system

Abstract

An object of the system according to the embodiment is to efficiently collect and analyze NPS comments from a plurality of platforms on the Internet.SOLUTION: A system includes a comment collection part, a comment classification part, a comment analysis part, and a report generation part. The comment collector automatically collects NPS comments for MNOs and MVNOs from multiple platforms on the Internet. The comment classification component classifies the comments collected by the comment collection component into positive comments and negative comments. The comment analysis unit analyzes the comments classified by the comment classification unit in more detail. The report generation part generates a result report on the basis of the result analyzed by the comment analysis part.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the drawback of making it difficult to efficiently collect and analyze NPS comments from multiple platforms on the Internet.

[0005] The system according to the embodiment aims to efficiently collect and analyze NPS comments from multiple platforms on the Internet. [Means for solving the problem]

[0006] The system according to the embodiment includes a comment collection unit, a comment classification unit, a comment analysis unit, and a report generation unit. The comment collection unit automatically collects NPS comments about MNOs and MVNOs from multiple platforms on the Internet. The comment classification unit classifies the comments collected by the comment collection unit into positive comments and negative comments. The comment analysis unit performs a more detailed analysis of the comments classified by the comment classification unit. The report generation unit generates a result report based on the results of the analysis by the comment analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently collect and analyze NPS comments from multiple platforms on the Internet. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

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

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

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

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) The NPS comment collection and analysis system according to an embodiment of the present invention is a system that automatically collects NPS comments about MNOs and MVNOs from multiple platforms on the Internet, and uses a generation AI to classify and analyze the comments and generate a result report. As a result, the NPS comment collection and analysis system can efficiently collect and analyze NPS comments about MNOs and MVNOs and generate a result report.

[0029] An NPS comment collection and analysis system according to an embodiment includes a comment collection unit, a comment classification unit, a comment analysis unit, and a report generation unit. The comment collection unit automatically collects NPS comments about MNOs and MVNOs from multiple platforms on the Internet. For example, the comment collection unit collects comments from social media, blogs, review sites, etc. The comment collection unit can collect comments using web scraping technology. The comment collection unit can also collect comments using an API. The comment classification unit classifies the comments collected by the comment collection unit into positive and negative comments. For example, the comment classification unit uses a generation AI to analyze the sentiment of the comments and distinguish between comments that indicate positive sentiment and comments that indicate negative sentiment. The generation AI analyzes the sentiment of the comments using natural language processing technology. The comment analysis unit further analyzes the comments classified by the comment classification unit. For example, if factors such as "price," "connection speed," and "customer support" appear frequently among positive comments, the comment analysis unit determines that these are factors that contributed to the high rating. The comment analysis unit can use the generation AI to analyze the content of comments and quantify the intensity of emotions. The report generation unit generates a result report based on the results analyzed by the comment analysis unit. For example, the report generation unit generates a result report including the ratio of positive and negative comments, evaluation factors, specific comment examples, and the like. The report generation unit can use the generation AI and an emotion estimation function when generating the report to highlight information that users are most interested in. As a result, the NPS comment collection and analysis system according to the embodiment can efficiently collect and analyze NPS comments for MNOs and MVNOs and generate a result report. For example, telecommunications carriers can use this report to identify areas for service improvement and take measures to improve customer satisfaction.

[0030] The comment collection unit can filter related comments using specific keywords or hashtags. The comment collection unit, for example, filters related comments using specific keywords or hashtags. For example, the comment collection unit filters comments using keywords such as "MNO service is good" and "MVNO fees are high." The comment collection unit can also use a generation AI to estimate the poster's emotions in real time when collecting comments and set the priority of comments based on the intensity of the emotions. For example, when collecting comments, the generation AI analyzes the poster's emotions in real time and sets the priority of comments based on the intensity of the emotions. This allows related comments to be collected efficiently.

[0031] The comment classification unit can use the generation AI to analyze the sentiment of comments and distinguish between comments that express positive sentiment and comments that express negative sentiment. For example, the comment classification unit can use the generation AI to analyze the sentiment of comments and distinguish between comments that express positive sentiment and comments that express negative sentiment. The generation AI analyzes the sentiment of comments using natural language processing technology. For example, the generation AI classifies comments such as "great service" and "very satisfied" as positive, and comments such as "slow connection" and "unsatisfied" as negative. The comment classification unit can also identify issues and trends specific to a region by limiting the comments collected by the generation AI to specific regions or time periods. For example, the generation AI can limit the collection of comments to specific regions and identify issues and trends specific to those regions. This allows the sentiment of comments to be accurately classified.

[0032] The comment analysis unit can determine that factors such as price, connection speed, and customer support are factors that contribute to a high rating if they appear frequently among positive comments. For example, the comment analysis unit can determine that factors such as price, connection speed, and customer support are factors that contribute to a high rating if they appear frequently among positive comments. The comment analysis unit can use the generation AI to analyze the content of the comments and quantify the intensity of emotions. For example, the generation AI can quantify the emotions of the comments and compare the intensity of positive and negative emotions. The comment analysis unit can also refer to the poster's past posting history and prioritize the collection of highly reliable comments among the comments collected by the generation AI. For example, the generation AI can analyze the poster's past posting history and prioritize the collection of highly reliable comments. This makes it possible to identify the factors that contribute to a high rating.

