. For example, it can customize training content based on specific skill sets. This makes it possible to propose optimal training content that takes into account past training history and fluctuations in customer satisfaction.

[0076] The Crew Training Support Department uses the emotion estimation function of the generation AI to evaluate the emotions of the crew after training and propose further areas for improvement. For example, the Crew Training Support Department uses the emotion estimation function to evaluate the emotions of the crew after training and proposes areas for improvement. For example, if the crew shows positive emotions after training, the training content will be strengthened. The Crew Training Support Department also uses the generation AI to analyze the emotions after training and adjust the training program. For example, if the crew shows negative emotions, the training content will be changed. This makes it possible to propose areas for improvement based on the emotional evaluation after training.

[0077] The Crew Training Support Department can incorporate best practices from different industries into crew training programs and introduce new training methods that are applicable to the telecommunications industry. For example, the Crew Training Support Department incorporates best practices from different industries and introduces new training methods that are applicable to the telecommunications industry. For example, it uses customer service training methods from the hotel industry as reference. The Crew Training Support Department also uses generative AI to analyze training methods from different industries and apply them to the telecommunications industry. For example, it uses training methods from the manufacturing industry as reference and applies them to the telecommunications industry. This makes it possible to introduce new training methods that incorporate best practices from different industries.

[0078] The crew training support department can integrate the effectiveness of crew training with other data sets (e.g., customer satisfaction data and performance data) and comprehensively evaluate it. The crew training support department, for example, integrates the effectiveness of crew training with customer satisfaction data and comprehensively evaluates it. For example, it analyzes changes in customer satisfaction after training. In addition, in the crew training support department, the generation AI analyzes performance data and evaluates the training effectiveness. For example, it analyzes changes in sales after training. In addition, in the crew training support department, the generation AI integrates multiple data sets and performs a comprehensive evaluation. For example, it integrates customer satisfaction data and performance data for evaluation. This makes it possible to integrate the training effectiveness with other data sets and comprehensively evaluate it.

[0079] The Crew Training Support Department uses generative AI to monitor crew emotional responses during training in real time and instantly adjust the training content. The Crew Training Support Department, for example, uses generative AI to monitor crew emotional responses during training in real time and instantly adjust the training content. For example, if a crew member shows negative emotions, the training content is changed. The Crew Training Support Department also uses generative AI to analyze the crew's emotional responses and optimize the training program. For example, if a crew member shows positive emotions, the training content is reinforced. This makes it possible to monitor emotional responses during training in real time and instantly adjust the training content.

[0080] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0081] The customer satisfaction improvement system can further analyze customer purchasing history and provide personalized services to individual customers. For example, it can suggest related new products and services based on products and services that the customer has purchased in the past. The customer satisfaction scoring unit can also analyze customer purchasing history and evaluate satisfaction with specific products and services. For example, it can analyze feedback from customers who have purchased a specific product and score their satisfaction with that product. Furthermore, the store evaluation management unit can optimize the sales strategy of each store based on customer purchasing history. For example, it can suggest to stores that are selling a particular product that they should focus on promoting that product. This makes it possible to provide personalized services that utilize customer purchasing history.

[0082] The customer satisfaction improvement system can also analyze customers' social media activity to understand their interests. For example, it can analyze posts that customers have "liked" or "shared" on social media and identify their interests based on the content. The customer satisfaction scoring unit can also score customer satisfaction based on social media activity. For example, if a customer posts positively about a particular brand or product, the post is analyzed to score the satisfaction. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on social media activity. For example, if there are many positive posts about a particular store, the evaluation of that store can be increased. This makes it possible to improve customer satisfaction by utilizing social media activity.

[0083] The customer satisfaction improvement system can further optimize store layout and design based on customer feedback. For example, if a customer provides feedback that "the store layout is difficult to understand," the system makes suggestions to improve the layout based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on the store layout and design and generate a satisfaction score. For example, if a customer provides feedback that "the store design is great," the system analyzes that feedback and generates a satisfaction score. The store evaluation management unit can further optimize the evaluation of each store based on feedback on the store layout and design. For example, if the layout of a particular store is highly rated, the system can make suggestions to introduce that layout to other stores. This makes it possible to improve customer satisfaction by optimizing store layout and design.

