system

Abstract

The system according to the embodiment aims to analyze customer comments and convert customer satisfaction into a score. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, and a provision unit. The reception unit receives customer comments. The analysis unit analyzes the comments received by the reception unit and converts the comments into a score representing customer satisfaction. The provision unit provides the results of the score generated by the analysis 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] Conventional techniques have not been able to efficiently analyze customer comments and convert customer satisfaction into a score, so there is room for improvement.

[0005] The system according to the embodiment aims to analyze customer comments and convert customer satisfaction into a score. [Means for solving the problem]

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, and a provision unit. The reception unit receives customer comments. The analysis unit analyzes the comments received by the reception unit and assigns a score to customer satisfaction. The provision unit provides the score assigned by the analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can analyze customer comments and assign a score to customer 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) A customer satisfaction evaluation system according to an embodiment of the present invention uses NPS (Net Promoter Score) survey data to score customer satisfaction. This customer satisfaction evaluation system limits customer evaluations to comments only, omitting score evaluations. Next, a generation AI (generation AI) is used to analyze customer comments and generate a score for customer satisfaction. This system is expected to shorten customer response time and improve response rates. It also makes it possible to evaluate the difference between comments and score evaluations using a unified standard. First, customers enter comments into the NPS survey. For example, they may enter comments such as "The staff's service was excellent" or "I'm satisfied with the quality of the product." These comments are then input into the generation AI. Next, the generation AI analyzes the entered comments. The generation AI uses natural language processing technology to understand the content of the comments and generate a score for customer satisfaction. For example, a comment such as "very good" is assigned a high score, and a comment such as "improvement required" is assigned a low score. The customer satisfaction scores generated by the generation AI are evaluated using a unified standard. This eliminates the discrepancy between comments and score ratings, enabling more accurate evaluation of customer satisfaction. This system is expected to shorten the time it takes for customers to respond and improve the response rate. It also makes it possible to evaluate the discrepancy between comments and score ratings using a unified standard, improving the fairness of customer service evaluations. This allows the customer satisfaction evaluation system to efficiently accept and analyze customer comments and provide scored results.

[0029] The customer satisfaction evaluation system according to this embodiment comprises a reception unit, an analysis unit, and a provision unit. The reception unit receives customer comments. Customer comments include, but are not limited to, text comments, voice comments, and evaluation comments. The reception unit receives text comments, for example, through an input form. The reception unit can also receive voice comments through a microphone. Furthermore, the reception unit can also receive evaluation comments in the form of multiple-choice options. For example, the reception unit stores the text comments entered by the customer in a database. Voice comments are converted into text data using speech recognition technology. Evaluation comments are stored in the database as the result of selecting options. The analysis unit uses a generation AI to analyze the comments received by the reception unit and assigns a score to customer satisfaction. The analysis unit uses, for example, natural language processing technology to understand the content of the comments and assign a score. For example, the generation AI analyzes the comments using a text generation AI (e.g., LLM). The analysis unit can also use a multimodal generation AI to analyze voice comments and evaluation comments. For example, the generating AI assigns a score based on the sentiment score of the comment. The service unit provides the scored results, which are then analyzed by the service unit. The service unit then provides feedback to the customer, for example, by displaying the scored results to the customer through a web application or mobile application. If the customer prefers feedback in paper form, the results are printed using a printer. Sending the results via email provides quick feedback by directly sending the results to the customer. Thus, the customer satisfaction evaluation system according to this embodiment can efficiently receive, analyze, and provide scored results from customer comments.

[0030] The customer satisfaction evaluation system includes a classification unit that categorizes customer comments. The classification unit classifies customer comments. The classification unit uses methods such as category classification, sentiment classification, and topic classification. For example, category classification classifies comments into specific categories. Sentiment classification analyzes the sentiment of comments and classifies them into positive, negative, neutral, etc. Topic classification extracts the topic of a comment and classifies it into related topics. For example, the classification unit uses natural language processing technology to analyze the content of comments and perform category classification. Sentiment classification evaluates the sentiment of comments using sentiment analysis algorithms. Topic classification extracts the topic of a comment using a topic model. By classifying customer comments in this way, the accuracy of the analysis is improved. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can perform classification using an AI model that takes comments as input and outputs categories, sentiments, and topics.

[0031] The analysis unit can understand the content of comments and assign scores using natural language processing techniques. The analysis unit uses natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis. For example, morphological analysis divides the comment into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the comment and understands the sentence structure. Semantic analysis analyzes the meaning of the comment and understands the context. For example, the analysis unit uses morphological analysis to divide the comment into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the comment and understands the sentence structure. Semantic analysis analyzes the meaning of the comment and understands the context. As a result, by using natural language processing techniques, the content of comments can be accurately understood and scores can be assigned. Some or all of the above processing in the analysis unit may be performed using, for example, generative AI, or without generative AI. For example, the analysis unit can assign scores using a generative AI model that takes comments as input and outputs scores.

[0032] The customer satisfaction evaluation system includes a suggestion unit that suggests specific improvements based on the scored results. The suggestion unit suggests specific improvements based on the scored results. The suggestion unit suggests improvements based on, for example, the analysis results of customer feedback and industry benchmarks. For example, the suggestion unit suggests improvements for a specific service or product based on the analysis results of customer feedback. The industry benchmark suggests improvements by comparing with other companies' services or products. For example, the suggestion unit suggests improvements for a specific service or product based on the analysis results of customer feedback. The industry benchmark suggests improvements by comparing with other companies' services or products. In this way, by suggesting specific improvements based on the scored results, it is possible to expect an improvement in customer satisfaction. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can suggest improvements using an AI model that receives the scored results as input and outputs improvements.

