system

Abstract

The system according to the embodiment aims to analyze customer voice data in real time and evaluate emotions and satisfaction levels. [Solution] A system according to an embodiment includes a collection unit, a speech recognition unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects customer speech data. The speech recognition unit converts the speech data collected by the collection unit into text. The analysis unit analyzes the text data converted by the speech recognition unit and evaluates the customer's emotions and satisfaction. The generation unit generates feedback based on the results of the evaluation by the analysis unit. The provision unit provides the feedback generated by the generation unit.

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technologies, it is difficult to analyze customer voice data in real time and evaluate their emotions and satisfaction, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze customer voice data in real time and evaluate emotions and satisfaction levels. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a voice recognition unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects voice data of customers. The voice recognition unit converts the voice data collected by the collection unit into text. The analysis unit analyzes the text data converted by the voice recognition unit and evaluates the customer's emotions and satisfaction. The generation unit generates feedback based on the results of the evaluation by the analysis unit. The provision unit provides the feedback generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze customer voice data in real time to assess emotions and satisfaction. [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) An AI voice analysis system according to an embodiment of the present invention automatically collects customer voice data, converts it into text using a voice recognition AI, evaluates emotions and satisfaction levels using an analysis AI, and generates and provides feedback using a generation AI. The AI ​​voice analysis system collects customer voice data, converts it into text using a voice recognition AI, evaluates emotions and satisfaction levels using an analysis AI, and generates and provides feedback. For example, the AI ​​voice analysis system records the content of a customer's call to a call center and saves it as voice data. The voice recognition AI then converts the collected voice data into text. For example, if a customer says, "Please tell me how to use this product," the content is output as text data. The analysis AI then analyzes the text data and evaluates the customer's emotions and satisfaction levels. For example, if a customer says, "I'm very satisfied," the content is evaluated as high satisfaction. The generation AI then generates feedback based on the evaluation results. For example, if customer satisfaction is low, the system identifies the cause and generates feedback suggesting improvements. This allows the AI ​​voice analysis system to instantly process large amounts of data in real time and evaluate customer emotions and satisfaction levels. This allows the AI ​​voice analysis system to automatically analyze customer voice data and provide feedback. For example, it can analyze customer voice data quickly and accurately to improve service quality and customer satisfaction.

[0029] The AI ​​voice analysis system according to the embodiment includes a collection unit, a voice recognition unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects customer voice data. Examples of customer voice data include, but are not limited to, telephone conversations and recorded messages. The collection unit, for example, records the content of a conversation when a customer calls a call center and saves it as voice data. The collection unit can also collect voice data in real time. For example, the collection unit can record the content of a conversation from the moment a customer makes a call and save it as voice data. The voice recognition unit converts the voice data collected by the collection unit into text. For example, the voice recognition unit analyzes the voice data using voice recognition technology and outputs the customer's speech as text data. For example, if a customer says, "Please tell me how to use this product," the voice recognition unit outputs the content as text data. The voice recognition unit can also analyze the voice data using a voice recognition algorithm. For example, the voice recognition unit can use a voice recognition algorithm based on deep learning to perform highly accurate text conversion. The analysis unit analyzes the text data converted by the speech recognition unit and evaluates the customer's emotions and satisfaction. The analysis unit, for example, analyzes the content of the text data, the use of words, and the context to evaluate the customer's emotions and satisfaction. For example, if a customer says, "I am very satisfied," the analysis unit evaluates the customer's satisfaction level based on the content. The analysis unit can also analyze the text data using a sentiment analysis algorithm. For example, the analysis unit can analyze the emotions of the text data using natural language processing technology to evaluate the customer's emotions. The generation unit generates feedback based on the results of the evaluation by the analysis unit. The generation unit generates feedback for service improvement based on the results of the evaluation by, for example, an analysis AI. For example, if customer satisfaction is low, the generation unit generates feedback that identifies the cause and suggests improvement measures. The generation unit can also generate feedback using a generation AI. For example, the generation unit generates feedback for the customer using a text generation AI (e.g., LLM). The provision unit provides the feedback generated by the generation unit.The providing unit provides the generated feedback in real time, for example. For example, the providing unit sends the generated feedback to the customer as a text message. The providing unit can also provide the generated feedback as a periodic report. For example, the providing unit provides the generated feedback as a weekly report. This allows the AI ​​voice analysis system according to the embodiment to automatically analyze the voice data of the customer and provide feedback. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can provide the generated feedback using an AI model.

[0030] The collection unit can record the content of a conversation when a customer calls the call center and save it as audio data. For example, the collection unit can record the content of a conversation when a customer calls the call center and save it as audio data. The content of the conversation can include, but is not limited to, customer questions, complaints, and feedback. For example, when a customer asks about how to use a product, the collection unit can record the content of the conversation and save it as audio data. In addition, when a customer complains about a service, the collection unit can record the content of the conversation and save it as audio data. Furthermore, when a customer provides feedback about a service, the collection unit can record the content of the conversation and save it as audio data. This makes it possible to accurately collect and save the content of customer conversations. Some or all of the above-described processing in the collection unit can be performed, for example, using AI, or can be performed without using AI. For example, the collection unit can collect audio data using an AI model that records customer conversations and saves them as audio data.

[0031] The speech recognition unit can analyze speech data and output the customer's speech as text data. The speech recognition unit, for example, analyzes speech data and outputs the customer's speech as text data. For example, a speech recognition algorithm is used for the analysis, but the analysis is not limited to this example. For example, when a customer says, "Please tell me how to use the product," the speech recognition unit outputs the speech as text data. Furthermore, when a customer says, "I am satisfied with the service," the speech recognition unit can also output the speech as text data. Furthermore, when a customer says, "I have a complaint," the speech recognition unit can also output the speech as text data. This allows the speech data to be accurately converted into text data. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that analyzes speech data and outputs text data.

[0032] The analysis unit can evaluate customer emotions and satisfaction by analyzing the content, word usage, context, etc. of the text data. The analysis unit can evaluate customer emotions and satisfaction by analyzing, for example, the content, word usage, context, etc. of the text data. For example, a sentiment analysis algorithm can be used for the analysis, but is not limited to such an example. For example, if a customer says, "I am very satisfied," the analysis unit can evaluate high satisfaction based on the content. Furthermore, if a customer says, "I am dissatisfied," the analysis unit can also evaluate low satisfaction based on the content. Furthermore, if a customer says, "I am grateful for the service," the analysis unit can also evaluate positive emotions based on the content. This allows for accurate evaluation of customer emotions and satisfaction. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or can be performed without AI. For example, the analysis unit can analyze the text data using an AI model that analyzes the text data and evaluates customer emotions and satisfaction.

[0033] The generation unit can generate feedback for service improvement based on the evaluation results of the analysis AI. The generation unit generates feedback for service improvement based on, for example, the evaluation results of the analysis AI. For example, a generation AI is used for the generation, but this is not a limitation. For example, when customer satisfaction is low, the generation unit identifies the cause and generates feedback suggesting improvement measures. Furthermore, when customer satisfaction is high, the generation unit can analyze the factors and generate feedback for continuous service improvement. Furthermore, when customer emotions are positive, the generation unit can generate feedback to maintain those emotions. This makes it possible to automatically generate feedback for service improvement. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that inputs the evaluation results of the analysis AI and outputs feedback.

[0034] The providing unit can provide the generated feedback. For example, the providing unit provides the generated feedback. Providing includes, but is not limited to, providing in real time, for example. For example, the providing unit sends the generated feedback to the customer as a text message. The providing unit can also provide the generated feedback as a periodic report. For example, the providing unit provides the generated feedback as a weekly report. Furthermore, the providing unit can also provide the generated feedback as a voice message. For example, the providing unit sends the generated feedback to the customer as a voice message. This allows the generated feedback to be provided quickly. Some or all of the above-described processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can provide the generated feedback using an AI model.

[0035] The collection unit can analyze the customer's past call history and select the optimal collection method. For example, the collection unit analyzes the customer's past call history and selects the optimal collection method. For example, a call history analysis algorithm can be used for the analysis, but the analysis is not limited to this example. For example, if the customer has made long calls in the past, the collection unit can select a method to collect key points in a short time. Furthermore, if the customer has frequently made inquiries in the past, the collection unit can also select a method to collect detailed information. Furthermore, if the customer has made inquiries about a specific problem in the past, the collection unit can also select a method to prioritize collecting information related to that problem. This makes it possible to select the optimal collection method based on the customer's past call history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect voice data using an AI model that analyzes the customer's past call history and selects the optimal collection method.

[0036] The collection unit can filter the voice data based on the customer's current situation and areas of interest when collecting the voice data. For example, the collection unit can filter the voice data based on the customer's current situation and areas of interest when collecting the voice data. For example, a situation recognition algorithm can be used for filtering, but the example is not limited to this. For example, if a customer is interested in a current product, the collection unit can prioritize collecting information related to that product. Furthermore, if a customer is dissatisfied with a particular service, the collection unit can prioritize collecting information related to that service. Furthermore, if a customer is interested in a new product, the collection unit can collect information about that product. This allows the voice data to be filtered based on the customer's current situation and areas of interest. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect voice data using an AI model that filters the voice data based on the customer's current situation and areas of interest.