[0084] The customer satisfaction improvement system can further optimize store business hours based on customer feedback. For example, if a customer provides feedback that the business hours are "short," a proposal to extend the business hours is made based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on store business hours and generate a satisfaction score. For example, if a customer provides feedback that the business hours are "long and convenient," the feedback is analyzed and a satisfaction score is generated. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on store business hours. For example, if the business hours of a particular store are highly rated, a proposal can be made to introduce those business hours to other stores. This makes it possible to improve customer satisfaction by optimizing store business hours.

[0085] The customer satisfaction improvement system can further optimize a store's promotion strategy based on customer feedback. For example, if a customer provides feedback that "the promotion is not attractive," the system makes suggestions to improve the promotion strategy based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on the promotion strategy and generate a satisfaction score. For example, if a customer provides feedback that "the promotion is great," the system analyzes that feedback and generates a satisfaction score. The store evaluation management unit can further optimize the evaluation of each store based on feedback on the promotion strategy. For example, if a particular promotion is highly rated, the system can make suggestions to introduce that promotion to other stores as well. This makes it possible to improve customer satisfaction by optimizing the promotion strategy.

[0086] The customer satisfaction improvement system can further optimize store staff allocation based on customer feedback. For example, if a customer provides feedback that "there are not enough staff," a proposal to increase staff allocation is made based on that feedback. The customer satisfaction scoring unit can also analyze customer feedback on staff allocation and generate a satisfaction score. For example, if a customer provides feedback that "there are many staff members and they respond quickly," the feedback can be analyzed and a satisfaction score generated. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on staff allocation. For example, if the staff allocation of a particular store is highly rated, a proposal can be made to introduce that allocation to other stores. This makes it possible to improve customer satisfaction by optimizing staff allocation.

[0087] The customer satisfaction improvement system can further optimize the service menu of a store based on customer feedback. For example, if a customer gives feedback that "the service menu is limited," a proposal to expand the service menu is made based on that feedback. The customer satisfaction scoring unit can also analyze customer feedback on the service menu and score the satisfaction level. For example, if a customer gives feedback that "the service menu is extensive and I'm satisfied," the feedback is analyzed and a satisfaction level is scored. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on the service menu. For example, if a specific service menu is highly rated, a proposal is made to introduce that menu in other stores as well. This makes it possible to improve customer satisfaction by optimizing the service menu.

[0088] The customer satisfaction improvement system can further optimize waiting times at stores based on customer feedback. For example, if a customer provides feedback that the waiting time is long, the system makes suggestions to shorten the waiting time based on that feedback. The customer satisfaction scoring unit can also analyze customer feedback on waiting times and generate a score for satisfaction. For example, if a customer provides feedback that the waiting time is short and comfortable, the system can analyze that feedback and generate a score for satisfaction. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on waiting times. For example, if the waiting time at a particular store is highly rated, the system can make suggestions to introduce that waiting time at other stores. This makes it possible to improve customer satisfaction by optimizing waiting times.

[0089] The customer satisfaction improvement system can further optimize a store's customer service attitude based on customer feedback. For example, if a customer provides feedback that the customer service attitude is "bad," the system makes suggestions to improve the customer service attitude based on that feedback. The customer satisfaction scoring unit can also analyze customer feedback on the customer service attitude and generate a satisfaction score. For example, if a customer provides feedback that the customer service attitude is "excellent," the system analyzes that feedback and generates a satisfaction score. The store evaluation management unit can also optimize the evaluation of each store based on feedback on the customer service attitude. For example, if the customer service attitude of a particular store is highly rated, the system can make suggestions to introduce that customer service attitude to other stores. This makes it possible to improve customer satisfaction by optimizing the customer service attitude.

[0090] The customer satisfaction improvement system can further optimize store cleanliness based on customer feedback. For example, if a customer provides feedback that "the store is dirty," a suggestion to increase cleaning frequency is made based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on store cleanliness and score satisfaction. For example, if a customer provides feedback that "the store is clean and comfortable," that feedback is analyzed and a satisfaction score is made. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on store cleanliness. For example, if the cleanliness of a particular store is highly rated, a suggestion is made to introduce that cleanliness to other stores. This makes it possible to improve customer satisfaction by optimizing store cleanliness.