[0033] The reception unit can analyze the customer's past comment history and select the optimal reception method. The reception unit, for example, prompts the customer to enter comments based on the time period in which the customer frequently entered comments in the past. For example, the reception unit prioritizes suggesting an input method (voice, text, etc.) that the customer has used in the past. The reception unit can also prioritize accepting comments on a specific topic based on the customer's past comment history. For example, the reception unit prompts the customer to enter comments based on the time period in which the customer frequently entered comments in the past. The reception unit prioritizes suggesting an input method (voice, text, etc.) that the customer has used in the past. The reception unit prioritizes accepting comments on a specific topic based on the customer's past comment history. In this way, the optimal reception method can be selected by analyzing the customer's past comment history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can select the reception method using an AI model that inputs the customer's past comment history and outputs the optimal reception method.

[0034] When receiving comments, the reception unit can filter them based on the customer's current purchasing history and areas of interest. For example, the reception unit prioritizes receiving comments about products recently purchased by the customer. For example, the reception unit prioritizes receiving comments on topics related to the customer's areas of interest. The reception unit can also filter and receive comments about specific products or services from the customer's purchasing history. For example, the reception unit prioritizes receiving comments about products recently purchased by the customer. The reception unit prioritizes receiving comments on topics related to the customer's areas of interest. The reception unit can filter and receive comments about specific products or services from the customer's purchasing history. In this way, by filtering based on the customer's current purchasing history and areas of interest, highly relevant comments can be preferentially received. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can perform filtering using an AI model that inputs data on the customer's purchasing history and areas of interest and outputs filtered results.

[0035] When receiving comments, the reception unit can prioritize receiving highly relevant comments based on the customer's geographical location information. For example, when a customer visits a specific store, the reception unit prioritizes receiving comments related to the store. For example, if the customer lives in a specific area, the reception unit prioritizes receiving comments related to the area. Furthermore, when a customer is traveling, the reception unit can also prioritize receiving comments related to the area they visited. For example, when a customer visits a specific store, the reception unit prioritizes receiving comments related to the store. If the customer lives in a specific area, the reception unit prioritizes receiving comments related to the area. If the customer is traveling, the reception unit prioritizes receiving comments related to the area they visited. This makes it possible to prioritize receiving highly relevant comments by taking the customer's geographical location information into consideration. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can perform filtering using an AI model that inputs the customer's geographical location information and outputs highly relevant comments.

[0036] The reception desk can analyze the customer's social media activity when receiving comments and receive relevant comments. For example, the reception desk can prioritize receiving comments about products or services mentioned by the customer on social media. For example, the reception desk can receive comments on topics of high interest based on the customer's social media activity. The reception desk can also prioritize receiving comments about brands that the customer follows on social media. For example, the reception desk can prioritize receiving comments about products or services mentioned by the customer on social media. For example, the reception desk can prioritize receiving comments about products or services mentioned by the customer on social media. For example, the reception desk can receive comments on topics of high interest based on the customer's social media activity. For example, the reception desk can filter comments using an AI model that takes customer social media activity data as input and outputs relevant comments.

[0037] The analysis unit can adjust the level of detail in scoring based on the importance of the comments during analysis. For example, the analysis unit can assign detailed scores to important comments and apply fine-grained evaluation criteria. For example, the analysis unit can assign standard scores to general comments and apply basic evaluation criteria. The analysis unit can also assign simplified scores to less important comments and apply simple evaluation criteria. For example, the analysis unit can assign detailed scores to important comments and apply fine-grained evaluation criteria. For general comments, it can assign standard scores and apply basic evaluation criteria. For less important comments, it can assign simplified scores and apply simple evaluation criteria. This allows for detailed evaluation of important comments by adjusting the level of detail in scoring based on the importance of the comments. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can adjust the level of detail using a generative AI model that takes comment importance data as input and outputs the level of detail in scoring.

[0038] The analysis unit can apply different scoring algorithms to comments depending on their category during analysis. For example, the analysis unit can apply a service-specific scoring algorithm to comments about services. For example, the analysis unit can apply a product-specific scoring algorithm to comments about products. The analysis unit can also apply a support-specific scoring algorithm to comments about support. For example, the analysis unit can apply a service-specific scoring algorithm to comments about services. For comments about products, it can apply a product-specific scoring algorithm. For comments about support, it can apply a support-specific scoring algorithm. This allows for more appropriate scoring by applying different scoring algorithms depending on the category of the comment. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can apply an algorithm using a generative AI model that takes comment category data as input and outputs a scoring algorithm.

[0039] The analysis unit can determine the priority of scoring based on the submission date of comments during analysis. For example, the analysis unit may prioritize scoring the most recent comments and perform a rapid evaluation. For example, the analysis unit may adjust the scoring priority according to the submission date while referring to past comments. The analysis unit can also prioritize scoring comments submitted within a specific period and evaluate comments from that period. For example, the analysis unit may prioritize scoring the most recent comments and perform a rapid evaluation. For example, the analysis unit may adjust the scoring priority according to the submission date while referring to past comments. For example, it may prioritize scoring comments submitted within a specific period and evaluate comments from that period. This allows for a rapid evaluation of the most recent comments by determining the scoring priority based on the submission date of the comments. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit may determine the priority using a generative AI model that takes comment submission date data as input and outputs the scoring priority.

[0040] During analysis, the analysis unit can adjust the scoring order based on the relevance of the comments. For example, if a customer's comment is related to a specific topic, the analysis unit prioritizes scoring the comment. For example, if a customer's comment is highly relevant to other comments, the analysis unit prioritizes scoring the comment. The analysis unit can also prioritize scoring the customer's comment if it is related to a specific issue. For example, if a customer's comment is related to a specific topic, the analysis unit prioritizes scoring the comment. If a customer's comment is highly relevant to other comments, the analysis unit prioritizes scoring the comment. In this way, by adjusting the scoring order based on the relevance of the comments, highly relevant comments can be prioritized for evaluation. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generative AI, or may be performed without using a generative AI. For example, the analysis unit can adjust the order using a generative AI model that inputs comment relevance data and outputs a scoring order.