[0037] The collection unit can select the optimal collection means depending on the customer's input method when collecting voice data. For example, the collection unit selects the optimal collection means depending on the customer's input method when collecting voice data. For example, an input method recognition algorithm can be used for the selection, but is not limited to this example. For example, when a customer makes an inquiry by voice, the collection unit can preferentially collect voice data. Furthermore, when a customer makes an inquiry by text, the collection unit can also preferentially collect text data. Furthermore, when a customer submits an image, the collection unit can collect image data and supplement related information. This makes it possible to select the optimal collection means depending on the customer's input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect voice data using an AI model that selects the optimal collection means depending on the customer's input method.

[0038] When collecting voice data, the collection unit can prioritize collecting highly relevant data by taking into account the customer's geographical location information. For example, when collecting voice data, the collection unit prioritizes collecting highly relevant data by taking into account the customer's geographical location information. For example, a location information analysis algorithm can be used to consider the geographical location information, but this is not a limitation. For example, if a customer lives in a specific area, the collection unit can prioritize collecting information related to that area. Furthermore, if a customer is traveling, the collection unit can prioritize collecting information related to the customer's travel destination. Furthermore, if a customer visits a specific store, the collection unit can prioritize collecting information related to that store. This allows highly relevant data to be prioritized based on the customer's geographical location information. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect voice data using an AI model that prioritizes collecting highly relevant data by taking into account the customer's geographical location information.

[0039] The collection unit may analyze the customer's social media activities and collect related data when collecting the voice data. For example, the collection unit may analyze the customer's social media activities and collect related data when collecting the voice data. For example, a social media analysis algorithm may be used for the analysis, but is not limited to such an example. For example, the collection unit may collect the content of a post made by a customer about a product on social media. Furthermore, when a customer mentions a specific issue on social media, the collection unit may also collect information related to the issue. Furthermore, when a customer interacts with other users on social media, the collection unit may also collect the content of the interaction. This makes it possible to collect related data based on the customer's social media activities. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may collect voice data using an AI model that analyzes the customer's social media activities and collects related data.

[0040] The collection unit can customize the collection method by reflecting the customer's past feedback when collecting voice data. For example, the collection unit customizes the collection method by reflecting the customer's past feedback when collecting voice data. For example, a feedback analysis algorithm can be used for the customization, but the example is not limited to this. For example, if the customer has provided detailed feedback in the past, the collection unit can select a method to collect detailed information. Furthermore, if the customer has provided brief feedback in the past, the collection unit can select a method to collect brief information. Furthermore, if the customer has provided feedback about a specific issue in the past, the collection unit can select a method to preferentially collect information related to that issue. This makes it possible to customize the collection method based on the customer's past feedback. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect voice data using an AI model that customizes the collection method by reflecting the customer's past feedback.

[0041] The speech recognition unit can adjust the level of detail of the speech recognition based on the importance of the speech data during speech recognition. For example, the speech recognition unit adjusts the level of detail of the speech recognition based on the importance of the speech data during speech recognition. For example, an importance evaluation algorithm is used for the adjustment, but this example is not limited to this. For example, the speech recognition unit increases the level of detail of the speech recognition to generate accurate text data for an important inquiry. Furthermore, the speech recognition unit can maintain the level of detail of the speech recognition at a normal level for a general inquiry. Furthermore, the speech recognition unit can adjust the level of detail of the speech recognition to quickly generate text data for a simple inquiry. In this way, the level of detail of the speech recognition can be adjusted based on the importance of the speech data. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that adjusts the level of detail of the speech recognition based on the importance of the speech data.

[0042] The speech recognition unit can apply different recognition algorithms depending on the category of the speech during speech recognition. For example, the speech recognition unit applies different recognition algorithms depending on the category of the speech during speech recognition. For example, a category recognition algorithm is used for the application, but this example is not limited to this. For example, in the case of an inquiry about a product, the speech recognition unit applies a recognition algorithm specialized for the product. Furthermore, in the case of an inquiry about a service, the speech recognition unit can also apply a recognition algorithm specialized for the service. Furthermore, in the case of an inquiry about a complaint, the speech recognition unit can also apply a recognition algorithm specialized for the complaint. This makes it possible to apply the optimal recognition algorithm depending on the category of the speech. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that applies different recognition algorithms depending on the category of the speech.

[0043] The speech recognition unit can improve the accuracy of speech recognition by referring to the customer's past recognition results. For example, the speech recognition unit can improve the accuracy of speech recognition by referring to the customer's past recognition results. For example, a past recognition result analysis algorithm can be used as a reference, but is not limited to such an example. The speech recognition unit can improve the accuracy of recognition by referring to specific words or phrases used by the customer in the past. The speech recognition unit can also improve the accuracy of recognition by referring to feedback provided by the customer in the past. The speech recognition unit can also improve the accuracy of recognition by referring to inquiries made by the customer in the past. This allows the accuracy of recognition to be improved by referring to the customer's past recognition results. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that improves the accuracy of recognition by referring to the customer's past recognition results.

[0044] The speech recognition unit can determine the recognition priority based on the time when the speech data was submitted during speech recognition. For example, the speech recognition unit determines the recognition priority based on the time when the speech data was submitted during speech recognition. For example, a submission time evaluation algorithm is used for the determination, but this example is not limiting. For example, the speech recognition unit can prioritize recognition of the most recent speech data and quickly generate text data. The speech recognition unit can also sequentially recognize past speech data and generate text data. The speech recognition unit can also prioritize recognition of speech data submitted within a specific time period and generate text data. This makes it possible to determine the recognition priority based on the time when the speech data was submitted. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that determines the recognition priority based on the time when the speech data was submitted.

[0045] The speech recognition unit can adjust the order of recognition based on the relevance of the speech data during speech recognition. For example, the speech recognition unit adjusts the order of recognition based on the relevance of the speech data during speech recognition. For example, a relevance assessment algorithm is used for the adjustment, but this example is not limiting. For example, the speech recognition unit prioritizes recognition of important inquiry content and generates text data. The speech recognition unit can also sequentially recognize general inquiry content and generate text data. The speech recognition unit can also recognize simple inquiry content later and generate text data. This makes it possible to adjust the order of recognition based on the relevance of the speech data. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that adjusts the order of recognition based on the relevance of the speech data.

[0046] The speech recognition unit can adjust the use of technical terms for recognition according to the customer's level of expertise during speech recognition. For example, the speech recognition unit adjusts the use of technical terms for recognition according to the customer's level of expertise during speech recognition. For example, an expertise evaluation algorithm can be used for the adjustment, but this example is not limiting. For example, the speech recognition unit uses technical terms for recognition if the customer has specialized knowledge. Furthermore, the speech recognition unit can also use general terms for recognition if the customer has general knowledge. Furthermore, the speech recognition unit can also use simple terms for recognition if the customer is a beginner. This allows the use of technical terms for recognition to be adjusted according to the customer's level of expertise. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that adjusts the use of technical terms for recognition according to the customer's level of expertise.

[0047] The analysis unit can improve the accuracy of the analysis by taking into account the interrelationships of the text data during analysis. For example, the analysis unit can improve the accuracy of the analysis by taking into account the interrelationships of the text data during analysis. For example, a correlation analysis algorithm can be used for taking into account the interrelationships, but this example is not limited to this. For example, the analysis unit extracts related keywords from the text data and analyzes the interrelationships. The analysis unit can also analyze related information by taking into account the context in the text data. The analysis unit can also analyze the structure of phrases and sentences in the text data to clarify the interrelationships. This can improve the accuracy of the analysis by taking into account the interrelationships of the text data. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can analyze the text data using an AI model that takes into account the interrelationships of the text data to improve the accuracy of the analysis.

[0048] The analysis unit can perform analysis taking into account customer attribute information. For example, the analysis unit performs analysis taking into account customer attribute information. For example, an attribute information analysis algorithm is used for consideration, but this example is not limited to this. The analysis unit adjusts the analysis criteria taking into account, for example, the customer's age and gender. The analysis unit can also adjust the analysis criteria taking into account the customer's past purchase history. The analysis unit can also adjust the analysis criteria taking into account the customer's region and cultural background. This makes it possible to perform analysis taking into account customer attribute information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze text data using an AI model that performs analysis taking into account customer attribute information.

[0049] The analysis unit can weight the analysis based on the frequency of submission of text data during analysis. For example, the analysis unit weights the analysis based on the frequency of submission of text data during analysis. For example, a frequency evaluation algorithm is used for weighting, but this is not a limitation. For example, the analysis unit can set a high weight for frequently submitted text data and perform analysis. Furthermore, the analysis unit can also set a low weight for text data submitted only once and perform analysis. Furthermore, the analysis unit can adjust the weight for text data submitted multiple times within a specific period and perform analysis. In this way, the analysis can be weighted based on the frequency of submission of text data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze text data using an AI model that weights the analysis based on the frequency of submission of text data.

[0050] The analysis unit can perform the analysis while taking into account the geographical distribution of the text data. For example, the analysis unit performs the analysis while taking into account the geographical distribution of the text data. For example, a geographical distribution analysis algorithm can be used to take into account the geographical distribution, but this example is not limiting. For example, the analysis unit preferentially analyzes text data from a specific region. The analysis unit can also analyze text data from a wide geographical area evenly. The analysis unit can also adjust the analysis criteria while taking into account geographical bias. This allows the analysis to be performed while taking into account the geographical distribution of the text data. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze the text data using an AI model that performs analysis while taking into account the geographical distribution of the text data.

