system

Abstract

An object of a system according to an embodiment is to accurately grasp an emotion of a customer and calculate a true NPS in which a low answer central tendency and a low response rate specific to Japanese are corrected.SOLUTION: A system according to an embodiment includes a voice data collection unit, a facial expression data collection unit, an emotion analysis unit, and an NPS calculation unit. The voice data collection unit collects voice data during customer service or call handling. The facial expression data collection unit collects facial expression data during customer service and call handling. The emotion analysis unit analyzes the voice data collected by the voice data collection unit and the facial expression data collected by the facial expression data collection unit, and specifies an emotion of the customer. The NPS calculation unit calculates a true NPS by correcting a Japanese-specific tendency of centering an answer and a low answer rate based on the emotion data specified by the emotion analysis 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] Conventional technology had the problem of making it difficult to accurately grasp customer sentiment and calculate a true NPS that corrected for the tendency for Japanese people to center their responses and the low response rate.

[0005] The system according to the embodiment aims to accurately grasp customer sentiment and calculate a true NPS that corrects for the tendency to center responses and low response rates that are unique to Japanese people. [Means for solving the problem]

[0006] The system according to the embodiment includes a voice data collection unit, a facial expression data collection unit, an emotion analysis unit, and an NPS calculation unit. The voice data collection unit collects voice data during customer service and call handling. The emotion data collection unit collects facial expression data during customer service and call handling. The emotion analysis unit analyzes the voice data collected by the voice data collection unit and the facial expression data collected by the emotion data collection unit to identify the customer's emotion. The NPS calculation unit calculates a true NPS based on the emotion data identified by the emotion analysis unit, correcting for the tendency to centralize responses and low response rates that are unique to Japanese people. [Effects of the Invention]

[0007] The system according to the embodiment can accurately grasp customer sentiment and calculate the true NPS by correcting for the tendency to center responses and low response rates that are unique to Japanese people. [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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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 NPS calculation system according to an embodiment of the present invention collects voice and facial expression data during customer service or call handling, analyzes emotions using a generation AI, and calculates the true NPS by correcting for the tendency toward answer centering and low response rate that are typical of Japanese people. This enables the NPS calculation system to accurately grasp customer emotions and calculate the true NPS that has been corrected for the tendency toward answer centering and low response rate that are typical of Japanese people.

[0029] An NPS calculation system according to an embodiment includes a voice data collection unit, a facial expression data collection unit, an emotion analysis unit, and an NPS calculation unit. The voice data collection unit collects voice data during customer service or call handling. For example, the voice data collection unit collects voice data in real time using a microphone. The voice data collection unit can also analyze recorded data. For example, the voice data collection unit collects customer tone of voice and speaking patterns. The emotion data collection unit collects emotion data during customer service or call handling. For example, the emotion data collection unit collects emotion data in real time using a camera. The emotion data collection unit can also analyze recorded data. For example, the emotion data collection unit collects customer facial expressions and eye movements. The emotion analysis unit analyzes the voice data collected by the voice data collection unit and the emotion data collected by the emotion data collection unit to identify the customer's emotion. For example, the emotion analysis unit analyzes the voice data and facial expression data using generative AI to identify the customer's emotion. The emotion analysis unit can also identify emotion using voice tone analysis or emotion recognition technology. For example, the emotion analysis unit identifies customer emotions using voice tone analysis. The NPS calculation unit calculates a true NPS based on the emotion data identified by the emotion analysis unit, correcting for the tendency toward centralized responses and low response rates that are unique to Japanese customers. For example, the NPS calculation unit analyzes the emotion data using a generation AI to correct for the tendency toward centralized responses. The NPS calculation unit can also correct for the low response rate using a statistical correction method. For example, the NPS calculation unit corrects for the low response rate using a statistical correction method. This allows the NPS calculation system according to the embodiment to accurately grasp customer emotions and calculate a true NPS that corrects for the tendency toward centralized responses and low response rates that are unique to Japanese customers. For example, the NPS calculation system identifies areas for service improvement based on customer emotions and proposes specific improvement measures. The generation AI analyzes the true NPS and identifies which aspects affect customer satisfaction. This allows effective improvement measures to be implemented.

[0030] The voice data collection unit simultaneously collects the customer's background and environmental sounds, allowing the generation AI to eliminate their influence and identify emotions. For example, when collecting a customer's voice data, the voice data collection unit simultaneously records the surrounding environmental and background sounds, and the generation AI removes these noises. For example, it filters out cafe or office noise and analyzes only the customer's voice. The voice data collection unit also identifies the type and intensity of background sounds, and the generation AI takes these into consideration when performing emotion analysis. For example, it removes traffic and crowd noise to accurately analyze the customer's tone of voice and speaking style. The voice data collection unit also creates a profile of environmental sounds along with the customer's voice data, and the generation AI uses this profile to remove noise. For example, it filters out sounds in specific frequency bands to identify the customer's emotions. This allows the influence of background and environmental sounds to be eliminated and the customer's emotions to be accurately identified.

[0031] The voice data collection unit analyzes not only the customer's tone of voice, but also their speaking speed and pauses, allowing for more detailed emotional identification. For example, the voice data collection unit analyzes not only the customer's tone of voice, but also their speaking speed and pauses, allowing the generation AI to identify their emotions. For example, speaking quickly may indicate nervousness or excitement. The voice data collection unit also analyzes speaking speed and pauses to track changes in the customer's emotions in real time. For example, a sudden slowdown in speaking speed may indicate the customer is deep in thought. The voice data collection unit also comprehensively analyzes the customer's tone of voice, speaking speed, and pauses, allowing the generation AI to identify multiple emotions. For example, a low tone and slow speaking speed indicate calmness and a sense of security. This makes it possible to identify more detailed emotional identification by analyzing the customer's tone of voice, speaking speed, and pauses.