[0041] The service provider can adjust the level of detail provided based on the importance of the scored results at the time of delivery. For example, the service provider can add detailed explanations and specific suggestions for improvement to important results. For example, the service provider can add standard explanations and basic suggestions for improvement to general results. The service provider can also add simplified explanations and simple suggestions for improvement to less important results. For example, the service provider can add detailed explanations and specific suggestions for improvement to important results. For general results, it can add standard explanations and basic suggestions for improvement. For less important results, it can add simplified explanations and simple suggestions for improvement. This allows for detailed feedback on important results by adjusting the level of detail provided based on the importance of the scored results. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can adjust the level of detail using an AI model that takes the importance data of the scored results as input and outputs the level of detail provided.

[0042] The service provider can apply different service provision algorithms depending on the category of the scored result at the time of provision. For example, the service provider can apply a service-specific service provision algorithm to results related to services. For example, the service provider can apply a product-specific service provision algorithm to results related to products. The service provider can also apply a support-specific service provision algorithm to results related to support. For example, the service provider can apply a service-specific service provision algorithm to results related to services. For results related to products, it can apply a product-specific service provision algorithm. For results related to support, it can apply a support-specific service provision algorithm. This allows for more appropriate feedback to be provided by applying different service provision algorithms depending on the category of the scored result. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can apply an algorithm using an AI model that takes the category data of the scored result as input and outputs a service provision algorithm.

[0043] The service provider can determine the priority of service provision based on the submission timing of the scored results. For example, the service provider can prioritize providing the latest results and provide prompt feedback. For example, the service provider can adjust the priority of service provision according to the submission timing, while referring to past results. The service provider can also prioritize providing results submitted within a specific period and provide feedback for that period. For example, the service provider can prioritize providing the latest results and provide prompt feedback. For example, the service provider can adjust the priority of service provision according to the submission timing, while referring to past results. For example, it can prioritize providing results submitted within a specific period and provide feedback for that period. This allows for the rapid provision of the latest results by determining the priority of service provision based on the submission timing of the scored results. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can determine the priority using an AI model that takes the submission timing data of scored results as input and outputs the priority of service provision.

[0044] The providing unit can adjust the order of providing the results based on the relevance of the scored results when providing them. For example, the providing unit can prioritize providing a customer's result if the customer's result is related to a specific topic. For example, the providing unit can prioritize providing a customer's result if the customer's result is highly relevant to other results. The providing unit can also prioritize providing a customer's result if the customer's result is related to a specific problem. For example, the providing unit can prioritize providing a customer's result if the customer's result is related to a specific topic. For example, the providing unit can prioritize providing a customer's result if the customer's result is highly relevant to other results. For example, the providing unit can prioritize providing a customer's result if the customer's result is related to a specific problem. In this way, by adjusting the order of providing based on the relevance of the scored results, it is possible to prioritize providing highly relevant results. 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 adjust the order using an AI model that receives relevance data of the scored results as input and outputs the order of providing.

[0045] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0046] When accepting customer comments, the reception unit can analyze the customer's past purchasing history and behavioral patterns and automatically generate optimal questions. For example, it can generate questions that ask for feedback on products the customer has purchased in the past. It can also generate questions about stores the customer frequently visits. It can also send optimal questions for specific times of day based on the customer's behavioral patterns. This can be expected to improve the response rate by providing questions based on the customer's interests.

[0047] When classifying customer comments, the classification unit can take into account not only the content of the comment but also the customer's past feedback history and purchasing history. For example, comments from customers who have provided a lot of positive feedback in the past can be preferentially classified into a positive category. Also, comments from customers who have provided negative feedback on specific products in the past can be classified into a negative category. Furthermore, based on the customer's purchasing history, it is possible to automatically extract comments related to specific products or services and classify them into appropriate categories. This enables highly accurate classification that takes into account the customer's past behavior.

[0048] The analysis unit uses natural language processing technology to understand the content of comments and can take the context of the comments into account when assigning scores. For example, if a comment is related to a specific event or campaign, the score can be adjusted taking that context into account. Also, if a comment is related to other comments, the score can be assigned taking that relevance into account. Furthermore, if comments are concentrated within a specific period, the score can be adjusted taking into account the trends of that period. This allows for more accurate scoring that takes the context of the comments into account.

[0049] The suggestion unit can take into account the customer's past feedback history and purchase history when proposing specific improvements based on the scoring results. For example, for a customer who has provided negative feedback about a particular product in the past, the suggestion unit can suggest specific improvements for that product. Also, for a customer who has provided a lot of positive feedback in the past, new suggestions can be made based on that feedback. Furthermore, it is possible to suggest improvements related to specific products or services based on the customer's purchase history. This makes it possible to propose specific improvements that take into account the customer's past behavior.

[0050] The reception desk can analyze a customer's past comment history and select the most suitable reception method. For example, it can prompt customers to submit comments at times when they frequently posted comments in the past. It can also prioritize suggesting input methods (voice, text, etc.) that customers have used in the past. Based on the customer's past comment history, it can also prioritize accepting comments on specific topics. In this way, by analyzing a customer's past comment history, the optimal reception method can be selected.

[0051] The reception system can filter comments based on the customer's current purchase history and areas of interest. For example, it can prioritize comments about products the customer has recently purchased, or comments on topics related to the customer's areas of interest. It can also filter comments based on the customer's purchase history to focus on specific products or services. This allows for prioritizing the reception of highly relevant comments by filtering based on the customer's current purchase history and areas of interest.

[0052] The reception desk can prioritize comments based on the customer's geographical location when receiving comments. For example, if a customer has visited a particular store, comments related to that store will be prioritized. If a customer lives in a specific region, comments related to that region will be prioritized. If a customer is traveling, comments related to the region they are visiting will also be prioritized. In this way, by considering the customer's geographical location, it is possible to prioritize the reception of comments that are highly relevant.