[0051] The analysis unit can improve the accuracy of the analysis by referring to related literature during analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to related literature during analysis. For example, a literature reference algorithm can be used for the reference, but this example is not limited to this. For example, the analysis unit can improve the accuracy of the analysis by referring to related academic papers. The analysis unit can also improve the accuracy of the analysis by referring to related industry reports. The analysis unit can also improve the accuracy of the analysis by referring to related patent documents. This can improve the accuracy of the analysis by referring to related literature. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can analyze text data using an AI model that improves the accuracy of the analysis by referring to related literature.

[0052] The analysis unit can perform the analysis taking into account the market value of the text data during analysis. For example, the analysis unit performs the analysis taking into account the market value of the text data during analysis. For example, a market value evaluation algorithm is used for the consideration, but this example is not limiting. For example, the analysis unit prioritizes the analysis of text data with a high market value. The analysis unit can also analyze text data with a low market value later. The analysis unit can also adjust the analysis criteria taking into account fluctuations in market value. This allows the analysis to be performed taking into account the market value of the text data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze the text data using an AI model that performs analysis taking into account the market value of the text data.

[0053] The generation unit can adjust the level of detail of the feedback based on the importance of the evaluation result when generating the feedback. For example, the generation unit adjusts the level of detail of the feedback based on the importance of the evaluation result when generating the feedback. For example, an importance evaluation algorithm is used for the adjustment, but this example is not limiting. For example, the generation unit generates detailed feedback for an important evaluation result. The generation unit can also generate normal feedback for a general evaluation result. The generation unit can also generate concise feedback for a simple evaluation result. In this way, the level of detail of the feedback can be adjusted based on the importance of the evaluation result. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that adjusts the level of detail of the feedback based on the importance of the evaluation result.

[0054] The generation unit can apply different generation algorithms depending on the category of the evaluation result when generating feedback. For example, the generation unit can apply different generation algorithms depending on the category of the evaluation result when generating feedback. For example, a category recognition algorithm can be used for the application, but this example is not limiting. For example, the generation unit can apply a product-specific generation algorithm to evaluation results related to a product. The generation unit can also apply a service-specific generation algorithm to evaluation results related to a service. The generation unit can also apply a complaint-specific generation algorithm to evaluation results related to a complaint. This makes it possible to apply an optimal generation algorithm depending on the category of the evaluation result. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that applies different generation algorithms depending on the category of the evaluation result.

[0055] The generation unit can improve the accuracy of feedback generation by referring to past feedback results. For example, the generation unit can improve the accuracy of feedback generation by referring to past feedback results. For example, a feedback result analysis algorithm can be used as a reference, but is not limited to such an example. For example, the generation unit can generate feedback for similar evaluation results by referring to feedback provided in the past. The generation unit can also analyze past feedback results and generate feedback that reflects improvements. The generation unit can also generate optimal feedback based on past feedback results. This can improve the accuracy of generation by referring to past feedback results. Some or all of the above-described processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that improves the accuracy of generation by referring to past feedback results.

[0056] The generation unit can determine the priority of feedback based on the submission time of the evaluation results when generating the feedback. For example, the generation unit determines the priority of feedback based on the submission time of the evaluation results when generating the feedback. For example, a submission time evaluation algorithm is used for the determination, but this example is not limiting. For example, the generation unit generates feedback preferentially for the most recent evaluation result. The generation unit can also generate feedback sequentially for past evaluation results. The generation unit can also generate feedback preferentially for evaluation results submitted within a specific period. This makes it possible to determine the priority of feedback based on the submission time of the evaluation results. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that determines the priority of feedback based on the submission time of the evaluation results.

[0057] The generation unit can adjust the order of feedback based on the relevance of the evaluation results when generating feedback. For example, the generation unit adjusts the order of feedback based on the relevance of the evaluation results when generating feedback. For example, a relevance assessment algorithm is used for the adjustment, but this example is not limiting. For example, the generation unit can generate feedback preferentially for important evaluation results. The generation unit can also generate feedback sequentially for general evaluation results. The generation unit can also generate feedback later for simple evaluation results. This makes it possible to adjust the order of feedback based on the relevance of the evaluation results. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that adjusts the order of feedback based on the relevance of the evaluation results.

[0058] The generation unit may adjust the use of technical terms in the feedback according to the customer's level of expertise when generating the feedback. For example, the generation unit may adjust the use of technical terms in the feedback according to the customer's level of expertise when generating the feedback. For example, an expertise evaluation algorithm may be used for the adjustment, but this example is not limited to this. For example, the generation unit may generate feedback using technical terms if the customer has specialized knowledge. Furthermore, the generation unit may generate feedback using general terms if the customer has general knowledge. Furthermore, the generation unit may generate feedback using simple terms if the customer is a beginner. This allows the use of technical terms in the feedback to be adjusted according to the customer's level of expertise. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may generate feedback using a generation AI model that adjusts the use of technical terms in the feedback according to the customer's level of expertise.

[0059] The providing unit can select the optimal feedback method by referring to the customer's past feedback history when providing feedback. For example, the providing unit can select the optimal feedback method by referring to the customer's past feedback history when providing feedback. For example, a feedback history analysis algorithm can be used for the reference, but this example is not limiting. For example, if the customer has provided detailed feedback in the past, the providing unit can select a method for providing detailed information. Furthermore, if the customer has provided brief feedback in the past, the providing unit can also select a method for providing brief information. Furthermore, if the customer has provided feedback on a specific issue in the past, the providing unit can also select a method for providing information related to the issue. This makes it possible to select the optimal feedback method based on the customer's past feedback history. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide feedback using an AI model that selects the optimal feedback method by referring to the customer's past feedback history.

[0060] The providing unit can customize the content of the offer based on the customer's current situation when providing feedback. For example, the providing unit customizes the content of the offer based on the customer's current situation when providing feedback. For example, a situation recognition algorithm can be used for the customization, but the example is not limited to this. For example, if the customer is interested in a current product, the providing unit can provide information related to the product. Furthermore, if the customer is dissatisfied with a particular service, the providing unit can provide information related to the service. Furthermore, if the customer is interested in a new product, the providing unit can provide information about the product. In this way, the content of the offer can be customized based on the customer's current situation. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide feedback using an AI model that customizes the content of the offer based on the customer's current situation.

[0061] The providing unit may select the optimal delivery method by taking into consideration the customer's device information when providing feedback. For example, the providing unit may select the optimal delivery method by taking into consideration the customer's device information when providing feedback. For example, a device information analysis algorithm may be used for the consideration, but is not limited to such an example. For example, if the customer is using a smartphone, the providing unit may provide a display method tailored to the screen size. Furthermore, if the customer is using a tablet, the providing unit may provide a display method optimized for a large screen. Furthermore, if the customer is using a smartwatch, the providing unit may provide a display method that is simple and highly visible. This allows the optimal delivery method to be selected based on the customer's device information. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may provide feedback using an AI model that selects the optimal delivery method by taking into consideration the customer's device information.

[0062] The providing unit can provide the feedback in multiple languages ​​according to the customer's language setting when providing the feedback. For example, the providing unit can provide the feedback in multiple languages ​​according to the customer's language setting when providing the feedback. For example, a language setting analysis algorithm can be used for this purpose, but the example is not limited thereto. For example, the providing unit can automatically set the language of the feedback based on the language setting of the customer's device. Furthermore, the providing unit can also provide a language switching function when the customer uses multiple languages. Furthermore, when the customer selects a specific language, the providing unit can provide the feedback in that language. This allows the feedback to be provided in multiple languages ​​according to the customer's language setting. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide feedback using an AI model that provides the feedback in multiple languages ​​according to the customer's language setting.

[0063] The providing unit may analyze the customer's social media activity and provide relevant information when providing feedback. For example, the providing unit may analyze the customer's social media activity and provide relevant information when providing feedback. For example, a social media analysis algorithm may be used for the analysis, but is not limited to such an example. For example, the providing unit may provide information about places where the customer has checked in on social media. The providing unit may also analyze the customer's social media posts and provide information about related tourist spots and stores. The providing unit may also provide information about related places and events based on the activities of the customer's friends on social media. This makes it possible to provide relevant information based on the customer's social media activity. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may provide feedback using an AI model that analyzes the customer's social media activity and provides relevant information.

[0064] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0065] When collecting customer voice data, the collection unit can refer to the customer's past purchase history and prioritize collection of information about related products and services. For example, if a customer has purchased a specific product in the past, inquiries and feedback about that product can be collected with priority. Also, if a customer has used the same service multiple times in the past, information about that service can be collected with priority. Furthermore, if a customer has inquired about a specific problem in the past, information related to that problem can be collected with priority. This makes it possible to select the optimal collection method based on the customer's past purchase history.