[0032] The voice data collection unit expands the collection of voice data not only from telephone responses but also from chatbots and email text-to-speech functions, enabling multi-channel emotion analysis. The voice data collection unit collects voice data not only from telephone responses but also from chatbots and email text-to-speech functions, and the generation AI performs emotion analysis. For example, it identifies customer emotions from the chatbot's voice responses. The voice data collection unit also integrates voice data collected from multiple channels, and the generation AI performs consistent emotion analysis. For example, it combines and analyzes voice data from telephone responses and chatbots. The voice data collection unit also uses chatbots and email text-to-speech functions to build a system that analyzes customer emotions in real time and provides feedback. For example, it identifies customer emotions while emails are being text-to-speech. This makes it possible to collect voice data not only from telephone responses but also from chatbots and email text-to-speech functions, enabling multi-channel emotion analysis.

[0033] The voice data collection unit collects voice data in different languages, allowing the generation AI to perform emotion analysis in multiple languages. The voice data collection unit, for example, collects voice data in different languages, allowing the generation AI to perform emotion analysis in multiple languages. For example, it analyzes voice data in English, French, Chinese, etc. The voice data collection unit also develops a multilingual emotion analysis algorithm, allowing the generation AI to identify emotions from voice data in different languages. For example, it takes into account differences in emotional expression in each language. The voice data collection unit also analyzes voice data in different languages ​​in real time, building a system in which the generation AI identifies emotions. For example, it performs emotion analysis when dealing with international customers. This makes it possible to collect voice data in different languages ​​and perform emotion analysis in multiple languages.

[0034] When collecting facial expression data, the facial expression data collection unit simultaneously analyzes the customer's body movements and posture, allowing for more detailed emotional identification. For example, when collecting facial expression data, the facial expression data collection unit simultaneously records the customer's body movements and posture, and the generation AI analyzes this data. For example, a customer with their arms crossed may indicate a defensive attitude. The facial expression data collection unit also analyzes the customer's body movements and posture, combining this with the facial expression data to identify emotions. For example, a customer leaning forward may indicate interest. The facial expression data collection unit also analyzes facial expression data together with body movements and posture, allowing the generation AI to identify multiple emotions. For example, a customer smiling but pulling their body back may indicate complex emotions. This makes it possible to identify emotions in more detail by also analyzing the customer's body movements and posture.

[0035] The facial expression data collection unit analyzes the speed and frequency of a customer's facial expression changes, allowing the generation AI to identify the intensity of their emotions. For example, the facial expression data collection unit analyzes the speed of a customer's facial expression changes, allowing the generation AI to identify the intensity of their emotions. For example, rapid changes in facial expression may indicate strong emotions. The facial expression data collection unit also tracks emotional fluctuations in real time by analyzing the frequency of facial expression changes. For example, frequent changes in facial expression may indicate emotional instability. The facial expression data collection unit also comprehensively analyzes the speed and frequency of facial expression changes, allowing the generation AI to identify the intensity and fluctuation of their emotions. For example, slow changes in facial expression may indicate calm emotions. In this way, the intensity and fluctuation of their emotions can be identified by analyzing the speed and frequency of a customer's facial expression changes.

[0036] The facial expression data collection unit expands the collection of facial expression data not only from face-to-face customer service but also from video calls and online conferences, enabling multi-channel emotion analysis. The facial expression data collection unit collects facial expression data not only from face-to-face customer service but also from video calls and online conferences, and the generation AI performs emotion analysis. For example, it obtains facial expression data from video calls on Zoom or Teams. The facial expression data collection unit also integrates facial expression data collected from multiple channels, and the generation AI performs consistent emotion analysis. For example, it combines and analyzes facial expression data from face-to-face customer service and video calls. The facial expression data collection unit also analyzes facial expression data from video calls and online conferences in real time to build a system that identifies emotions. For example, it analyzes facial expression changes during online conferences. This makes it possible to collect facial expression data not only from face-to-face customer service but also from video calls and online conferences, enabling multi-channel emotion analysis.

[0037] The facial expression data collection unit collects facial expression data from different cultural spheres, allowing the generation AI to perform multicultural emotion analysis. The facial expression data collection unit, for example, collects facial expression data from different cultural spheres, allowing the generation AI to perform multicultural emotion analysis. For example, it analyzes facial expression data from Asia, Europe, Africa, etc. The facial expression data collection unit also develops a multicultural emotion analysis algorithm, allowing the generation AI to identify emotions from facial expression data from different cultural spheres. For example, it takes into account differences in facial expressions between cultures. The facial expression data collection unit also analyzes facial expression data from different cultural spheres in real time, building a system in which the generation AI identifies emotions. For example, it performs emotion analysis when dealing with international customers. This makes it possible to collect facial expression data from different cultural spheres and perform multicultural emotion analysis.

[0038] The emotion analysis unit takes into account the customer's past emotional data when integrating voice data and facial expression data, making it possible to identify long-term emotional trends. For example, when integrating voice data and facial expression data, the emotion analysis unit also takes into account the customer's past emotional data, allowing the generation AI to identify long-term emotional trends. For example, it tracks changes in emotions based on past data. The emotion analysis unit also analyzes the customer's past emotional data, building a system in which the generation AI identifies long-term emotional trends. For example, it evaluates the customer's current emotions based on the emotions they have shown in the past. The emotion analysis unit also integrates voice data and facial expression data, making it possible to identify long-term emotional trends by taking into account past emotional data. For example, it predicts the customer's current emotions based on the emotions they have shown in the past. In this way, it is possible to identify long-term emotional trends by taking into account the customer's past emotional data.

[0039] When correcting emotion data, the emotion analysis unit also takes into account attribute information such as the customer's age and gender, allowing for more accurate corrections. For example, when correcting emotion data, the emotion analysis unit takes into account attribute information such as the customer's age and gender, allowing the generation AI to make more accurate corrections. For example, differences in emotional expression due to age and gender are taken into account. The emotion analysis unit also builds a system that corrects emotion data based on customer attribute information. For example, it corrects for differences in emotional expression between young and older customers. The emotion analysis unit also develops an algorithm that corrects emotion data, taking into account attribute information such as age and gender. For example, it corrects for differences in emotional expression between men and women. This makes it possible to correct emotion data with greater accuracy by taking into account attribute information such as the customer's age and gender.