[0053] The reception department can analyze customers' social media activity when receiving comments and prioritize relevant comments. For example, it can prioritize comments about products or services mentioned by customers on social media. It can also prioritize comments on topics of high interest based on customers' social media activity. It can prioritize comments about brands that customers follow on social media. In this way, by analyzing customers' social media activity, it is possible to prioritize the reception of relevant comments.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The reception desk receives customer comments. Customer comments include text comments, voice comments, and evaluation comments. The reception desk receives text comments through an input form, voice comments through a microphone, and evaluation comments in a multiple-choice format. For example, the reception desk saves the text comments entered by the customer to a database, converts voice comments into text data using speech recognition technology, and saves evaluation comments to the database as selection results from a multiple-choice system. Step 2: The analysis unit uses a generation AI to analyze the comments received by the reception unit and assign a score to customer satisfaction. The analysis unit uses natural language processing technology to understand the content of the comments and assign a score. For example, the generation AI can analyze comments using a text generation AI (e.g., LLM), and can also analyze voice comments and evaluation comments using a multimodal generation AI. The generation AI assigns a score based on the sentiment score of the comments. Step 3: The service department provides the results scored by the analysis department. The service department then provides feedback to the customer on the scored results. For example, the service department may display the scored results to the customer through a web application or mobile application, or print the results using a printer if the customer prefers paper feedback. Sending the results via email provides quick feedback by sending them directly to the customer.

[0056] (Example 2) A customer satisfaction evaluation system according to an embodiment of the present invention uses NPS (Net Promoter Score) survey data to score customer satisfaction. This customer satisfaction evaluation system limits customer evaluations to comments only, omitting score evaluations. Next, a generation AI (generation AI) is used to analyze customer comments and generate a score for customer satisfaction. This system is expected to shorten customer response time and improve response rates. It also makes it possible to evaluate the difference between comments and score evaluations using a unified standard. First, customers enter comments into the NPS survey. For example, they may enter comments such as "The staff's service was excellent" or "I'm satisfied with the quality of the product." These comments are then input into the generation AI. Next, the generation AI analyzes the entered comments. The generation AI uses natural language processing technology to understand the content of the comments and generate a score for customer satisfaction. For example, a comment such as "very good" is assigned a high score, and a comment such as "improvement required" is assigned a low score. The customer satisfaction scores generated by the generation AI are evaluated using a unified standard. This eliminates the discrepancy between comments and score ratings, enabling more accurate evaluation of customer satisfaction. This system is expected to shorten the time it takes for customers to respond and improve the response rate. It also makes it possible to evaluate the discrepancy between comments and score ratings using a unified standard, improving the fairness of customer service evaluations. This allows the customer satisfaction evaluation system to efficiently accept and analyze customer comments and provide scored results.

[0057] The customer satisfaction evaluation system according to this embodiment comprises a reception unit, an analysis unit, and a provision unit. The reception unit receives customer comments. Customer comments include, but are not limited to, text comments, voice comments, and evaluation comments. The reception unit receives text comments, for example, through an input form. The reception unit can also receive voice comments through a microphone. Furthermore, the reception unit can also receive evaluation comments in the form of multiple-choice options. For example, the reception unit stores the text comments entered by the customer in a database. Voice comments are converted into text data using speech recognition technology. Evaluation comments are stored in the database as the result of selecting options. The analysis unit uses a generation AI to analyze the comments received by the reception unit and assigns a score to customer satisfaction. The analysis unit uses, for example, natural language processing technology to understand the content of the comments and assign a score. For example, the generation AI analyzes the comments using a text generation AI (e.g., LLM). The analysis unit can also use a multimodal generation AI to analyze voice comments and evaluation comments. For example, the generating AI assigns a score based on the sentiment score of the comment. The service unit provides the scored results, which are then analyzed by the service unit. The service unit then provides feedback to the customer, for example, by displaying the scored results to the customer through a web application or mobile application. If the customer prefers feedback in paper form, the results are printed using a printer. Sending the results via email provides quick feedback by directly sending the results to the customer. Thus, the customer satisfaction evaluation system according to this embodiment can efficiently receive, analyze, and provide scored results from customer comments.

[0058] The customer satisfaction evaluation system includes a classification unit that categorizes customer comments. The classification unit classifies customer comments. The classification unit uses methods such as category classification, sentiment classification, and topic classification. For example, category classification classifies comments into specific categories. Sentiment classification analyzes the sentiment of comments and classifies them into positive, negative, neutral, etc. Topic classification extracts the topic of a comment and classifies it into related topics. For example, the classification unit uses natural language processing technology to analyze the content of comments and perform category classification. Sentiment classification evaluates the sentiment of comments using sentiment analysis algorithms. Topic classification extracts the topic of a comment using a topic model. By classifying customer comments in this way, the accuracy of the analysis is improved. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can perform classification using an AI model that takes comments as input and outputs categories, sentiments, and topics.

[0059] The analysis unit can understand the content of comments and assign scores using natural language processing techniques. The analysis unit uses natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis. For example, morphological analysis divides the comment into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the comment and understands the sentence structure. Semantic analysis analyzes the meaning of the comment and understands the context. For example, the analysis unit uses morphological analysis to divide the comment into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the comment and understands the sentence structure. Semantic analysis analyzes the meaning of the comment and understands the context. As a result, by using natural language processing techniques, the content of comments can be accurately understood and scores can be assigned. Some or all of the above processing in the analysis unit may be performed using, for example, generative AI, or without generative AI. For example, the analysis unit can assign scores using a generative AI model that takes comments as input and outputs scores.