[0066] When analyzing voice data, the speech recognition unit can refer to a related external database based on the content of what the customer says to obtain additional information. For example, if a customer inquires about a specific product, the latest manuals and FAQs related to that product can be obtained from an external database. Also, if a customer asks about a specific service, the latest update information on that service can be obtained. Furthermore, if a customer complains about a specific problem, solutions related to that problem can be obtained from an external database. This allows the speech recognition unit to provide related additional information based on the content of what the customer says.

[0067] When generating feedback, the generation unit can refer to the customer's past feedback history and generate feedback that reflects the content of the past feedback. For example, if a customer has provided feedback about a specific problem in the past, feedback that proposes the latest solution related to that problem can be generated. Also, if a customer has shown high satisfaction with a specific service in the past, feedback that encourages continued use of that service can be generated. Furthermore, if a customer has provided detailed feedback about a specific product in the past, feedback that provides the latest information about that product can be generated. This makes it possible to generate optimal feedback based on the customer's past feedback history.

[0068] When collecting a customer's voice data, the collection unit can adjust the collection method based on the customer's current situation and environment. For example, if the customer is in a noisy environment, the collection unit can collect voice data using noise canceling technology. If the customer is in a quiet environment, the collection unit can collect voice data using a normal method. Furthermore, if the customer is on the move, the collection unit can collect voice data using a mobile device. This makes it possible to select the optimal collection method depending on the customer's current situation and environment.

[0069] When analyzing voice data, the speech recognition unit can refer to relevant internal databases based on what the customer said to obtain additional information. For example, if a customer inquires about a specific product, the internal manual or troubleshooting guide for that product can be referenced. Also, if a customer asks about a specific service, internal documentation for that service can be referenced. Furthermore, if a customer complains about a specific problem, internal solutions related to that problem can be referenced. This allows the speech recognition unit to provide relevant additional information based on what the customer said.

[0070] When generating feedback, the generation unit can customize the feedback content based on the customer's current situation and environment. For example, if a customer is interested in a current product, feedback including information related to that product can be generated. Also, if a customer is dissatisfied with a specific service, feedback suggesting improvements related to that service can be generated. Furthermore, if a customer is interested in a new product, feedback providing information about that product can be generated. This makes it possible to generate optimal feedback based on the customer's current situation and environment.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The collection unit collects customer voice data. Customer voice data includes, for example, telephone conversations and recorded messages. The collection unit records the content of conversations when customers call the call center and saves it as voice data. It is also possible to collect voice data in real time. Step 2: The speech recognition unit converts the voice data collected by the collection unit into text. The speech recognition unit uses speech recognition technology to analyze the voice data and output the customer's speech as text data. For example, it uses a speech recognition algorithm that uses deep learning to perform highly accurate text conversion. Step 3: The analysis unit analyzes the text data converted by the speech recognition unit and evaluates the customer's emotions and satisfaction. The analysis unit analyzes the content of the text data, the use of words, the context, etc., and evaluates the customer's emotions and satisfaction. For example, natural language processing technology is used to analyze the emotions in the text data and evaluate the customer's emotions. Step 4: The generation unit generates feedback based on the results evaluated by the analysis unit. The generation unit generates feedback for service improvement based on the results evaluated by the analysis AI. For example, feedback for customers is generated using a text generation AI (e.g., LLM). Step 5: The providing unit provides the feedback generated by the generating unit. The providing unit provides the generated feedback in real time. For example, the generated feedback may be sent to the customer as a text message. Alternatively, the generated feedback may be provided as a periodic report.

[0073] (Example 2) An AI voice analysis system according to an embodiment of the present invention automatically collects customer voice data, converts it into text using a voice recognition AI, evaluates emotions and satisfaction levels using an analysis AI, and generates and provides feedback using a generation AI. The AI ​​voice analysis system collects customer voice data, converts it into text using a voice recognition AI, evaluates emotions and satisfaction levels using an analysis AI, and generates and provides feedback. For example, the AI ​​voice analysis system records the content of a customer's call to a call center and saves it as voice data. The voice recognition AI then converts the collected voice data into text. For example, if a customer says, "Please tell me how to use this product," the content is output as text data. The analysis AI then analyzes the text data and evaluates the customer's emotions and satisfaction levels. For example, if a customer says, "I'm very satisfied," the content is evaluated as high satisfaction. The generation AI then generates feedback based on the evaluation results. For example, if customer satisfaction is low, the system identifies the cause and generates feedback suggesting improvements. This allows the AI ​​voice analysis system to instantly process large amounts of data in real time and evaluate customer emotions and satisfaction levels. This allows the AI ​​voice analysis system to automatically analyze customer voice data and provide feedback. For example, it can analyze customer voice data quickly and accurately to improve service quality and customer satisfaction.

[0074] The AI ​​voice analysis system according to the embodiment includes a collection unit, a voice recognition unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects customer voice data. Examples of customer voice data include, but are not limited to, telephone conversations and recorded messages. The collection unit, for example, records the content of a conversation when a customer calls a call center and saves it as voice data. The collection unit can also collect voice data in real time. For example, the collection unit can record the content of a conversation from the moment a customer makes a call and save it as voice data. The voice recognition unit converts the voice data collected by the collection unit into text. For example, the voice recognition unit analyzes the voice data using voice recognition technology and outputs the customer's speech as text data. For example, if a customer says, "Please tell me how to use this product," the voice recognition unit outputs the content as text data. The voice recognition unit can also analyze the voice data using a voice recognition algorithm. For example, the voice recognition unit can use a voice recognition algorithm based on deep learning to perform highly accurate text conversion. The analysis unit analyzes the text data converted by the speech recognition unit and evaluates the customer's emotions and satisfaction. The analysis unit, for example, analyzes the content of the text data, the use of words, and the context to evaluate the customer's emotions and satisfaction. For example, if a customer says, "I am very satisfied," the analysis unit evaluates the customer's satisfaction level based on the content. The analysis unit can also analyze the text data using a sentiment analysis algorithm. For example, the analysis unit can analyze the emotions of the text data using natural language processing technology to evaluate the customer's emotions. The generation unit generates feedback based on the results of the evaluation by the analysis unit. The generation unit generates feedback for service improvement based on the results of the evaluation by, for example, an analysis AI. For example, if customer satisfaction is low, the generation unit generates feedback that identifies the cause and suggests improvement measures. The generation unit can also generate feedback using a generation AI. For example, the generation unit generates feedback for the customer using a text generation AI (e.g., LLM). The provision unit provides the feedback generated by the generation unit.The providing unit provides the generated feedback in real time, for example. For example, the providing unit sends the generated feedback to the customer as a text message. The providing unit can also provide the generated feedback as a periodic report. For example, the providing unit provides the generated feedback as a weekly report. This allows the AI ​​voice analysis system according to the embodiment to automatically analyze the voice data of the customer and provide feedback. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can provide the generated feedback using an AI model.

[0075] The collection unit can record the content of a conversation when a customer calls the call center and save it as audio data. For example, the collection unit can record the content of a conversation when a customer calls the call center and save it as audio data. The content of the conversation can include, but is not limited to, customer questions, complaints, and feedback. For example, when a customer asks about how to use a product, the collection unit can record the content of the conversation and save it as audio data. In addition, when a customer complains about a service, the collection unit can record the content of the conversation and save it as audio data. Furthermore, when a customer provides feedback about a service, the collection unit can record the content of the conversation and save it as audio data. This makes it possible to accurately collect and save the content of customer conversations. Some or all of the above-described processing in the collection unit can be performed, for example, using AI, or can be performed without using AI. For example, the collection unit can collect audio data using an AI model that records customer conversations and saves them as audio data.

[0076] The speech recognition unit can analyze speech data and output the customer's speech as text data. The speech recognition unit, for example, analyzes speech data and outputs the customer's speech as text data. For example, a speech recognition algorithm is used for the analysis, but the analysis is not limited to this example. For example, when a customer says, "Please tell me how to use the product," the speech recognition unit outputs the speech as text data. Furthermore, when a customer says, "I am satisfied with the service," the speech recognition unit can also output the speech as text data. Furthermore, when a customer says, "I have a complaint," the speech recognition unit can also output the speech as text data. This allows the speech data to be accurately converted into text data. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that analyzes speech data and outputs text data.

[0077] The analysis unit can evaluate customer emotions and satisfaction by analyzing the content, word usage, context, etc. of the text data. The analysis unit can evaluate customer emotions and satisfaction by analyzing, for example, the content, word usage, context, etc. of the text data. For example, a sentiment analysis algorithm can be used for the analysis, but is not limited to such an example. For example, if a customer says, "I am very satisfied," the analysis unit can evaluate high satisfaction based on the content. Furthermore, if a customer says, "I am dissatisfied," the analysis unit can also evaluate low satisfaction based on the content. Furthermore, if a customer says, "I am grateful for the service," the analysis unit can also evaluate positive emotions based on the content. This allows for accurate evaluation of customer emotions and satisfaction. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or can be performed without AI. For example, the analysis unit can analyze the text data using an AI model that analyzes the text data and evaluates customer emotions and satisfaction.

[0078] The generation unit can generate feedback for service improvement based on the evaluation results of the analysis AI. The generation unit generates feedback for service improvement based on, for example, the evaluation results of the analysis AI. For example, a generation AI is used for the generation, but this is not a limitation. For example, when customer satisfaction is low, the generation unit identifies the cause and generates feedback suggesting improvement measures. Furthermore, when customer satisfaction is high, the generation unit can analyze the factors and generate feedback for continuous service improvement. Furthermore, when customer emotions are positive, the generation unit can generate feedback to maintain those emotions. This makes it possible to automatically generate feedback for service improvement. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that inputs the evaluation results of the analysis AI and outputs feedback.