[0091] The customer satisfaction improvement system can further optimize the store atmosphere based on customer feedback. For example, if a customer provides feedback that "the store atmosphere is bad," the system makes suggestions to improve the atmosphere based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on the store atmosphere and generate a satisfaction score. For example, if a customer provides feedback that "the store atmosphere is great," the system analyzes that feedback and generates a satisfaction score. The store evaluation management unit can further optimize the evaluation of each store based on feedback on the store atmosphere. For example, if the atmosphere of a particular store is highly rated, the system can make suggestions to introduce that atmosphere to other stores. This makes it possible to improve customer satisfaction by optimizing the store atmosphere.

[0092] The customer satisfaction improvement system can further optimize the music and lighting in a store based on customer feedback. For example, if a customer gives feedback that "the music is too loud," the system makes a suggestion to adjust the music volume based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on music and lighting and generate a score for satisfaction. For example, if a customer gives feedback that "the lighting is bright and comfortable," the system analyzes that feedback and generates a score for satisfaction. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on music and lighting. For example, if the music and lighting in a particular store are highly rated, the system can make a suggestion to introduce those settings in other stores. This makes it possible to improve customer satisfaction by optimizing music and lighting.

[0093] The customer satisfaction improvement system can further optimize the music and lighting in a store based on customer feedback. For example, if a customer gives feedback that "the music is too loud," the system makes a suggestion to adjust the music volume based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on music and lighting and generate a score for satisfaction. For example, if a customer gives feedback that "the lighting is bright and comfortable," the system analyzes that feedback and generates a score for satisfaction. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on music and lighting. For example, if the music and lighting in a particular store are highly rated, the system can make a suggestion to introduce those settings in other stores. This makes it possible to improve customer satisfaction by optimizing music and lighting.

[0094] The customer satisfaction improvement system can further optimize store service times based on customer feedback. For example, if a customer provides feedback that "service times are long," the system makes a proposal to shorten service times based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on service times and generate a satisfaction score. For example, if a customer provides feedback that "service times are short and I'm satisfied," the system analyzes that feedback and generates a satisfaction score. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on service times. For example, if the service times of a particular store are highly rated, the system can propose introducing those times to other stores. This makes it possible to improve customer satisfaction by optimizing service times.

[0095] The customer satisfaction improvement system can further optimize the expertise of store staff based on customer feedback. For example, if a customer provides feedback that "the staff lacks knowledge," the system can make suggestions to strengthen staff training based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on staff expertise and generate a satisfaction score. For example, if a customer provides feedback that "the staff was very knowledgeable and helpful," the system can analyze that feedback and generate a satisfaction score. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on staff expertise. For example, if the expertise of staff at a particular store is highly rated, the system can make a suggestion to share that knowledge with other stores. This makes it possible to improve customer satisfaction by optimizing staff expertise.

[0096] The customer satisfaction improvement system can also monitor waiting times at stores in real time based on customer feedback and work to reduce waiting times. For example, if a customer provides feedback that the waiting time is long, the system can monitor waiting times in real time based on that feedback and make suggestions to adjust staff deployment. The customer satisfaction scoring unit can also analyze customer feedback on waiting times and generate a satisfaction score. For example, if a customer provides feedback that the waiting time is short and comfortable, the system can analyze that feedback and generate a satisfaction score. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on waiting times. For example, if the waiting time at a particular store is highly rated, the system can make suggestions to introduce that waiting time at other stores. This makes it possible to monitor and reduce waiting times in real time.

[0097] The customer satisfaction improvement system can further optimize the service provision process of a store based on customer feedback. For example, if a customer provides feedback that the "service provision process is complicated," the system can make suggestions to simplify the process based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on the service provision process and generate a satisfaction score. For example, if a customer provides feedback that the "service provision process was smooth and satisfying," the system can analyze that feedback and generate a satisfaction score. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on the service provision process. For example, if the service provision process of a particular store has received high evaluations, the system can make suggestions to introduce that process to other stores. This makes it possible to improve customer satisfaction by optimizing the service provision process.