[0060] The customer satisfaction evaluation system includes a suggestion unit that suggests specific improvements based on the scored results. The suggestion unit suggests specific improvements based on the scored results. The suggestion unit suggests improvements based on, for example, the analysis results of customer feedback and industry benchmarks. For example, the suggestion unit suggests improvements for a specific service or product based on the analysis results of customer feedback. The industry benchmark suggests improvements by comparing with other companies' services or products. For example, the suggestion unit suggests improvements for a specific service or product based on the analysis results of customer feedback. The industry benchmark suggests improvements by comparing with other companies' services or products. In this way, by suggesting specific improvements based on the scored results, it is possible to expect an improvement in customer satisfaction. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can suggest improvements using an AI model that receives the scored results as input and outputs improvements.

[0061] The reception unit can estimate the customer's emotions and adjust the timing of comment acceptance based on the estimated customer emotions. For example, if the customer is feeling stressed, the reception unit prompts the customer to accept a comment at a time when the customer can relax. For example, if the customer is satisfied, the reception unit immediately accepts a comment on the spot. Furthermore, if the customer is in a hurry, the reception unit can send a reminder so that the customer can enter a comment later. For example, if the customer is feeling stressed, the reception unit prompts the customer to accept a comment at a time when the customer can relax. If the customer is satisfied, the reception unit immediately accepts a comment on the spot. If the customer is in a hurry, the reception unit sends a reminder so that the customer can enter a comment later. In this way, by adjusting the timing of comment acceptance according to the customer's emotions, comments can be accepted at a more appropriate time. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or without AI. For example, the reception unit can adjust the reception timing using an AI model that inputs customer emotion data and outputs the reception timing.

[0062] The reception unit can analyze the customer's past comment history and select the optimal reception method. The reception unit, for example, prompts the customer to enter comments based on the time period in which the customer frequently entered comments in the past. For example, the reception unit prioritizes suggesting an input method (voice, text, etc.) that the customer has used in the past. The reception unit can also prioritize accepting comments on a specific topic based on the customer's past comment history. For example, the reception unit prompts the customer to enter comments based on the time period in which the customer frequently entered comments in the past. The reception unit prioritizes suggesting an input method (voice, text, etc.) that the customer has used in the past. The reception unit prioritizes accepting comments on a specific topic based on the customer's past comment history. In this way, the optimal reception method can be selected by analyzing the customer's past comment history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can select the reception method using an AI model that inputs the customer's past comment history and outputs the optimal reception method.

[0063] When receiving comments, the reception unit can filter them based on the customer's current purchasing history and areas of interest. For example, the reception unit prioritizes receiving comments about products recently purchased by the customer. For example, the reception unit prioritizes receiving comments on topics related to the customer's areas of interest. The reception unit can also filter and receive comments about specific products or services from the customer's purchasing history. For example, the reception unit prioritizes receiving comments about products recently purchased by the customer. The reception unit prioritizes receiving comments on topics related to the customer's areas of interest. The reception unit can filter and receive comments about specific products or services from the customer's purchasing history. In this way, by filtering based on the customer's current purchasing history and areas of interest, highly relevant comments can be preferentially received. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can perform filtering using an AI model that inputs data on the customer's purchasing history and areas of interest and outputs filtered results.

[0064] The reception unit can estimate the customer's emotions and determine the priority of comments to be received based on the estimated customer emotions. For example, if a customer is very satisfied, the reception unit prioritizes receiving the comment. For example, if a customer is dissatisfied, the reception unit quickly accepts the comment. Furthermore, if a customer has neutral emotions, the reception unit can also accept the comment on an equal footing with other comments. For example, if a customer is very satisfied, the reception unit prioritizes receiving the comment. If a customer is dissatisfied, the reception unit quickly accepts the comment. If a customer has neutral emotions, the reception unit accepts the comment on an equal footing with other comments. In this way, by determining the priority of comments according to the customer's emotions, important comments can be preferentially received. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or without AI. For example, the reception desk can use an AI model that takes customer sentiment data as input and outputs comment priority rankings to determine priorities.

[0065] When receiving comments, the reception unit can prioritize receiving highly relevant comments based on the customer's geographical location information. For example, when a customer visits a specific store, the reception unit prioritizes receiving comments related to the store. For example, if the customer lives in a specific area, the reception unit prioritizes receiving comments related to the area. Furthermore, when a customer is traveling, the reception unit can also prioritize receiving comments related to the area they visited. For example, when a customer visits a specific store, the reception unit prioritizes receiving comments related to the store. If the customer lives in a specific area, the reception unit prioritizes receiving comments related to the area. If the customer is traveling, the reception unit prioritizes receiving comments related to the area they visited. This makes it possible to prioritize receiving highly relevant comments by taking the customer's geographical location information into consideration. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can perform filtering using an AI model that inputs the customer's geographical location information and outputs highly relevant comments.

[0066] The reception desk can analyze the customer's social media activity when receiving comments and receive relevant comments. For example, the reception desk can prioritize receiving comments about products or services mentioned by the customer on social media. For example, the reception desk can receive comments on topics of high interest based on the customer's social media activity. The reception desk can also prioritize receiving comments about brands that the customer follows on social media. For example, the reception desk can prioritize receiving comments about products or services mentioned by the customer on social media. For example, the reception desk can prioritize receiving comments about products or services mentioned by the customer on social media. For example, the reception desk can receive comments on topics of high interest based on the customer's social media activity. For example, the reception desk can filter comments using an AI model that takes customer social media activity data as input and outputs relevant comments.

[0067] The analysis unit can estimate customer emotions and adjust the scoring criteria based on the estimated customer emotions. For example, the analysis unit can set a criterion for assigning a high score if the customer is very satisfied. For example, the analysis unit can set a criterion for assigning a low score if the customer is dissatisfied. The analysis unit can also set a criterion for assigning an average score if the customer has neutral emotions. For example, the analysis unit can set a criterion for assigning a high score if the customer is very satisfied. For example, it can set a criterion for assigning a low score if the customer is dissatisfied. For example, it can set a criterion for assigning an average score if the customer has neutral emotions. By adjusting the scoring criteria based on customer emotions, more accurate scoring becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using a generative AI, for example, or without a generative AI. For example, the analysis unit can adjust the criteria using a generative AI model that takes customer emotional data as input and outputs scoring criteria.