[0079] The providing unit can provide the generated feedback. For example, the providing unit provides the generated feedback. Providing includes, but is not limited to, providing in real time, for example. For example, the providing unit sends the generated feedback to the customer as a text message. The providing unit can also provide the generated feedback as a periodic report. For example, the providing unit provides the generated feedback as a weekly report. Furthermore, the providing unit can also provide the generated feedback as a voice message. For example, the providing unit sends the generated feedback to the customer as a voice message. This allows the generated feedback to be provided quickly. Some or all of the above-described processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can provide the generated feedback using an AI model.

[0080] The collection unit can estimate the customer's emotions and adjust the timing of collecting voice data based on the estimated customer emotions. For example, the collection unit can estimate the customer's emotions and adjust the timing of collecting voice data based on the estimated customer emotions. For example, an emotion estimation algorithm can be used for the estimation, but the example is not limited to this. For example, if the customer is angry, the collection unit can collect voice data at the beginning of the conversation to resolve the problem quickly. Furthermore, if the customer is relaxed, the collection unit can collect voice data in the middle of the conversation to obtain detailed information. Furthermore, if the customer is in a hurry, the collection unit can collect voice data at the end of the conversation to grasp the main points. This allows voice data to be collected at the optimal timing depending on the customer's emotions. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect voice data using an AI model that estimates the customer's emotions and adjusts the timing of collecting voice data based on the estimated emotions.

[0081] The collection unit can analyze the customer's past call history and select the optimal collection method. For example, the collection unit analyzes the customer's past call history and selects the optimal collection method. For example, a call history analysis algorithm can be used for the analysis, but the analysis is not limited to this example. For example, if the customer has made long calls in the past, the collection unit can select a method to collect key points in a short time. Furthermore, if the customer has frequently made inquiries in the past, the collection unit can also select a method to collect detailed information. Furthermore, if the customer has made inquiries about a specific problem in the past, the collection unit can also select a method to prioritize collecting information related to that problem. This makes it possible to select the optimal collection method based on the customer's past call history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect voice data using an AI model that analyzes the customer's past call history and selects the optimal collection method.

[0082] The collection unit can filter the voice data based on the customer's current situation and areas of interest when collecting the voice data. For example, the collection unit can filter the voice data based on the customer's current situation and areas of interest when collecting the voice data. For example, a situation recognition algorithm can be used for filtering, but the example is not limited to this. For example, if a customer is interested in a current product, the collection unit can prioritize collecting information related to that product. Furthermore, if a customer is dissatisfied with a particular service, the collection unit can prioritize collecting information related to that service. Furthermore, if a customer is interested in a new product, the collection unit can collect information about that product. This allows the voice data to be filtered based on the customer's current situation and areas of interest. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect voice data using an AI model that filters the voice data based on the customer's current situation and areas of interest.

[0083] The collection unit can select the optimal collection means depending on the customer's input method when collecting voice data. For example, the collection unit selects the optimal collection means depending on the customer's input method when collecting voice data. For example, an input method recognition algorithm can be used for the selection, but is not limited to this example. For example, when a customer makes an inquiry by voice, the collection unit can preferentially collect voice data. Furthermore, when a customer makes an inquiry by text, the collection unit can also preferentially collect text data. Furthermore, when a customer submits an image, the collection unit can collect image data and supplement related information. This makes it possible to select the optimal collection means depending on the customer's input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect voice data using an AI model that selects the optimal collection means depending on the customer's input method.

[0084] The collection unit can estimate a customer's emotions and prioritize the voice data to be collected based on the estimated customer emotions. The collection unit, for example, estimates a customer's emotions and prioritizes the voice data to be collected based on the estimated customer emotions. For example, an emotion estimation algorithm is used for the estimation, but the method is not limited to this example. For example, if a customer is angry, the collection unit prioritizes collecting the content of the conversation and responds promptly. Furthermore, if a customer is satisfied, the collection unit can prioritize collecting feedback and use it to improve services. Furthermore, if a customer is feeling anxious, the collection unit can prioritize collecting information to identify the cause of the anxiety. This makes it possible to prioritize the voice data based on the customer's emotions. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect voice data using an AI model that estimates a customer's emotions and prioritizes the voice data based on the estimated emotions.

[0085] When collecting voice data, the collection unit can prioritize collecting highly relevant data by taking into account the customer's geographical location information. For example, when collecting voice data, the collection unit prioritizes collecting highly relevant data by taking into account the customer's geographical location information. For example, a location information analysis algorithm can be used to consider the geographical location information, but this is not a limitation. For example, if a customer lives in a specific area, the collection unit can prioritize collecting information related to that area. Furthermore, if a customer is traveling, the collection unit can prioritize collecting information related to the customer's travel destination. Furthermore, if a customer visits a specific store, the collection unit can prioritize collecting information related to that store. This allows highly relevant data to be prioritized based on the customer's geographical location information. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect voice data using an AI model that prioritizes collecting highly relevant data by taking into account the customer's geographical location information.

[0086] The collection unit may analyze the customer's social media activities and collect related data when collecting the voice data. For example, the collection unit may analyze the customer's social media activities and collect related data when collecting the voice data. For example, a social media analysis algorithm may be used for the analysis, but is not limited to such an example. For example, the collection unit may collect the content of a post made by a customer about a product on social media. Furthermore, when a customer mentions a specific issue on social media, the collection unit may also collect information related to the issue. Furthermore, when a customer interacts with other users on social media, the collection unit may also collect the content of the interaction. This makes it possible to collect related data based on the customer's social media activities. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may collect voice data using an AI model that analyzes the customer's social media activities and collects related data.

[0087] The collection unit can customize the collection method by reflecting the customer's past feedback when collecting voice data. For example, the collection unit customizes the collection method by reflecting the customer's past feedback when collecting voice data. For example, a feedback analysis algorithm can be used for the customization, but the example is not limited to this. For example, if the customer has provided detailed feedback in the past, the collection unit can select a method to collect detailed information. Furthermore, if the customer has provided brief feedback in the past, the collection unit can select a method to collect brief information. Furthermore, if the customer has provided feedback about a specific issue in the past, the collection unit can select a method to preferentially collect information related to that issue. This makes it possible to customize the collection method based on the customer's past feedback. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect voice data using an AI model that customizes the collection method by reflecting the customer's past feedback.

[0088] The speech recognition unit can estimate a customer's emotion and adjust the accuracy of speech recognition based on the estimated emotion. The speech recognition unit, for example, estimates a customer's emotion and adjusts the accuracy of speech recognition based on the estimated emotion. For example, an emotion estimation algorithm is used for the estimation, but this example is not limited to this. For example, if the customer is angry, the speech recognition unit increases the accuracy of speech recognition to generate accurate text data. Furthermore, if the customer is relaxed, the speech recognition unit can maintain the accuracy of speech recognition at normal levels. Furthermore, if the customer is in a hurry, the speech recognition unit can adjust the accuracy of speech recognition to quickly generate text data. This allows the accuracy of speech recognition to be adjusted based on the customer's emotion. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that estimates a customer's emotion and adjusts the accuracy of speech recognition based on the estimated emotion.

[0089] The speech recognition unit can adjust the level of detail of the speech recognition based on the importance of the speech data during speech recognition. For example, the speech recognition unit adjusts the level of detail of the speech recognition based on the importance of the speech data during speech recognition. For example, an importance evaluation algorithm is used for the adjustment, but this example is not limited to this. For example, the speech recognition unit increases the level of detail of the speech recognition to generate accurate text data for an important inquiry. Furthermore, the speech recognition unit can maintain the level of detail of the speech recognition at a normal level for a general inquiry. Furthermore, the speech recognition unit can adjust the level of detail of the speech recognition to quickly generate text data for a simple inquiry. In this way, the level of detail of the speech recognition can be adjusted based on the importance of the speech data. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that adjusts the level of detail of the speech recognition based on the importance of the speech data.

[0090] The speech recognition unit can apply different recognition algorithms depending on the category of the speech during speech recognition. For example, the speech recognition unit applies different recognition algorithms depending on the category of the speech during speech recognition. For example, a category recognition algorithm is used for the application, but this example is not limited to this. For example, in the case of an inquiry about a product, the speech recognition unit applies a recognition algorithm specialized for the product. Furthermore, in the case of an inquiry about a service, the speech recognition unit can also apply a recognition algorithm specialized for the service. Furthermore, in the case of an inquiry about a complaint, the speech recognition unit can also apply a recognition algorithm specialized for the complaint. This makes it possible to apply the optimal recognition algorithm depending on the category of the speech. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that applies different recognition algorithms depending on the category of the speech.