[0098] The customer satisfaction improvement system can further optimize the communication skills of store staff based on customer feedback. For example, if a customer provides feedback that "the staff's communication is insufficient," the system makes suggestions to improve the staff's communication skills based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on the staff's communication skills and generate a satisfaction score. For example, if a customer provides feedback that "the staff's communication is good and I'm satisfied," the system analyzes that feedback and generates a satisfaction score. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on the staff's communication skills. For example, if the communication skills of the staff at a particular store are highly rated, the system can make a suggestion to share those skills with other stores. This makes it possible to improve customer satisfaction by optimizing the staff's communication skills.

[0099] The customer satisfaction improvement system can further optimize the motivation of store staff based on customer feedback. For example, if a customer provides feedback that "the staff's motivation is low," the system makes suggestions to improve staff motivation based on that feedback. The customer satisfaction scoring unit can analyze customer feedback on staff motivation and generate a score for satisfaction. For example, if a customer provides feedback that "the staff's motivation is high and I'm satisfied," the system analyzes that feedback and generates a score for satisfaction. Furthermore, the store evaluation management unit can optimize the evaluation of each store based on feedback on staff motivation. For example, if the staff motivation of a particular store is highly rated, the system can make a suggestion to share that motivation with other stores. This makes it possible to improve customer satisfaction by optimizing staff motivation.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The customer satisfaction scoring unit analyzes customer feedback and generates a score for customer satisfaction. For example, the generation AI analyzes the customer's responses to a questionnaire and assigns a score for each item, such as "customer service attitude," "waiting time," and "store cleanliness." The generation AI also uses a text generation AI (e.g., LLM) to analyze the feedback and calculate a score. Step 2: The store evaluation management department manages the evaluation of each store using the customer satisfaction scores generated by the customer satisfaction scoring department. For example, the generation AI compares the scores of each store and suggests improvements to stores with low ratings. It also analyzes best practices from stores with good ratings and shares them with other stores. Step 3: The Crew Training Support Department trains and supports crew members based on the evaluations managed by the Store Evaluation Management Department. For example, for crew members at stores with low evaluations, the department provides them with a training program to improve their customer service attitude. In addition, the generative AI evaluates the effectiveness of the crew members' training and suggests areas for further improvement.

[0102] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0104] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0107] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0108] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, 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. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0109] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0110] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0111] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0112] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0113] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0114] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0115] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0116] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0117] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0118] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0122] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0123] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. 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. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0124] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0125] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0126] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0127] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0128] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0129] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0130] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0131] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0132] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0133] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0134] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0135] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0136] 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.

[0137] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0138] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. 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. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0139] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0141] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0142] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0143] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0144] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0145] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0146] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0147] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0148] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0149] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0150] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0151] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0152] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0153] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0154] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0155] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0156] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0157] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0158] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0159] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0160] 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.

[0161] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0162] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0163] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0164] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0165] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0166] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0167] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0168] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0169] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a customer satisfaction scoring unit that analyzes customer feedback and scores customer satisfaction; a store evaluation management unit that manages evaluations of each store using the customer satisfaction scores obtained by the customer satisfaction scoring unit; a crew training support unit that trains and supports crews based on the evaluations managed by the store evaluation management unit. A system characterized by:

2. The customer satisfaction scoring unit The customer satisfaction score is calculated by analyzing multimodal data, including audio and video feedback.

2. The system of claim 1.

3. The store evaluation management unit Using generative AI, the emotional response of the customer to each store's rating is analyzed, and emotionally positive ratings are prioritized.

2. The system of claim 1.

4. The crew training support department Using generative AI, the effectiveness of the crew's training is evaluated using emotion estimation functionality, and a training program is provided that elicits a positive emotional response.

2. The system of claim 1.

5. The customer satisfaction scoring unit Analyzing the emotions contained in the customer feedback and adjusting the score based on the intensity and type of the emotions.

2. The system of claim 1.

6. The store evaluation management unit Using generative AI to make emotionally relatable improvement suggestions for stores with low ratings 2. The system of claim 1.

7. The crew training support department Evaluate the crew's feelings after the training and suggest further improvements 2. The system of claim 1.

8. The crew training support department Using generative AI to monitor the crew's emotional responses during the training in real time and adjust the training content immediately.

2. The system of claim 1.

Images