[0040] The sentiment analysis unit can integrate emotional data with behavioral data such as customer purchase history and website browsing history to create a comprehensive customer profile. For example, the sentiment analysis unit integrates emotional data with customer purchase history, and the generation AI creates a comprehensive customer profile. For example, it identifies customer preferences and trends from the purchase history. The sentiment analysis unit also integrates emotional data with website browsing history, and the generation AI creates a comprehensive customer profile. For example, it identifies customer interests from the browsing history. The sentiment analysis unit also integrates emotional data with behavioral data, and builds a system in which the generation AI creates a comprehensive customer profile. For example, it creates a customer profile based on purchase history and browsing history. In this way, a comprehensive customer profile can be created by integrating emotional data and behavioral data.

[0041] The emotion analysis unit integrates emotion data from different industries and applications, allowing the generation AI to perform emotion analysis for multiple applications. For example, the emotion analysis unit integrates emotion data from different industries, allowing the generation AI to perform emotion analysis for multiple applications. For example, it analyzes emotion data from medical, education, entertainment, etc. The emotion analysis unit also develops emotion analysis algorithms for multiple applications, allowing the generation AI to identify emotions from emotion data from different industries. For example, it takes into account differences in emotional expression between industries. The emotion analysis unit also analyzes emotion data from different applications in real time, building a system where the generation AI can identify emotions. For example, it analyzes emotion data from customer service and education. This makes it possible to integrate emotion data from different industries and applications, allowing for emotion analysis for multiple applications.

[0042] The NPS calculation unit also takes into account the customer's past NPS data when calculating the true NPS, making it possible to identify long-term fluctuations in satisfaction. For example, when calculating the true NPS, the NPS calculation unit takes into account the customer's past NPS data, and the generation AI identifies long-term fluctuations in satisfaction. For example, the current satisfaction level is evaluated based on the past NPS data. The NPS calculation unit also analyzes the customer's past NPS data, and builds a system in which the generation AI identifies long-term fluctuations in satisfaction. For example, it tracks changes in satisfaction based on past data. The NPS calculation unit also takes into account past NPS data when calculating the true NPS to identify long-term fluctuations in satisfaction. For example, it predicts current satisfaction levels based on how satisfied the customer was in the past. In this way, by also taking into account the customer's past NPS data, it is possible to identify long-term fluctuations in satisfaction.

[0043] The NPS calculation unit takes into account customer attribute information (age, gender, region, etc.) when calculating the NPS, allowing it to calculate a more accurate NPS. For example, when calculating the NPS, the NPS calculation unit takes into account attribute information such as the customer's age, gender, and region, allowing the generation AI to calculate a more accurate NPS. For example, differences in satisfaction levels due to age and gender are taken into account. The NPS calculation unit also builds a system to calculate the NPS based on customer attribute information. For example, it evaluates different levels of satisfaction between younger and older customers. The NPS calculation unit also develops an algorithm to calculate the NPS, taking into account attribute information such as age, gender, and region. For example, it evaluates different levels of satisfaction between men and women. In this way, by taking customer attribute information into account, it is possible to calculate a more accurate NPS.

[0044] The NPS calculation unit applies the NPS calculation to different industries and applications, allowing the generation AI to perform versatile NPS analysis. For example, the NPS calculation unit calculates the NPS for different industries, and the generation AI performs versatile NPS analysis. For example, it analyzes NPS for healthcare, education, entertainment, etc. The NPS calculation unit also develops a versatile NPS analysis algorithm, allowing the generation AI to identify NPS for different industries. For example, it takes into account differences in satisfaction between industries. The NPS calculation unit also builds a system that analyzes NPS for different applications in real time, allowing the generation AI to identify NPS. For example, it analyzes NPS for customer service and education. This makes it possible to apply the algorithm to different industries and applications, enabling versatile NPS analysis.

[0045] The NPS calculation unit integrates the NPS calculation results with behavioral data such as customer purchase history and website browsing history to evaluate overall customer satisfaction. For example, the NPS calculation unit integrates the NPS calculation results with customer purchase history, and the generation AI evaluates overall customer satisfaction. For example, it identifies customer satisfaction from the purchase history. The NPS calculation unit also integrates the NPS calculation results with website browsing history, and the generation AI evaluates overall customer satisfaction. For example, it identifies customer interests from the browsing history. The NPS calculation unit also integrates the NPS calculation results with behavioral data, and builds a system in which the generation AI evaluates overall customer satisfaction. For example, it evaluates customer satisfaction based on purchase history and browsing history. In this way, overall customer satisfaction can be evaluated by integrating the NPS calculation results with the behavioral data.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The NPS calculation system can also collect customer purchase history, and the NPS calculation unit can take this into account when calculating the NPS. For example, fluctuations in satisfaction can be evaluated based on the history of products and services a customer has purchased in the past. The NPS calculation unit can also integrate purchase history and emotional data to calculate a more accurate NPS. For example, it can evaluate customer satisfaction based on emotional data after purchasing a specific product. The NPS calculation unit can also identify customer preferences and trends based on purchase history and reflect this in the NPS calculation. This allows for a more accurate NPS to be calculated by taking customer purchase history into account.

[0048] The NPS calculation system can also collect a customer's website browsing history, and the NPS calculation unit can take this into account when calculating the NPS. For example, the NPS calculation unit can evaluate fluctuations in satisfaction based on which pages a customer views and how much time they spend there. The NPS calculation unit can also integrate the browsing history with emotional data to calculate a more accurate NPS. For example, it can evaluate customer satisfaction based on emotional data after viewing a specific page. The NPS calculation unit can also identify a customer's interests and concerns based on the browsing history and reflect this in the NPS calculation. This allows for a more accurate NPS to be calculated by taking into account the customer's website browsing history.

[0049] The NPS calculation system can also collect customer social media activity data, and the NPS calculation unit can take this into account when calculating the NPS. For example, it can evaluate fluctuations in satisfaction based on the types of posts customers make and the reactions they receive. The NPS calculation unit can also integrate social media activity data with emotional data to calculate a more accurate NPS. For example, it can evaluate customer satisfaction based on emotional data after a specific post. The NPS calculation unit can also identify customer interests and trends based on social media activity data and reflect this in the NPS calculation. This allows for a more accurate NPS to be calculated by taking customer social media activity data into account.