[0068] The analysis unit can adjust the level of detail in scoring based on the importance of the comments during analysis. For example, the analysis unit can assign detailed scores to important comments and apply fine-grained evaluation criteria. For example, the analysis unit can assign standard scores to general comments and apply basic evaluation criteria. The analysis unit can also assign simplified scores to less important comments and apply simple evaluation criteria. For example, the analysis unit can assign detailed scores to important comments and apply fine-grained evaluation criteria. For general comments, it can assign standard scores and apply basic evaluation criteria. For less important comments, it can assign simplified scores and apply simple evaluation criteria. This allows for detailed evaluation of important comments by adjusting the level of detail in scoring based on the importance of the comments. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can adjust the level of detail using a generative AI model that takes comment importance data as input and outputs the level of detail in scoring.

[0069] The analysis unit can apply different scoring algorithms to comments depending on their category during analysis. For example, the analysis unit can apply a service-specific scoring algorithm to comments about services. For example, the analysis unit can apply a product-specific scoring algorithm to comments about products. The analysis unit can also apply a support-specific scoring algorithm to comments about support. For example, the analysis unit can apply a service-specific scoring algorithm to comments about services. For comments about products, it can apply a product-specific scoring algorithm. For comments about support, it can apply a support-specific scoring algorithm. This allows for more appropriate scoring by applying different scoring algorithms depending on the category of the comment. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can apply an algorithm using a generative AI model that takes comment category data as input and outputs a scoring algorithm.

[0070] The analysis unit can estimate the customer's emotions and adjust the length of the scoring based on the estimated emotions. For example, if the customer is very satisfied, the analysis unit will perform a detailed scoring and provide a longer evaluation. For example, if the customer is dissatisfied, the analysis unit will perform a concise scoring and provide a shorter evaluation. The analysis unit can also perform a standard scoring and provide an average evaluation if the customer has neutral emotions. For example, if the customer is very satisfied, the analysis unit will perform a detailed scoring and provide a longer evaluation. If the customer is dissatisfied, it will perform a concise scoring and provide a shorter evaluation. If the customer has neutral emotions, it will perform a standard scoring and provide an average evaluation. This allows for a more appropriate evaluation by adjusting the length of the scoring based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit may adjust the length using a generation AI model that inputs customer emotion data and outputs the length of the scoring.

[0071] The analysis unit can determine the priority of scoring based on the submission date of comments during analysis. For example, the analysis unit may prioritize scoring the most recent comments and perform a rapid evaluation. For example, the analysis unit may adjust the scoring priority according to the submission date while referring to past comments. The analysis unit can also prioritize scoring comments submitted within a specific period and evaluate comments from that period. For example, the analysis unit may prioritize scoring the most recent comments and perform a rapid evaluation. For example, the analysis unit may adjust the scoring priority according to the submission date while referring to past comments. For example, it may prioritize scoring comments submitted within a specific period and evaluate comments from that period. This allows for a rapid evaluation of the most recent comments by determining the scoring priority based on the submission date of the comments. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit may determine the priority using a generative AI model that takes comment submission date data as input and outputs the scoring priority.

[0072] During analysis, the analysis unit can adjust the scoring order based on the relevance of the comments. For example, if a customer's comment is related to a specific topic, the analysis unit prioritizes scoring the comment. For example, if a customer's comment is highly relevant to other comments, the analysis unit prioritizes scoring the comment. The analysis unit can also prioritize scoring the customer's comment if it is related to a specific issue. For example, if a customer's comment is related to a specific topic, the analysis unit prioritizes scoring the comment. If a customer's comment is highly relevant to other comments, the analysis unit prioritizes scoring the comment. In this way, by adjusting the scoring order based on the relevance of the comments, highly relevant comments can be prioritized for evaluation. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generative AI, or may be performed without using a generative AI. For example, the analysis unit can adjust the order using a generative AI model that inputs comment relevance data and outputs a scoring order.

[0073] The providing unit can estimate the customer's emotions and adjust the display method of the results to be provided based on the estimated customer emotions. For example, if the customer is very satisfied, the providing unit provides a display method that emphasizes positive feedback. For example, if the customer is dissatisfied, the providing unit provides a display method that clearly indicates areas for improvement. The providing unit can also provide a balanced display method if the customer has neutral emotions. For example, if the customer is very satisfied, the providing unit provides a display method that emphasizes positive feedback. If the customer is dissatisfied, the providing unit provides a display method that clearly indicates areas for improvement. If the customer has neutral emotions, the providing unit provides a balanced display method. This allows for adjusting the display method of the results based on the customer's emotions to provide more appropriate feedback. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using AI or without AI. For example, the service provider can use an AI model that takes customer emotion data as input and outputs how the results should be displayed to adjust the display method.

[0074] The service provider can adjust the level of detail provided based on the importance of the scored results at the time of delivery. For example, the service provider can add detailed explanations and specific suggestions for improvement to important results. For example, the service provider can add standard explanations and basic suggestions for improvement to general results. The service provider can also add simplified explanations and simple suggestions for improvement to less important results. For example, the service provider can add detailed explanations and specific suggestions for improvement to important results. For general results, it can add standard explanations and basic suggestions for improvement. For less important results, it can add simplified explanations and simple suggestions for improvement. This allows for detailed feedback on important results by adjusting the level of detail provided based on the importance of the scored results. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can adjust the level of detail using an AI model that takes the importance data of the scored results as input and outputs the level of detail provided.