[0091] The speech recognition unit can improve the accuracy of speech recognition by referring to the customer's past recognition results. For example, the speech recognition unit can improve the accuracy of speech recognition by referring to the customer's past recognition results. For example, a past recognition result analysis algorithm can be used as a reference, but is not limited to such an example. The speech recognition unit can improve the accuracy of recognition by referring to specific words or phrases used by the customer in the past. The speech recognition unit can also improve the accuracy of recognition by referring to feedback provided by the customer in the past. The speech recognition unit can also improve the accuracy of recognition by referring to inquiries made by the customer in the past. This allows the accuracy of recognition to be improved by referring to the customer's past recognition results. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that improves the accuracy of recognition by referring to the customer's past recognition results.

[0092] The speech recognition unit can estimate the customer's emotion and adjust the speech recognition speed based on the estimated customer's emotion. For example, the speech recognition unit can estimate the customer's emotion and adjust the speech recognition speed based on the estimated customer's emotion. For example, an emotion estimation algorithm can be used for the estimation, but this example is not limiting. For example, if the customer is in a hurry, the speech recognition unit can increase the speech recognition speed to quickly generate text data. Furthermore, if the customer is relaxed, the speech recognition unit can maintain the speech recognition speed at a normal level. Furthermore, if the customer is angry, the speech recognition unit can adjust the speech recognition speed to generate accurate text data. This makes it possible to adjust the speech recognition speed based on the customer's emotion. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that estimates the customer's emotion and adjusts the speech recognition speed based on the estimated emotion.

[0093] The speech recognition unit can determine the recognition priority based on the time when the speech data was submitted during speech recognition. For example, the speech recognition unit determines the recognition priority based on the time when the speech data was submitted during speech recognition. For example, a submission time evaluation algorithm is used for the determination, but this example is not limiting. For example, the speech recognition unit can prioritize recognition of the most recent speech data and quickly generate text data. The speech recognition unit can also sequentially recognize past speech data and generate text data. The speech recognition unit can also prioritize recognition of speech data submitted within a specific time period and generate text data. This makes it possible to determine the recognition priority based on the time when the speech data was submitted. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that determines the recognition priority based on the time when the speech data was submitted.

[0094] The speech recognition unit can adjust the order of recognition based on the relevance of the speech data during speech recognition. For example, the speech recognition unit adjusts the order of recognition based on the relevance of the speech data during speech recognition. For example, a relevance assessment algorithm is used for the adjustment, but this example is not limiting. For example, the speech recognition unit prioritizes recognition of important inquiry content and generates text data. The speech recognition unit can also sequentially recognize general inquiry content and generate text data. The speech recognition unit can also recognize simple inquiry content later and generate text data. This makes it possible to adjust the order of recognition based on the relevance of the speech data. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that adjusts the order of recognition based on the relevance of the speech data.

[0095] The speech recognition unit can adjust the use of technical terms for recognition according to the customer's level of expertise during speech recognition. For example, the speech recognition unit adjusts the use of technical terms for recognition according to the customer's level of expertise during speech recognition. For example, an expertise evaluation algorithm can be used for the adjustment, but this example is not limiting. For example, the speech recognition unit uses technical terms for recognition if the customer has specialized knowledge. Furthermore, the speech recognition unit can also use general terms for recognition if the customer has general knowledge. Furthermore, the speech recognition unit can also use simple terms for recognition if the customer is a beginner. This allows the use of technical terms for recognition to be adjusted according to the customer's level of expertise. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can convert speech data into text data using an AI model that adjusts the use of technical terms for recognition according to the customer's level of expertise.

[0096] The analysis unit can estimate the customer's emotions and adjust the analysis criteria based on the estimated customer emotions. For example, the analysis unit can estimate the customer's emotions and adjust the analysis criteria based on the estimated customer emotions. For example, an emotion estimation algorithm can be used for the estimation, but this is not a limitation. For example, if the customer is angry, the analysis unit can perform analysis by emphasizing the intensity of the emotion. Furthermore, if the customer is relaxed, the analysis unit can perform analysis by emphasizing the balance of the emotion. Furthermore, if the customer is in a hurry, the analysis unit can perform analysis by emphasizing important points. This allows the analysis criteria to be adjusted based on the customer's emotions. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze text data using an AI model that estimates the customer's emotions and adjusts the analysis criteria based on the estimated emotions.

[0097] The analysis unit can improve the accuracy of the analysis by taking into account the interrelationships of the text data during analysis. For example, the analysis unit can improve the accuracy of the analysis by taking into account the interrelationships of the text data during analysis. For example, a correlation analysis algorithm can be used for taking into account the interrelationships, but this example is not limited to this. For example, the analysis unit extracts related keywords from the text data and analyzes the interrelationships. The analysis unit can also analyze related information by taking into account the context in the text data. The analysis unit can also analyze the structure of phrases and sentences in the text data to clarify the interrelationships. This can improve the accuracy of the analysis by taking into account the interrelationships of the text data. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can analyze the text data using an AI model that takes into account the interrelationships of the text data to improve the accuracy of the analysis.

[0098] The analysis unit can perform analysis taking into account customer attribute information. For example, the analysis unit performs analysis taking into account customer attribute information. For example, an attribute information analysis algorithm is used for consideration, but this example is not limited to this. The analysis unit adjusts the analysis criteria taking into account, for example, the customer's age and gender. The analysis unit can also adjust the analysis criteria taking into account the customer's past purchase history. The analysis unit can also adjust the analysis criteria taking into account the customer's region and cultural background. This makes it possible to perform analysis taking into account customer attribute information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze text data using an AI model that performs analysis taking into account customer attribute information.

[0099] The analysis unit can weight the analysis based on the frequency of submission of text data during analysis. For example, the analysis unit weights the analysis based on the frequency of submission of text data during analysis. For example, a frequency evaluation algorithm is used for weighting, but this is not a limitation. For example, the analysis unit can set a high weight for frequently submitted text data and perform analysis. Furthermore, the analysis unit can also set a low weight for text data submitted only once and perform analysis. Furthermore, the analysis unit can adjust the weight for text data submitted multiple times within a specific period and perform analysis. In this way, the analysis can be weighted based on the frequency of submission of text data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze text data using an AI model that weights the analysis based on the frequency of submission of text data.

[0100] The analysis unit can estimate the customer's emotions and adjust the display order of the analysis results based on the estimated customer emotions. The analysis unit, for example, estimates the customer's emotions and adjusts the display order of the analysis results based on the estimated customer emotions. For example, an emotion estimation algorithm is used for the estimation, but the example is not limited to this. For example, if the customer is angry, the analysis unit can display important issues first. Furthermore, if the customer is relaxed, the analysis unit can also adjust the display order taking into account the overall balance. Furthermore, if the customer is in a hurry, the analysis unit can also display results that highlight the main points first. This makes it possible to adjust the display order of the analysis results based on the customer's emotions. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze text data using an AI model that estimates the customer's emotions and adjusts the display order of the analysis results based on the estimated emotions.

[0101] The analysis unit can perform the analysis while taking into account the geographical distribution of the text data. For example, the analysis unit performs the analysis while taking into account the geographical distribution of the text data. For example, a geographical distribution analysis algorithm can be used to take into account the geographical distribution, but this example is not limiting. For example, the analysis unit preferentially analyzes text data from a specific region. The analysis unit can also analyze text data from a wide geographical area evenly. The analysis unit can also adjust the analysis criteria while taking into account geographical bias. This allows the analysis to be performed while taking into account the geographical distribution of the text data. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze the text data using an AI model that performs analysis while taking into account the geographical distribution of the text data.

[0102] The analysis unit can improve the accuracy of the analysis by referring to related literature during analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to related literature during analysis. For example, a literature reference algorithm can be used for the reference, but this example is not limited to this. For example, the analysis unit can improve the accuracy of the analysis by referring to related academic papers. The analysis unit can also improve the accuracy of the analysis by referring to related industry reports. The analysis unit can also improve the accuracy of the analysis by referring to related patent documents. This can improve the accuracy of the analysis by referring to related literature. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can analyze text data using an AI model that improves the accuracy of the analysis by referring to related literature.

[0103] The analysis unit can perform the analysis taking into account the market value of the text data during analysis. For example, the analysis unit performs the analysis taking into account the market value of the text data during analysis. For example, a market value evaluation algorithm is used for the consideration, but this example is not limiting. For example, the analysis unit prioritizes the analysis of text data with a high market value. The analysis unit can also analyze text data with a low market value later. The analysis unit can also adjust the analysis criteria taking into account fluctuations in market value. This allows the analysis to be performed taking into account the market value of the text data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze the text data using an AI model that performs analysis taking into account the market value of the text data.

[0104] The generation unit can estimate the customer's emotions and adjust the feedback generation method based on the estimated customer emotions. For example, the generation unit can estimate the customer's emotions and adjust the feedback generation method based on the estimated customer emotions. For example, an emotion estimation algorithm can be used for the estimation, but this example is not limiting. For example, if the customer is angry, the generation unit can generate feedback that suggests quick and specific improvement measures. Furthermore, if the customer is relaxed, the generation unit can generate feedback that includes detailed explanations. Furthermore, if the customer is in a hurry, the generation unit can generate concise and to-the-point feedback. This allows the feedback generation method to be adjusted based on the customer's emotions. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that estimates the customer's emotions and adjusts the feedback generation method based on the estimated emotions.