[0050] The NPS calculation system can also collect customer feedback data, and the NPS calculation unit can take this into account when calculating the NPS. For example, the NPS calculation unit can evaluate fluctuations in satisfaction based on feedback and reviews provided by customers. The NPS calculation unit can also integrate feedback data with emotional data to calculate a more accurate NPS. For example, the NPS calculation unit can evaluate customer satisfaction based on emotional data after providing specific feedback. The NPS calculation unit can also identify customer opinions and requests based on feedback data and reflect them in the NPS calculation. This allows for a more accurate NPS to be calculated by taking customer feedback data into account.

[0051] The NPS calculation system can also collect customer location data, and the NPS calculation unit can take this into account when calculating the NPS. For example, fluctuations in satisfaction can be evaluated based on the area in which the customer uses the service. The NPS calculation unit can also integrate location data and emotional data to calculate a more accurate NPS. For example, customer satisfaction can be evaluated based on emotional data after using the service in a specific area. The NPS calculation unit can also identify customer behavior patterns based on location data and reflect this in the NPS calculation. In this way, by taking customer location data into account, a more accurate NPS can be calculated.

[0052] The processing flow of the first embodiment will be briefly explained below.

[0053] Step 1: The voice data collection unit collects voice data while serving customers or answering calls. For example, the voice data collection unit collects voice data in real time using a microphone. It can also analyze recorded data. The voice data collection unit collects the customer's tone of voice and speaking patterns. Step 2: The facial expression data collection unit collects facial expression data while serving customers or answering calls. For example, the facial expression data collection unit collects facial expression data in real time using a camera. It can also analyze recorded data. The facial expression data collection unit collects facial expressions and eye movements of customers. Step 3: The emotion analysis unit analyzes the voice data collected by the voice data collection unit and the facial expression data collected by the facial expression data collection unit to identify the customer's emotions. For example, the emotion analysis unit may use generative AI to analyze the voice data and facial expression data, and identify the customer's emotions using voice tone analysis and facial expression recognition technology. Step 4: The NPS calculation unit calculates the true NPS based on the emotional data identified by the emotion analysis unit, correcting for the tendency to center responses and the low response rate that are unique to Japanese people. For example, the emotion data can be analyzed using a generation AI, and the low response rate can be corrected using a statistical correction method.

[0054] (Example 2) The NPS calculation system according to an embodiment of the present invention collects voice and facial expression data during customer service or call handling, analyzes emotions using a generation AI, and calculates the true NPS by correcting for the tendency toward answer centering and low response rate that are typical of Japanese people. This enables the NPS calculation system to accurately grasp customer emotions and calculate the true NPS that has been corrected for the tendency toward answer centering and low response rate that are typical of Japanese people.

[0055] An NPS calculation system according to an embodiment includes a voice data collection unit, a facial expression data collection unit, an emotion analysis unit, and an NPS calculation unit. The voice data collection unit collects voice data during customer service or call handling. For example, the voice data collection unit collects voice data in real time using a microphone. The voice data collection unit can also analyze recorded data. For example, the voice data collection unit collects customer tone of voice and speaking patterns. The emotion data collection unit collects emotion data during customer service or call handling. For example, the emotion data collection unit collects emotion data in real time using a camera. The emotion data collection unit can also analyze recorded data. For example, the emotion data collection unit collects customer facial expressions and eye movements. The emotion analysis unit analyzes the voice data collected by the voice data collection unit and the emotion data collected by the emotion data collection unit to identify the customer's emotion. For example, the emotion analysis unit analyzes the voice data and facial expression data using generative AI to identify the customer's emotion. The emotion analysis unit can also identify emotion using voice tone analysis or emotion recognition technology. For example, the emotion analysis unit identifies customer emotions using voice tone analysis. The NPS calculation unit calculates a true NPS based on the emotion data identified by the emotion analysis unit, correcting for the tendency toward centralized responses and low response rates that are unique to Japanese customers. For example, the NPS calculation unit analyzes the emotion data using a generation AI to correct for the tendency toward centralized responses. The NPS calculation unit can also correct for the low response rate using a statistical correction method. For example, the NPS calculation unit corrects for the low response rate using a statistical correction method. This allows the NPS calculation system according to the embodiment to accurately grasp customer emotions and calculate a true NPS that corrects for the tendency toward centralized responses and low response rates that are unique to Japanese customers. For example, the NPS calculation system identifies areas for service improvement based on customer emotions and proposes specific improvement measures. The generation AI analyzes the true NPS and identifies which aspects affect customer satisfaction. This allows effective improvement measures to be implemented.

[0056] The voice data collection unit simultaneously collects the customer's background and environmental sounds, allowing the generation AI to eliminate their influence and identify emotions. For example, when collecting a customer's voice data, the voice data collection unit simultaneously records the surrounding environmental and background sounds, and the generation AI removes these noises. For example, it filters out cafe or office noise and analyzes only the customer's voice. The voice data collection unit also identifies the type and intensity of background sounds, and the generation AI takes these into consideration when performing emotion analysis. For example, it removes traffic and crowd noise to accurately analyze the customer's tone of voice and speaking style. The voice data collection unit also creates a profile of environmental sounds along with the customer's voice data, and the generation AI uses this profile to remove noise. For example, it filters out sounds in specific frequency bands to identify the customer's emotions. This allows the influence of background and environmental sounds to be eliminated and the customer's emotions to be accurately identified.

[0057] The voice data collection unit analyzes not only the customer's tone of voice, but also their speaking speed and pauses, allowing for more detailed emotional identification. For example, the voice data collection unit analyzes not only the customer's tone of voice, but also their speaking speed and pauses, allowing the generation AI to identify their emotions. For example, speaking quickly may indicate nervousness or excitement. The voice data collection unit also analyzes speaking speed and pauses to track changes in the customer's emotions in real time. For example, a sudden slowdown in speaking speed may indicate the customer is deep in thought. The voice data collection unit also comprehensively analyzes the customer's tone of voice, speaking speed, and pauses, allowing the generation AI to identify multiple emotions. For example, a low tone and slow speaking speed indicate calmness and a sense of security. This makes it possible to identify more detailed emotional identification by analyzing the customer's tone of voice, speaking speed, and pauses.