[0075] The service provider can apply different service provision algorithms depending on the category of the scored result at the time of provision. For example, the service provider can apply a service-specific service provision algorithm to results related to services. For example, the service provider can apply a product-specific service provision algorithm to results related to products. The service provider can also apply a support-specific service provision algorithm to results related to support. For example, the service provider can apply a service-specific service provision algorithm to results related to services. For results related to products, it can apply a product-specific service provision algorithm. For results related to support, it can apply a support-specific service provision algorithm. This allows for more appropriate feedback to be provided by applying different service provision algorithms depending on the category of the scored result. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can apply an algorithm using an AI model that takes the category data of the scored result as input and outputs a service provision algorithm.

[0076] The providing unit can estimate the customer's emotions and determine the priority of results to provide based on the estimated customer emotions. For example, if the customer is very satisfied, the providing unit can provide the results preferentially. For example, if the customer is dissatisfied, the providing unit can quickly provide the results. Furthermore, if the customer has neutral emotions, the providing unit can provide the results on an equal footing with other results. For example, if the customer is very satisfied, the providing unit can provide the results on an equal footing with other results. For example, if the customer is dissatisfied, the providing unit can provide the results on an equal footing with other results. In this way, by determining the priority of results based on the customer's emotions, important results can be provided preferentially. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can determine the priority using an AI model that inputs customer emotion data and outputs a priority order of results.

[0077] The service provider can determine the priority of service provision based on the submission timing of the scored results. For example, the service provider can prioritize providing the latest results and provide prompt feedback. For example, the service provider can adjust the priority of service provision according to the submission timing, while referring to past results. The service provider can also prioritize providing results submitted within a specific period and provide feedback for that period. For example, the service provider can prioritize providing the latest results and provide prompt feedback. For example, the service provider can adjust the priority of service provision according to the submission timing, while referring to past results. For example, it can prioritize providing results submitted within a specific period and provide feedback for that period. This allows for the rapid provision of the latest results by determining the priority of service provision based on the submission timing of the scored results. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can determine the priority using an AI model that takes the submission timing data of scored results as input and outputs the priority of service provision.

[0078] The providing unit can adjust the order of providing the results based on the relevance of the scored results when providing them. For example, the providing unit can prioritize providing a customer's result if the customer's result is related to a specific topic. For example, the providing unit can prioritize providing a customer's result if the customer's result is highly relevant to other results. The providing unit can also prioritize providing a customer's result if the customer's result is related to a specific problem. For example, the providing unit can prioritize providing a customer's result if the customer's result is related to a specific topic. For example, the providing unit can prioritize providing a customer's result if the customer's result is highly relevant to other results. For example, the providing unit can prioritize providing a customer's result if the customer's result is related to a specific problem. In this way, by adjusting the order of providing based on the relevance of the scored results, it is possible to prioritize providing highly relevant results. 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 adjust the order using an AI model that receives relevance data of the scored results as input and outputs the order of providing. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, provision unit, classification unit, and suggestion unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit accepts customer comments using the reception device 38 of the smart device 14. The analysis unit performs comment analysis using a generation AI by the specific processing unit 290 of the data processing device 12. The provision unit provides the scored results to the customer using the output device 40 of the smart device 14. The classification unit classifies the comments into categories, emotions, and topics by the specific processing unit 290 of the data processing device 12. The suggestion unit proposes specific improvements based on the scored results by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, provision unit, classification unit, and suggestion unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit receives voice comments from customers using the microphone 238 of the smart glasses 214. The analysis unit performs comment analysis using a generation AI by the specific processing unit 290 of the data processing device 12. The provision unit provides the scored results to the customer using the speaker 240 of the smart glasses 214. The classification unit classifies the comments into categories, emotions, and topics by the specific processing unit 290 of the data processing device 12. The suggestion unit suggests specific improvements based on the scored results by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements described above, including the reception unit, analysis unit, provision unit, classification unit, and proposal unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit receives customer voice comments using the microphone 238 of the headset terminal 314. The analysis unit performs comment analysis using generated AI by the identification processing unit 290 of the data processing unit 12. The provision unit provides the customer with the scored results using the display 343 of the headset terminal 314. The classification unit classifies the comments into categories, sentiments, and topics using the identification processing unit 290 of the data processing unit 12. The proposal unit proposes specific improvements based on the scored results by the identification processing unit 290 of the data processing unit 12. === Hard Collateral 1-4 === Each of the multiple elements described above, including the reception unit, analysis unit, provision unit, classification unit, and proposal unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit receives customer voice comments using the microphone 238 of the robot 414. The analysis unit performs comment analysis using generated AI by the identification processing unit 290 of the data processing unit 12. The provision unit provides the customer with the scored results using the speaker 240 of the robot 414. The classification unit classifies the comments into categories, sentiments, and topics using the identification processing unit 290 of the data processing unit 12. The proposal unit proposes specific improvements based on the scored results from the identification processing unit 290 of the data processing unit 12.

[0079] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0080] When accepting customer comments, the reception unit can analyze the customer's past purchasing history and behavioral patterns and automatically generate optimal questions. For example, it can generate questions that ask for feedback on products the customer has purchased in the past. It can also generate questions about stores the customer frequently visits. It can also send optimal questions for specific times of day based on the customer's behavioral patterns. This can be expected to improve the response rate by providing questions based on the customer's interests.

[0081] When classifying customer comments, the classification unit can take into account not only the content of the comment but also the customer's past feedback history and purchasing history. For example, comments from customers who have provided a lot of positive feedback in the past can be preferentially classified into a positive category. Also, comments from customers who have provided negative feedback on specific products in the past can be classified into a negative category. Furthermore, based on the customer's purchasing history, it is possible to automatically extract comments related to specific products or services and classify them into appropriate categories. This enables highly accurate classification that takes into account the customer's past behavior.