[0105] The generation unit can adjust the level of detail of the feedback based on the importance of the evaluation result when generating the feedback. For example, the generation unit adjusts the level of detail of the feedback based on the importance of the evaluation result when generating the feedback. For example, an importance evaluation algorithm is used for the adjustment, but this example is not limiting. For example, the generation unit generates detailed feedback for an important evaluation result. The generation unit can also generate normal feedback for a general evaluation result. The generation unit can also generate concise feedback for a simple evaluation result. In this way, the level of detail of the feedback can be adjusted based on the importance of the evaluation result. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that adjusts the level of detail of the feedback based on the importance of the evaluation result.

[0106] The generation unit can apply different generation algorithms depending on the category of the evaluation result when generating feedback. For example, the generation unit can apply different generation algorithms depending on the category of the evaluation result when generating feedback. For example, a category recognition algorithm can be used for the application, but this example is not limiting. For example, the generation unit can apply a product-specific generation algorithm to evaluation results related to a product. The generation unit can also apply a service-specific generation algorithm to evaluation results related to a service. The generation unit can also apply a complaint-specific generation algorithm to evaluation results related to a complaint. This makes it possible to apply an optimal generation algorithm depending on the category of the evaluation result. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that applies different generation algorithms depending on the category of the evaluation result.

[0107] The generation unit can improve the accuracy of feedback generation by referring to past feedback results. For example, the generation unit can improve the accuracy of feedback generation by referring to past feedback results. For example, a feedback result analysis algorithm can be used as a reference, but is not limited to such an example. For example, the generation unit can generate feedback for similar evaluation results by referring to feedback provided in the past. The generation unit can also analyze past feedback results and generate feedback that reflects improvements. The generation unit can also generate optimal feedback based on past feedback results. This can improve the accuracy of generation by referring to past feedback results. Some or all of the above-described processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that improves the accuracy of generation by referring to past feedback results.

[0108] The generation unit can estimate the customer's emotions and adjust the length of the feedback based on the estimated customer emotions. For example, the generation unit can estimate the customer's emotions and adjust the length of the feedback based on the estimated customer emotions. For example, an emotion estimation algorithm can be used for the estimation, but this example is not limiting. For example, the generation unit can generate short and to-the-point feedback when the customer is in a hurry. Furthermore, the generation unit can generate longer feedback including detailed explanations when the customer is relaxed. Furthermore, the generation unit can generate feedback that suggests quick and specific improvement measures when the customer is angry. This allows the length of the feedback to be adjusted based on the customer's emotions. Some or all of the above-described processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that estimates the customer's emotions and adjusts the length of the feedback based on the estimated emotions.

[0109] The generation unit can determine the priority of feedback based on the submission time of the evaluation results when generating the feedback. For example, the generation unit determines the priority of feedback based on the submission time of the evaluation results when generating the feedback. For example, a submission time evaluation algorithm is used for the determination, but this example is not limiting. For example, the generation unit generates feedback preferentially for the most recent evaluation result. The generation unit can also generate feedback sequentially for past evaluation results. The generation unit can also generate feedback preferentially for evaluation results submitted within a specific period. This makes it possible to determine the priority of feedback based on the submission time of the evaluation results. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that determines the priority of feedback based on the submission time of the evaluation results.

[0110] The generation unit can adjust the order of feedback based on the relevance of the evaluation results when generating feedback. For example, the generation unit adjusts the order of feedback based on the relevance of the evaluation results when generating feedback. For example, a relevance assessment algorithm is used for the adjustment, but this example is not limiting. For example, the generation unit can generate feedback preferentially for important evaluation results. The generation unit can also generate feedback sequentially for general evaluation results. The generation unit can also generate feedback later for simple evaluation results. This makes it possible to adjust the order of feedback based on the relevance of the evaluation results. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate feedback using a generation AI model that adjusts the order of feedback based on the relevance of the evaluation results.

[0111] The generation unit may adjust the use of technical terms in the feedback according to the customer's level of expertise when generating the feedback. For example, the generation unit may adjust the use of technical terms in the feedback according to the customer's level of expertise when generating the feedback. For example, an expertise evaluation algorithm may be used for the adjustment, but this example is not limited to this. For example, the generation unit may generate feedback using technical terms if the customer has specialized knowledge. Furthermore, the generation unit may generate feedback using general terms if the customer has general knowledge. Furthermore, the generation unit may generate feedback using simple terms if the customer is a beginner. This allows the use of technical terms in the feedback to be adjusted according to the customer's level of expertise. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may generate feedback using a generation AI model that adjusts the use of technical terms in the feedback according to the customer's level of expertise.

[0112] The providing unit can estimate the customer's emotions and adjust the feedback provision method based on the estimated customer emotions. For example, the providing unit can estimate the customer's emotions and adjust the feedback provision method based on the estimated customer emotions. For example, an emotion estimation algorithm can be used for the estimation, but this example is not limited to this. For example, if the customer is angry, the providing unit can provide feedback that suggests quick and specific improvement measures. Furthermore, if the customer is relaxed, the providing unit can provide feedback that includes detailed explanations. Furthermore, if the customer is in a hurry, the providing unit can provide concise and to-the-point feedback. This makes it possible to adjust the feedback provision method based on the customer's emotions. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide feedback using an AI model that estimates the customer's emotions and adjusts the feedback provision method based on the estimated emotions.

[0113] The providing unit can select the optimal feedback method by referring to the customer's past feedback history when providing feedback. For example, the providing unit can select the optimal feedback method by referring to the customer's past feedback history when providing feedback. For example, a feedback history analysis algorithm can be used for the reference, but this example is not limiting. For example, if the customer has provided detailed feedback in the past, the providing unit can select a method for providing detailed information. Furthermore, if the customer has provided brief feedback in the past, the providing unit can also select a method for providing brief information. Furthermore, if the customer has provided feedback on a specific issue in the past, the providing unit can also select a method for providing information related to the issue. This makes it possible to select the optimal feedback method based on the customer's past feedback history. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide feedback using an AI model that selects the optimal feedback method by referring to the customer's past feedback history.

[0114] The providing unit can customize the content of the offer based on the customer's current situation when providing feedback. For example, the providing unit customizes the content of the offer based on the customer's current situation when providing feedback. For example, a situation recognition algorithm can be used for the customization, but the example is not limited to this. For example, if the customer is interested in a current product, the providing unit can provide information related to the product. Furthermore, if the customer is dissatisfied with a particular service, the providing unit can provide information related to the service. Furthermore, if the customer is interested in a new product, the providing unit can provide information about the product. In this way, the content of the offer can be customized based on the customer's current situation. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide feedback using an AI model that customizes the content of the offer based on the customer's current situation.

[0115] The providing unit can estimate the customer's emotions and adjust the feedback provision procedure based on the estimated customer emotions. For example, the providing unit can estimate the customer's emotions and adjust the feedback provision procedure based on the estimated customer emotions. For example, an emotion estimation algorithm can be used for the estimation, but this example is not limiting. For example, if the customer is angry, the providing unit can provide feedback that suggests quick and specific improvement measures. Furthermore, if the customer is relaxed, the providing unit can provide feedback that includes detailed explanations. Furthermore, if the customer is in a hurry, the providing unit can provide concise and to-the-point feedback. This makes it possible to adjust the feedback provision procedure based on the customer's emotions. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide feedback using an AI model that estimates the customer's emotions and adjusts the feedback provision procedure based on the estimated emotions.

[0116] The providing unit may select the optimal delivery method by taking into consideration the customer's device information when providing feedback. For example, the providing unit may select the optimal delivery method by taking into consideration the customer's device information when providing feedback. For example, a device information analysis algorithm may be used for the consideration, but is not limited to such an example. For example, if the customer is using a smartphone, the providing unit may provide a display method tailored to the screen size. Furthermore, if the customer is using a tablet, the providing unit may provide a display method optimized for a large screen. Furthermore, if the customer is using a smartwatch, the providing unit may provide a display method that is simple and highly visible. This allows the optimal delivery method to be selected based on the customer's device information. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may provide feedback using an AI model that selects the optimal delivery method by taking into consideration the customer's device information.

[0117] The providing unit can provide the feedback in multiple languages ​​according to the customer's language setting when providing the feedback. For example, the providing unit can provide the feedback in multiple languages ​​according to the customer's language setting when providing the feedback. For example, a language setting analysis algorithm can be used for this purpose, but the example is not limited thereto. For example, the providing unit can automatically set the language of the feedback based on the language setting of the customer's device. Furthermore, the providing unit can also provide a language switching function when the customer uses multiple languages. Furthermore, when the customer selects a specific language, the providing unit can provide the feedback in that language. This allows the feedback to be provided in multiple languages ​​according to the customer's language setting. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide feedback using an AI model that provides the feedback in multiple languages ​​according to the customer's language setting.