[0058] The voice data collection unit uses the emotion estimation function to estimate emotions from the tone of a customer's voice in real time, allowing instant feedback to be provided during customer service. For example, the voice data collection unit analyzes the tone of a customer's voice in real time, and the generation AI estimates the emotion. For example, a high-pitched tone may indicate joy or excitement. The voice data collection unit also builds a system that provides instant feedback to customer service staff based on the emotion data estimated in real time. For example, an alert is displayed if a customer is dissatisfied. The voice data collection unit also estimates emotions from the tone of a customer's voice in real time and adjusts how the customer is treated during service. For example, if the customer is nervous, suggestions are made to help them relax. This makes it possible to estimate emotions from the tone of a customer's voice in real time and provide instant feedback.

[0059] The voice data collection unit expands the collection of voice data not only from telephone responses but also from chatbots and email text-to-speech functions, enabling multi-channel emotion analysis. The voice data collection unit collects voice data not only from telephone responses but also from chatbots and email text-to-speech functions, and the generation AI performs emotion analysis. For example, it identifies customer emotions from the chatbot's voice responses. The voice data collection unit also integrates voice data collected from multiple channels, and the generation AI performs consistent emotion analysis. For example, it combines and analyzes voice data from telephone responses and chatbots. The voice data collection unit also uses chatbots and email text-to-speech functions to build a system that analyzes customer emotions in real time and provides feedback. For example, it identifies customer emotions while emails are being text-to-speech. This makes it possible to collect voice data not only from telephone responses but also from chatbots and email text-to-speech functions, enabling multi-channel emotion analysis.

[0060] The voice data collection unit collects voice data in different languages, allowing the generation AI to perform emotion analysis in multiple languages. The voice data collection unit, for example, collects voice data in different languages, allowing the generation AI to perform emotion analysis in multiple languages. For example, it analyzes voice data in English, French, Chinese, etc. The voice data collection unit also develops a multilingual emotion analysis algorithm, allowing the generation AI to identify emotions from voice data in different languages. For example, it takes into account differences in emotional expression in each language. The voice data collection unit also analyzes voice data in different languages ​​in real time, building a system in which the generation AI identifies emotions. For example, it performs emotion analysis when dealing with international customers. This makes it possible to collect voice data in different languages ​​and perform emotion analysis in multiple languages.

[0061] The voice data collection unit can use the emotion estimation function to provide customized services that meet customer needs based on emotions estimated from voice data. The voice data collection unit, for example, builds a system that provides customized services that meet customer needs based on emotions estimated from voice data. For example, if a customer is dissatisfied, it provides a special offer. The voice data collection unit also uses the emotion estimation function to make service suggestions based on the customer's emotions. For example, if a customer is happy, it suggests additional services. The voice data collection unit also analyzes the emotions estimated from the voice data in real time and responds according to the customer's needs. For example, if a customer is tense, it makes suggestions to help the customer relax. In this way, customized services that meet customer needs can be provided based on emotions estimated from voice data.

[0062] When collecting facial expression data, the facial expression data collection unit simultaneously analyzes the customer's body movements and posture, allowing for more detailed emotional identification. For example, when collecting facial expression data, the facial expression data collection unit simultaneously records the customer's body movements and posture, and the generation AI analyzes this data. For example, a customer with their arms crossed may indicate a defensive attitude. The facial expression data collection unit also analyzes the customer's body movements and posture, combining this with the facial expression data to identify emotions. For example, a customer leaning forward may indicate interest. The facial expression data collection unit also analyzes facial expression data together with body movements and posture, allowing the generation AI to identify multiple emotions. For example, a customer smiling but pulling their body back may indicate complex emotions. This makes it possible to identify emotions in more detail by also analyzing the customer's body movements and posture.

[0063] The facial expression data collection unit analyzes the speed and frequency of a customer's facial expression changes, allowing the generation AI to identify the intensity of their emotions. For example, the facial expression data collection unit analyzes the speed of a customer's facial expression changes, allowing the generation AI to identify the intensity of their emotions. For example, rapid changes in facial expression may indicate strong emotions. The facial expression data collection unit also tracks emotional fluctuations in real time by analyzing the frequency of facial expression changes. For example, frequent changes in facial expression may indicate emotional instability. The facial expression data collection unit also comprehensively analyzes the speed and frequency of facial expression changes, allowing the generation AI to identify the intensity and fluctuation of their emotions. For example, slow changes in facial expression may indicate calm emotions. In this way, the intensity and fluctuation of their emotions can be identified by analyzing the speed and frequency of a customer's facial expression changes.

[0064] The facial expression data collection unit uses the emotion estimation function to estimate emotions from customers' facial expressions in real time and provide instant feedback during customer service. For example, the facial expression data collection unit analyzes customers' facial expressions in real time, and the generation AI estimates their emotions. For example, a smile may indicate joy. The facial expression data collection unit also builds a system that provides instant feedback to customer service staff based on the emotion data estimated in real time. For example, an alert is displayed if a customer is dissatisfied. The facial expression data collection unit also estimates emotions from customers' facial expressions in real time and adjusts how the staff responds during customer service. For example, if a customer appears nervous, suggestions are made to help them relax. This makes it possible to estimate emotions from customers' facial expressions in real time and provide instant feedback.

[0065] The facial expression data collection unit expands the collection of facial expression data not only from face-to-face customer service but also from video calls and online conferences, enabling multi-channel emotion analysis. The facial expression data collection unit collects facial expression data not only from face-to-face customer service but also from video calls and online conferences, and the generation AI performs emotion analysis. For example, it obtains facial expression data from video calls on Zoom or Teams. The facial expression data collection unit also integrates facial expression data collected from multiple channels, and the generation AI performs consistent emotion analysis. For example, it combines and analyzes facial expression data from face-to-face customer service and video calls. The facial expression data collection unit also analyzes facial expression data from video calls and online conferences in real time to build a system that identifies emotions. For example, it analyzes facial expression changes during online conferences. This makes it possible to collect facial expression data not only from face-to-face customer service but also from video calls and online conferences, enabling multi-channel emotion analysis.