[0082] The analysis unit uses natural language processing technology to understand the content of comments and can take the context of the comments into account when assigning scores. For example, if a comment is related to a specific event or campaign, the score can be adjusted taking that context into account. Also, if a comment is related to other comments, the score can be assigned taking that relevance into account. Furthermore, if comments are concentrated within a specific period, the score can be adjusted taking into account the trends of that period. This allows for more accurate scoring that takes the context of the comments into account.

[0083] The suggestion unit can take into account the customer's past feedback history and purchase history when proposing specific improvements based on the scoring results. For example, for a customer who has provided negative feedback about a particular product in the past, the suggestion unit can suggest specific improvements for that product. Also, for a customer who has provided a lot of positive feedback in the past, new suggestions can be made based on that feedback. Furthermore, it is possible to suggest improvements related to specific products or services based on the customer's purchase history. This makes it possible to propose specific improvements that take into account the customer's past behavior.

[0084] The reception unit can estimate the customer's emotions and adjust the timing of comment reception based on the estimated customer emotions. For example, if a customer is feeling stressed, the reception unit can encourage the customer to leave a comment at a time when they are relaxed. If the customer is satisfied, the reception unit can immediately accept the comment on the spot. If the customer is in a hurry, the reception unit can send a reminder so that the customer can enter a comment later. In this way, by adjusting the timing of comment reception according to the customer's emotions, comments can be received at a more appropriate time.

[0085] The reception desk can analyze a customer's past comment history and select the most suitable reception method. For example, it can prompt customers to submit comments at times when they frequently posted comments in the past. It can also prioritize suggesting input methods (voice, text, etc.) that customers have used in the past. Based on the customer's past comment history, it can also prioritize accepting comments on specific topics. In this way, by analyzing a customer's past comment history, the optimal reception method can be selected.

[0086] The reception system can filter comments based on the customer's current purchase history and areas of interest. For example, it can prioritize comments about products the customer has recently purchased, or comments on topics related to the customer's areas of interest. It can also filter comments based on the customer's purchase history to focus on specific products or services. This allows for prioritizing the reception of highly relevant comments by filtering based on the customer's current purchase history and areas of interest.

[0087] The reception desk can estimate the customer's emotions and determine the priority of comments to receive based on those estimates. For example, if the customer is very satisfied, that comment will be given priority. If the customer is dissatisfied, that comment will be received quickly. If the customer has neutral emotions, it can be received on par with other comments. This allows important comments to be received preferentially by prioritizing them according to the customer's emotions.

[0088] The reception desk can prioritize comments based on the customer's geographical location when receiving comments. For example, if a customer has visited a particular store, comments related to that store will be prioritized. If a customer lives in a specific region, comments related to that region will be prioritized. If a customer is traveling, comments related to the region they are visiting will also be prioritized. In this way, by considering the customer's geographical location, it is possible to prioritize the reception of comments that are highly relevant.

[0089] The reception department can analyze customers' social media activity when receiving comments and prioritize relevant comments. For example, it can prioritize comments about products or services mentioned by customers on social media. It can also prioritize comments on topics of high interest based on customers' social media activity. It can prioritize comments about brands that customers follow on social media. In this way, by analyzing customers' social media activity, it is possible to prioritize the reception of relevant comments.

[0090] The processing flow of the second embodiment will be briefly explained below.

[0091] Step 1: The reception desk receives customer comments. Customer comments include text comments, voice comments, and evaluation comments. The reception desk receives text comments through an input form, voice comments through a microphone, and evaluation comments in a multiple-choice format. For example, the reception desk saves the text comments entered by the customer to a database, converts voice comments into text data using speech recognition technology, and saves evaluation comments to the database as selection results from a multiple-choice system. Step 2: The analysis unit uses a generation AI to analyze the comments received by the reception unit and assign a score to customer satisfaction. The analysis unit uses natural language processing technology to understand the content of the comments and assign a score. For example, the generation AI can analyze comments using a text generation AI (e.g., LLM), and can also analyze voice comments and evaluation comments using a multimodal generation AI. The generation AI assigns a score based on the sentiment score of the comments. Step 3: The service department provides the results scored by the analysis department. The service department then provides feedback to the customer on the scored results. For example, the service department may display the scored results to the customer through a web application or mobile application, or print the results using a printer if the customer prefers paper feedback. Sending the results via email provides quick feedback by sending them directly to the customer.

[0092] 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.

[0093] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0094] 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.

[0095] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

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

[0098] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0099] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0100] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0101] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0102] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0103] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0104] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0105] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0106] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0107] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0108] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0109] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0110] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0111] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0112] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0113] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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).

[0118] 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.

[0119] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0126] 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.

[0127] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0128] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0129] 7, a 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0143] 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.

[0144] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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."

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] [Explanation of symbols]

[0164] 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 reception desk for receiving customer comments, An analysis unit analyzes the comments received by the reception unit and assigns a score to customer satisfaction, The system includes a providing unit that provides the results scored by the analysis unit. A system characterized by:

2. The reception unit It includes a classification unit for categorizing customer comments.

2. The system of claim 1.

3. The analysis unit The system uses natural language processing technology to understand the content of comments and assigns scores.

2. The system of claim 1.

4. The providing unit The department includes a proposal section that suggests specific areas for improvement based on the scored results.

2. The system of claim 1.

5. The reception unit We estimate customer sentiment and adjust the timing of comment submissions based on that estimated sentiment.

2. The system of claim 1.

6. The reception unit Analyze the customer's past comment history and select the appropriate method of receiving their comments.

2. The system of claim 1.

7. The reception unit When receiving comments, filtering is performed based on the customer's current purchase history and areas of interest.

2. The system of claim 1.

8. The reception unit The system estimates customer sentiment and prioritizes the comments to be received based on that estimated sentiment.

2. The system of claim 1.

9. The reception unit When receiving comments, the system prioritizes receiving comments that are highly relevant based on the customer's geographical location.

2. The system of claim 1.

Images