[0118] The providing unit may analyze the customer's social media activity and provide relevant information when providing feedback. For example, the providing unit may analyze the customer's social media activity and provide relevant information when providing feedback. For example, a social media analysis algorithm may be used for the analysis, but is not limited to such an example. For example, the providing unit may provide information about places where the customer has checked in on social media. The providing unit may also analyze the customer's social media posts and provide information about related tourist spots and stores. The providing unit may also provide information about related places and events based on the activities of the customer's friends on social media. This makes it possible to provide relevant information based on the customer's social media activity. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may provide feedback using an AI model that analyzes the customer's social media activity and provides relevant information. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, voice recognition unit, analysis unit, generation unit, and provision unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects customer voice data using the camera 42 and microphone 38B of the smart device 14 and stores the voice data using the control unit 46A. The voice recognition unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, converts the collected voice data into text. The analysis unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, analyzes the text data and evaluates the customer's emotions and satisfaction. The generation unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, generates feedback based on the evaluation results. The provision unit, implemented, for example, by the control unit 46A of the smart device 14, provides the generated feedback to the customer. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, voice recognition unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects customer voice data using the camera 42 and microphone 238 of the smart glasses 214 and stores the voice data using the control unit 46A. The voice recognition unit, realized, for example, by the specific processing unit 290 of the data processing device 12, converts the collected voice data into text. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the text data and evaluates the customer's emotions and satisfaction. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates feedback based on the evaluation results. The provision unit, realized, for example, by the control unit 46A of the smart glasses 214, provides the generated feedback to the customer. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, voice recognition unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects customer voice data using the camera 42 and microphone 238 of the headset-type terminal 314 and stores the voice data using the control unit 46A. The voice recognition unit, realized, for example, by the specific processing unit 290 of the data processing device 12, converts the collected voice data into text. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the text data and evaluates the customer's emotions and satisfaction. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates feedback based on the evaluation results. The provision unit, realized, for example, by the control unit 46A of the headset-type terminal 314, provides the generated feedback to the customer. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, voice recognition unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects customer voice data using the camera 42 and microphone 238 of the robot 414 and stores the voice data using the control unit 46A. The voice recognition unit, realized, for example, by the specific processing unit 290 of the data processing device 12, converts the collected voice data into text. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the text data and evaluates the customer's emotions and satisfaction. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates feedback based on the evaluation results. The provision unit, realized, for example, by the control unit 46A of the robot 414, provides the generated feedback to the customer.

[0119] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0120] When collecting customer voice data, the collection unit can refer to the customer's past purchase history and prioritize collection of information about related products and services. For example, if a customer has purchased a specific product in the past, inquiries and feedback about that product can be collected with priority. Also, if a customer has used the same service multiple times in the past, information about that service can be collected with priority. Furthermore, if a customer has inquired about a specific problem in the past, information related to that problem can be collected with priority. This makes it possible to select the optimal collection method based on the customer's past purchase history.

[0121] When analyzing voice data, the speech recognition unit can refer to a related external database based on the content of what the customer says to obtain additional information. For example, if a customer inquires about a specific product, the latest manuals and FAQs related to that product can be obtained from an external database. Also, if a customer asks about a specific service, the latest update information on that service can be obtained. Furthermore, if a customer complains about a specific problem, solutions related to that problem can be obtained from an external database. This allows the speech recognition unit to provide related additional information based on the content of what the customer says.

[0122] When analyzing text data, the analysis unit can estimate the customer's emotions and determine the analysis priority based on the estimated emotions. For example, if a customer is very dissatisfied, the analysis of that text data can be prioritized and a quick response can be made. Also, if a customer is very satisfied, the analysis of that feedback can be prioritized and used to improve services. Furthermore, if a customer has neutral emotions, the analysis of that text data can be performed with normal priority. This makes it possible to adjust the analysis priority based on the customer's emotions.

[0123] When generating feedback, the generation unit can refer to the customer's past feedback history and generate feedback that reflects the content of the past feedback. For example, if a customer has provided feedback about a specific problem in the past, feedback that proposes the latest solution related to that problem can be generated. Also, if a customer has shown high satisfaction with a specific service in the past, feedback that encourages continued use of that service can be generated. Furthermore, if a customer has provided detailed feedback about a specific product in the past, feedback that provides the latest information about that product can be generated. This makes it possible to generate optimal feedback based on the customer's past feedback history.

[0124] The providing unit can estimate the customer's emotions when providing the generated feedback and adjust the method of providing the feedback based on the estimated emotions. For example, if the customer is very dissatisfied, the providing unit can provide feedback that suggests quick and specific improvement measures. Also, if the customer is very satisfied, the providing unit can provide feedback to maintain the customer's satisfaction. Furthermore, if the customer has neutral emotions, the providing unit can provide normal feedback. This makes it possible to select the optimal feedback providing method based on the customer's emotions.

[0125] When collecting a customer's voice data, the collection unit can adjust the collection method based on the customer's current situation and environment. For example, if the customer is in a noisy environment, the collection unit can collect voice data using noise canceling technology. If the customer is in a quiet environment, the collection unit can collect voice data using a normal method. Furthermore, if the customer is on the move, the collection unit can collect voice data using a mobile device. This makes it possible to select the optimal collection method depending on the customer's current situation and environment.

[0126] When analyzing voice data, the speech recognition unit can refer to relevant internal databases based on what the customer said to obtain additional information. For example, if a customer inquires about a specific product, the internal manual or troubleshooting guide for that product can be referenced. Also, if a customer asks about a specific service, internal documentation for that service can be referenced. Furthermore, if a customer complains about a specific problem, internal solutions related to that problem can be referenced. This allows the speech recognition unit to provide relevant additional information based on what the customer said.

[0127] When analyzing text data, the analysis unit can estimate customer sentiment and adjust the level of analysis detail based on the estimated sentiment. For example, if a customer is highly dissatisfied, the text data can be analyzed in detail to identify the root cause of the problem. Alternatively, if a customer is highly satisfied, the feedback can be analyzed in detail to identify success factors. Furthermore, if a customer has neutral sentiment, the text data can be analyzed at a normal level of detail. This allows the level of analysis detail to be adjusted based on customer sentiment.

[0128] When generating feedback, the generation unit can customize the feedback content based on the customer's current situation and environment. For example, if a customer is interested in a current product, feedback including information related to that product can be generated. Also, if a customer is dissatisfied with a specific service, feedback suggesting improvements related to that service can be generated. Furthermore, if a customer is interested in a new product, feedback providing information about that product can be generated. This makes it possible to generate optimal feedback based on the customer's current situation and environment.

[0129] The providing unit can estimate the customer's emotions when providing the generated feedback and adjust the providing procedure based on the estimated emotions. For example, if the customer is very dissatisfied, feedback that suggests quick and specific improvement measures can be provided first. Also, if the customer is very satisfied, feedback to maintain the customer's satisfaction can be provided first. Furthermore, if the customer has neutral emotions, normal feedback can be provided. This makes it possible to select the optimal feedback providing procedure based on the customer's emotions.

[0130] The processing flow of the second embodiment will be briefly explained below.

[0131] Step 1: The collection unit collects customer voice data. Customer voice data includes, for example, telephone conversations and recorded messages. The collection unit records the content of conversations when customers call the call center and saves it as voice data. It is also possible to collect voice data in real time. Step 2: The speech recognition unit converts the voice data collected by the collection unit into text. The speech recognition unit uses speech recognition technology to analyze the voice data and output the customer's speech as text data. For example, it uses a speech recognition algorithm that uses deep learning to perform highly accurate text conversion. Step 3: The analysis unit analyzes the text data converted by the speech recognition unit and evaluates the customer's emotions and satisfaction. The analysis unit analyzes the content of the text data, the use of words, the context, etc., and evaluates the customer's emotions and satisfaction. For example, natural language processing technology is used to analyze the emotions in the text data and evaluate the customer's emotions. Step 4: The generation unit generates feedback based on the results evaluated by the analysis unit. The generation unit generates feedback for service improvement based on the results evaluated by the analysis AI. For example, feedback for customers is generated using a text generation AI (e.g., LLM). Step 5: The providing unit provides the feedback generated by the generating unit. The providing unit provides the generated feedback in real time. For example, the generated feedback may be sent to the customer as a text message. Alternatively, the generated feedback may be provided as a periodic report.

[0132] 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.

[0133] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0134] 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.

[0135] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0136] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0137] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0145] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0146] 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.

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

[0148] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0150] The data processing system 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.

[0151] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0152] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 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 identification processing unit 290 using these models.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0168] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification 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 the same process as the identification processing unit 290 using these models.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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).

[0189] 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.

[0190] 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."

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] [Explanation of symbols]

[0204] 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 collection unit that collects customer voice data; a speech recognition unit that converts the speech data collected by the collection unit into text; an analysis unit that analyzes the text data converted by the speech recognition unit and evaluates customer emotions and satisfaction; a generation unit that generates feedback based on the results of the evaluation by the analysis unit; a providing unit that provides the feedback generated by the generating unit. A system characterized by:

2. The collecting unit Record the conversations that customers make with the call center and save them as audio data.

2. The system of claim 1.

3. The voice recognition unit Analyzes voice data and outputs what the customer says as text data 2. The system of claim 1.

4. The analysis unit Analyze the content, word usage, and context of text data to evaluate customer sentiment and satisfaction 2. The system of claim 1.

5. The generation unit Based on the results of the analysis AI evaluation, feedback is generated to improve the service.

2. The system of claim 1.

6. The providing unit Provide generated feedback 2. The system of claim 1.

7. The collecting unit Estimate customer sentiment and adjust the timing of voice data collection based on the estimated sentiment 2. The system of claim 1.

8. The collecting unit Analyze customer call history and select the best collection method 2. The system of claim 1.

Images