[0066] The facial expression data collection unit collects facial expression data from different cultural spheres, allowing the generation AI to perform multicultural emotion analysis. The facial expression data collection unit, for example, collects facial expression data from different cultural spheres, allowing the generation AI to perform multicultural emotion analysis. For example, it analyzes facial expression data from Asia, Europe, Africa, etc. The facial expression data collection unit also develops a multicultural emotion analysis algorithm, allowing the generation AI to identify emotions from facial expression data from different cultural spheres. For example, it takes into account differences in facial expressions between cultures. The facial expression data collection unit also analyzes facial expression data from different cultural spheres in real time, building a system in which the generation AI identifies emotions. For example, it performs emotion analysis when dealing with international customers. This makes it possible to collect facial expression data from different cultural spheres and perform multicultural emotion analysis.

[0067] The facial expression data collection unit can use the emotion estimation function to provide customized services that meet customer needs based on emotions estimated from facial expression data. The facial expression data collection unit, for example, builds a system that provides customized services that meet customer needs based on emotions estimated from facial expression data. For example, if a customer is dissatisfied, it provides a special offer. The facial expression data collection unit also uses the emotion estimation function to make service suggestions based on the customer's emotions. For example, if a customer is happy, it suggests additional services. The facial expression data collection unit also analyzes emotions estimated from facial expression data in real time and responds according to the customer's needs. For example, if a customer is nervous, it makes suggestions to help the customer relax. This makes it possible to provide customized services that meet customer needs based on emotions estimated from facial expression data.

[0068] The emotion analysis unit takes into account the customer's past emotional data when integrating voice data and facial expression data, making it possible to identify long-term emotional trends. For example, when integrating voice data and facial expression data, the emotion analysis unit also takes into account the customer's past emotional data, allowing the generation AI to identify long-term emotional trends. For example, it tracks changes in emotions based on past data. The emotion analysis unit also analyzes the customer's past emotional data, building a system in which the generation AI identifies long-term emotional trends. For example, it evaluates the customer's current emotions based on the emotions they have shown in the past. The emotion analysis unit also integrates voice data and facial expression data, making it possible to identify long-term emotional trends by taking into account past emotional data. For example, it predicts the customer's current emotions based on the emotions they have shown in the past. In this way, it is possible to identify long-term emotional trends by taking into account the customer's past emotional data.

[0069] When correcting emotion data, the emotion analysis unit also takes into account attribute information such as the customer's age and gender, allowing for more accurate corrections. For example, when correcting emotion data, the emotion analysis unit takes into account attribute information such as the customer's age and gender, allowing the generation AI to make more accurate corrections. For example, differences in emotional expression due to age and gender are taken into account. The emotion analysis unit also builds a system that corrects emotion data based on customer attribute information. For example, it corrects for differences in emotional expression between young and older customers. The emotion analysis unit also develops an algorithm that corrects emotion data, taking into account attribute information such as age and gender. For example, it corrects for differences in emotional expression between men and women. This makes it possible to correct emotion data with greater accuracy by taking into account attribute information such as the customer's age and gender.

[0070] The emotion analysis unit uses the emotion estimation function to monitor emotional fluctuations in real time from the integrated emotion data and provide instant feedback. For example, the emotion analysis unit monitors the integrated emotion data in real time and the generative AI identifies emotional fluctuations. For example, an alert is displayed if there is a sudden change in a customer's emotion. The emotion analysis unit also uses the emotion estimation function to build a system that monitors emotional fluctuations in real time from the integrated emotion data. For example, it evaluates whether a customer's emotions are stable. The emotion analysis unit also monitors emotional fluctuations in real time based on the integrated emotion data and provides instant feedback. For example, it suggests countermeasures if a customer is dissatisfied. This makes it possible to monitor emotional fluctuations in real time from the integrated emotion data and provide instant feedback.

[0071] The sentiment analysis unit can integrate emotional data with behavioral data such as customer purchase history and website browsing history to create a comprehensive customer profile. For example, the sentiment analysis unit integrates emotional data with customer purchase history, and the generation AI creates a comprehensive customer profile. For example, it identifies customer preferences and trends from the purchase history. The sentiment analysis unit also integrates emotional data with website browsing history, and the generation AI creates a comprehensive customer profile. For example, it identifies customer interests from the browsing history. The sentiment analysis unit also integrates emotional data with behavioral data, and builds a system in which the generation AI creates a comprehensive customer profile. For example, it creates a customer profile based on purchase history and browsing history. In this way, a comprehensive customer profile can be created by integrating emotional data and behavioral data.

[0072] The emotion analysis unit integrates emotion data from different industries and applications, allowing the generation AI to perform emotion analysis for multiple applications. For example, the emotion analysis unit integrates emotion data from different industries, allowing the generation AI to perform emotion analysis for multiple applications. For example, it analyzes emotion data from medical, education, entertainment, etc. The emotion analysis unit also develops emotion analysis algorithms for multiple applications, allowing the generation AI to identify emotions from emotion data from different industries. For example, it takes into account differences in emotional expression between industries. The emotion analysis unit also analyzes emotion data from different applications in real time, building a system where the generation AI can identify emotions. For example, it analyzes emotion data from customer service and education. This makes it possible to integrate emotion data from different industries and applications, allowing for emotion analysis for multiple applications.

[0073] The emotion analysis unit can use the emotion estimation function to provide customized services that meet customer needs based on emotions estimated from the integrated emotion data. The emotion analysis unit, for example, builds a system that provides customized services that meet customer needs based on emotions estimated from the integrated emotion data. For example, if a customer is dissatisfied, it provides a special offer. The emotion analysis unit also uses the emotion estimation function to make service suggestions based on the customer's emotions. For example, if a customer is happy, it suggests additional services. The emotion analysis unit also analyzes emotions estimated from the integrated emotion data in real time to respond according to the customer's needs. For example, if a customer is tense, it makes suggestions to help the customer relax. In this way, customized services that meet customer needs can be provided based on emotions estimated from the integrated emotion data.

[0074] The NPS calculation unit also takes into account the customer's past NPS data when calculating the true NPS, making it possible to identify long-term fluctuations in satisfaction. For example, when calculating the true NPS, the NPS calculation unit takes into account the customer's past NPS data, and the generation AI identifies long-term fluctuations in satisfaction. For example, the current satisfaction level is evaluated based on the past NPS data. The NPS calculation unit also analyzes the customer's past NPS data, and builds a system in which the generation AI identifies long-term fluctuations in satisfaction. For example, it tracks changes in satisfaction based on past data. The NPS calculation unit also takes into account past NPS data when calculating the true NPS to identify long-term fluctuations in satisfaction. For example, it predicts current satisfaction levels based on how satisfied the customer was in the past. In this way, by also taking into account the customer's past NPS data, it is possible to identify long-term fluctuations in satisfaction.

[0075] The NPS calculation unit takes into account customer attribute information (age, gender, region, etc.) when calculating the NPS, allowing it to calculate a more accurate NPS. For example, when calculating the NPS, the NPS calculation unit takes into account attribute information such as the customer's age, gender, and region, allowing the generation AI to calculate a more accurate NPS. For example, differences in satisfaction levels due to age and gender are taken into account. The NPS calculation unit also builds a system to calculate the NPS based on customer attribute information. For example, it evaluates different levels of satisfaction between younger and older customers. The NPS calculation unit also develops an algorithm to calculate the NPS, taking into account attribute information such as age, gender, and region. For example, it evaluates different levels of satisfaction between men and women. In this way, by taking customer attribute information into account, it is possible to calculate a more accurate NPS.

[0076] The NPS calculation unit can instantly calculate an NPS based on emotion data estimated in real time using the emotion estimation function and provide feedback. In the NPS calculation unit, for example, a generation AI instantly calculates an NPS based on emotion data estimated in real time. For example, a high NPS is calculated when a customer's emotion is positive. The NPS calculation unit also uses the emotion estimation function to build a system that calculates an NPS based on emotion data estimated in real time. For example, a low NPS is calculated when a customer's emotion is negative. The NPS calculation unit also instantly calculates an NPS based on emotion data estimated in real time and provides feedback. For example, a countermeasure is suggested when a customer is dissatisfied. This makes it possible to instantly calculate an NPS based on emotion data estimated in real time and provide feedback.

[0077] The NPS calculation unit applies the NPS calculation to different industries and applications, allowing the generation AI to perform versatile NPS analysis. For example, the NPS calculation unit calculates the NPS for different industries, and the generation AI performs versatile NPS analysis. For example, it analyzes NPS for healthcare, education, entertainment, etc. The NPS calculation unit also develops a versatile NPS analysis algorithm, allowing the generation AI to identify NPS for different industries. For example, it takes into account differences in satisfaction between industries. The NPS calculation unit also builds a system that analyzes NPS for different applications in real time, allowing the generation AI to identify NPS. For example, it analyzes NPS for customer service and education. This makes it possible to apply the algorithm to different industries and applications, enabling versatile NPS analysis.

[0078] The NPS calculation unit integrates the NPS calculation results with behavioral data such as customer purchase history and website browsing history to evaluate overall customer satisfaction. For example, the NPS calculation unit integrates the NPS calculation results with customer purchase history, and the generation AI evaluates overall customer satisfaction. For example, it identifies customer satisfaction from the purchase history. The NPS calculation unit also integrates the NPS calculation results with website browsing history, and the generation AI evaluates overall customer satisfaction. For example, it identifies customer interests from the browsing history. The NPS calculation unit also integrates the NPS calculation results with behavioral data, and builds a system in which the generation AI evaluates overall customer satisfaction. For example, it evaluates customer satisfaction based on purchase history and browsing history. In this way, overall customer satisfaction can be evaluated by integrating the NPS calculation results with the behavioral data.

[0079] The NPS calculation unit can use the emotion estimation function to provide customized services tailored to customer needs based on emotions estimated from the NPS calculation results. The NPS calculation unit, for example, builds a system that provides customized services tailored to customer needs based on emotions estimated from the NPS calculation results. For example, if a customer is dissatisfied, it provides a special offer. The NPS calculation unit also uses the emotion estimation function to make service suggestions based on the customer's emotions. For example, if a customer is happy, it suggests additional services. The NPS calculation unit also analyzes the emotions estimated from the NPS calculation results in real time and responds according to the customer's needs. For example, if a customer is tense, it makes suggestions to help them relax. This makes it possible to provide customized services tailored to customer needs based on emotions estimated from the NPS calculation results.

[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 NPS calculation system can also collect customer purchase history, and the NPS calculation unit can take this into account when calculating the NPS. For example, fluctuations in satisfaction can be evaluated based on the history of products and services a customer has purchased in the past. The NPS calculation unit can also integrate purchase history and emotional data to calculate a more accurate NPS. For example, it can evaluate customer satisfaction based on emotional data after purchasing a specific product. The NPS calculation unit can also identify customer preferences and trends based on purchase history and reflect this in the NPS calculation. This allows for a more accurate NPS to be calculated by taking customer purchase history into account.

[0082] The NPS calculation system can also collect a customer's website browsing history, and the NPS calculation unit can take this into account when calculating the NPS. For example, the NPS calculation unit can evaluate fluctuations in satisfaction based on which pages a customer views and how much time they spend there. The NPS calculation unit can also integrate the browsing history with emotional data to calculate a more accurate NPS. For example, it can evaluate customer satisfaction based on emotional data after viewing a specific page. The NPS calculation unit can also identify a customer's interests and concerns based on the browsing history and reflect this in the NPS calculation. This allows for a more accurate NPS to be calculated by taking into account the customer's website browsing history.

[0083] The NPS calculation system can also collect customer social media activity data, and the NPS calculation unit can take this into account when calculating the NPS. For example, it can evaluate fluctuations in satisfaction based on the types of posts customers make and the reactions they receive. The NPS calculation unit can also integrate social media activity data with emotional data to calculate a more accurate NPS. For example, it can evaluate customer satisfaction based on emotional data after a specific post. The NPS calculation unit can also identify customer interests and trends based on social media activity data and reflect this in the NPS calculation. This allows for a more accurate NPS to be calculated by taking customer social media activity data into account.

[0084] The NPS calculation system can also collect customer feedback data, and the NPS calculation unit can take this into account when calculating the NPS. For example, the NPS calculation unit can evaluate fluctuations in satisfaction based on feedback and reviews provided by customers. The NPS calculation unit can also integrate feedback data with emotional data to calculate a more accurate NPS. For example, the NPS calculation unit can evaluate customer satisfaction based on emotional data after providing specific feedback. The NPS calculation unit can also identify customer opinions and requests based on feedback data and reflect them in the NPS calculation. This allows for a more accurate NPS to be calculated by taking customer feedback data into account.

[0085] The NPS calculation system can also collect customer location data, and the NPS calculation unit can take this into account when calculating the NPS. For example, fluctuations in satisfaction can be evaluated based on the area in which the customer uses the service. The NPS calculation unit can also integrate location data and emotional data to calculate a more accurate NPS. For example, customer satisfaction can be evaluated based on emotional data after using the service in a specific area. The NPS calculation unit can also identify customer behavior patterns based on location data and reflect this in the NPS calculation. In this way, by taking customer location data into account, a more accurate NPS can be calculated.

[0086] The NPS calculation system can further provide customized services tailored to customer needs based on customer emotional data. For example, if a customer is dissatisfied, it can provide a special offer. The NPS calculation unit can also identify customer needs based on emotional data and suggest customized services. For example, if a customer is happy, it can suggest additional services. The NPS calculation unit can also analyze emotional data in real time and respond according to customer needs. For example, if a customer is tense, it can make suggestions to help them relax. This makes it possible to provide customized services tailored to needs based on customer emotional data.

[0087] The NPS calculation system can also monitor customer satisfaction in real time based on customer emotional data and provide instant feedback. For example, it can display an alert if there is a sudden change in customer emotion. The NPS calculation unit can also build a system that evaluates customer satisfaction in real time based on emotional data and provides feedback. For example, it can suggest countermeasures if a customer feels dissatisfied. The NPS calculation unit can also monitor customer satisfaction in real time based on emotional data and take immediate action. For example, it can make suggestions to help a customer relax if they feel tense. This makes it possible to monitor customer satisfaction in real time based on customer emotional data and provide instant feedback.

[0088] The NPS calculation system can further identify fluctuations in customer satisfaction over the long term based on customer emotion data. For example, it evaluates current satisfaction based on past emotion data. The NPS calculation unit can also build a system that identifies fluctuations in customer satisfaction over the long term based on emotion data. For example, it tracks changes in satisfaction based on past data. The NPS calculation unit can also identify fluctuations in customer satisfaction over the long term based on emotion data and predict current satisfaction. This makes it possible to identify fluctuations in customer satisfaction over the long term based on customer emotion data.

[0089] The NPS calculation system can further calculate NPS based on customer emotional data, taking into account customer attribute information (age, gender, region, etc.). For example, differences in emotional expression due to age and gender can be taken into account. The NPS calculation unit can also build a system that calculates NPS based on emotional data, taking into account customer attribute information. For example, it can correct for differences in emotional expression between young and elderly customers. The NPS calculation unit can also develop an algorithm that calculates NPS based on emotional data, taking into account customer attribute information. For example, it can correct for differences in emotional expression between men and women. This makes it possible to calculate NPS based on customer emotional data, taking into account attribute information.

[0090] The NPS calculation system can also be applied to different industries and applications based on customer emotional data, allowing the generation AI to perform versatile NPS analysis. For example, it can analyze emotional data from healthcare, education, entertainment, and other fields. The NPS calculation unit can also develop a versatile NPS analysis algorithm based on emotional data to determine the NPS for different industries. For example, it takes into account differences in emotional expression between industries. The NPS calculation unit can also analyze NPS for different applications in real time based on emotional data, allowing the generation AI to determine the NPS. For example, it can analyze emotional data from customer service and education. This makes it possible to apply NPS analysis to different industries and applications based on customer emotional data, enabling versatile NPS analysis.

[0091] The processing flow of the second embodiment will be briefly explained below.

[0092] Step 1: The voice data collection unit collects voice data while serving customers or answering calls. For example, the voice data collection unit collects voice data in real time using a microphone. It can also analyze recorded data. The voice data collection unit collects the customer's tone of voice and speaking patterns. Step 2: The facial expression data collection unit collects facial expression data while serving customers or answering calls. For example, the facial expression data collection unit collects facial expression data in real time using a camera. It can also analyze recorded data. The facial expression data collection unit collects facial expressions and eye movements of customers. Step 3: The emotion analysis unit analyzes the voice data collected by the voice data collection unit and the facial expression data collected by the facial expression data collection unit to identify the customer's emotions. For example, the emotion analysis unit may use generative AI to analyze the voice data and facial expression data, and identify the customer's emotions using voice tone analysis and facial expression recognition technology. Step 4: The NPS calculation unit calculates the true NPS based on the emotional data identified by the emotion analysis unit, correcting for the tendency to center responses and the low response rate that are unique to Japanese people. For example, the emotion data can be analyzed using a generation AI, and the low response rate can be corrected using a statistical correction method.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0097] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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).

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0106] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0121] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0137] In the robot 414, 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. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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."

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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]

[0160] 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 voice data collection unit that collects voice data while serving customers or answering calls; a facial expression data collection unit that collects facial expression data while serving customers or answering calls; an emotion analysis unit that analyzes the voice data collected by the voice data collection unit and the facial expression data collected by the facial expression data collection unit to identify the emotion of the customer; and an NPS calculation unit that calculates a true NPS by correcting for the tendency to center responses and the low response rate that are unique to Japanese people based on the emotion data identified by the emotion analysis unit. A system characterized by:

2. The voice data collection unit The customer's background and environmental sounds are also collected at the same time, and the generation AI eliminates their influence to identify the emotion.

2. The system of claim 1.

3. The voice data collection unit Analyze not only the tone of the customer's voice, but also the speed at which they speak and the pauses they take to identify their emotions in more detail 2. The system of claim 1.

4. The voice data collection unit Estimate customer emotions in real time from the tone of their voice and provide instant feedback during the conversation.

2. The system of claim 1.

5. The voice data collection unit Expand voice data collection beyond phone calls to chatbots and email voice reading functions to perform multi-channel sentiment analysis.

2. The system of claim 1.

6. The voice data collection unit Collecting voice data in different languages, generative AI performs multilingual sentiment analysis 2. The system of claim 1.

Images