[0033] The report generation unit can generate a result report including the ratio of positive and negative comments, factors for evaluation, and specific example comments. The report generation unit can generate a result report including, for example, the ratio of positive and negative comments, factors for evaluation, and specific example comments. The report generation unit can also use the generation AI to collect text information contained in images and videos and extract NPS comments from visual information. For example, the generation AI can use image recognition technology to extract text information contained in images and collect it as NPS comments. The report generation unit can also use the generation AI to automatically translate comments in different languages ​​and collect comments in multiple languages. For example, the generation AI can automatically translate comments in different languages ​​and collect comments in multiple languages. This makes it possible to generate a detailed result report.

[0034] The comment collection unit can use the generation AI to collect comments limited to a specific region or time period. For example, the comment collection unit uses the generation AI to collect comments limited to a specific region or time period. The generation AI collects comments limited to a specific region to identify issues and trends specific to that region. For example, it analyzes differences between urban and rural areas. It can also collect comments limited to a specific time period to identify trends by time period. For example, it can collect comments related to connection speeds at night. Furthermore, it can filter comments based on region or time period to collect user opinions under specific conditions. For example, it can collect comments during a specific event period. This makes it possible to collect comments limited to a specific region or time period.

[0035] The comment collection unit can use the generation AI to refer to the poster's past posting history and preferentially collect highly reliable comments. The comment collection unit, for example, uses the generation AI to refer to the poster's past posting history and preferentially collect highly reliable comments. The generation AI analyzes the poster's past posting history and preferentially collects highly reliable comments. For example, it gives priority to comments from users who have posted many useful comments in the past. It is also possible to build a system that filters highly reliable comments based on the poster's history data. For example, it collects comments from users with high past evaluation scores. Furthermore, it is also possible to introduce a filtering function that refers to the past posting history and eliminates low-reliability comments. For example, it automatically filters out spam comments. This allows highly reliable comments to be preferentially collected.

[0036] The comment collection unit uses a generation AI to collect text information contained in images and videos, and can extract NPS comments from visual information. The comment collection unit, for example, uses a generation AI to collect text information contained in images and videos and extract NPS comments from visual information. The generation AI uses image recognition technology to extract text information contained in images and collect it as NPS comments. For example, it analyzes text contained in screenshots. It can also use video analysis technology to extract subtitles and text information from videos and collect it as NPS comments. For example, it analyzes YouTube video comments. Furthermore, it is possible to build a system that automatically analyzes text information contained in images and videos and extracts NPS comments from visual information. For example, it collects text contained in infographics. This makes it possible to extract NPS comments from visual information.

[0037] The comment collection unit can use the generation AI to automatically translate comments in different languages ​​and collect comments in multiple languages. The comment collection unit can, for example, use the generation AI to automatically translate comments in different languages ​​and collect comments in multiple languages. The generation AI can automatically translate comments in different languages ​​and collect comments in multiple languages. For example, it can collect comments in English, French, and Chinese. It can also use an automatic translation function to translate comments in different languages ​​in real time and collect them as NPS comments. For example, it can analyze multilingual comments on social media. Furthermore, it can build a multilingual comment collection system and comprehensively analyze comments in different languages. For example, it can collect opinions from international users. This makes it possible to collect comments in multiple languages.

[0038] The comment classification unit uses a generative AI to understand the context of a comment and to perform detailed classification of comments containing multiple emotions. For example, the comment classification unit uses a generative AI to understand the context of a comment and to perform detailed classification of comments containing multiple emotions. The generative AI analyzes the context of a comment and performs detailed classification of comments containing multiple emotions. For example, it separates the positive and negative elements contained in a single comment. Detailed emotion classification can also be performed using natural language processing technology to understand the context of a comment. For example, it evaluates the intensity of the emotion based on the context. Furthermore, it is possible to develop an algorithm for detailed classification of comments containing multiple emotions. For example, it analyzes the mixture of emotions and identifies the proportion of each emotion. This allows for detailed classification of comments containing multiple emotions.

[0039] The comment classification unit uses generation AI to classify comments, taking into account the poster's background information and enabling more precise classification. The comment classification unit, for example, uses generation AI to classify comments, taking into account the poster's background information and enabling more precise classification. The generation AI analyzes the poster's background information and reflects it in the classification of comments. For example, it analyzes differences in emotions based on age and gender. It is also possible to build a system that takes into account the poster's regional information and classifies regionally specific emotional trends. For example, it compares emotional trends between urban and rural areas. Furthermore, it is possible to develop an algorithm that performs more precise emotional classification based on the poster's background information. For example, it analyzes emotions specific to specific age groups and gender. This allows for more precise classification by taking into account the poster's background information.

[0040] The comment classification unit can use a generation AI to convert voice comments into text and classify NPS comments from the voice data as well. The comment classification unit can, for example, use a generation AI to convert voice comments into text and classify NPS comments from the voice data as well. The generation AI can use voice recognition technology to convert voice comments into text and classify them as NPS comments. For example, feedback over the phone can be converted into text. It is also possible to build a system that analyzes voice data and extracts text information including emotions. For example, the tone and intonation of the voice can be analyzed. Furthermore, it is also possible to develop an algorithm for converting voice comments into text and classifying them as NPS comments. For example, emotions can be extracted from the voice data and classified as positive or negative. This makes it possible to classify NPS comments from the voice data as well.

[0041] The comment classification unit uses a generation AI to set classification criteria for different platforms (such as social media, blogs, and review sites) when classifying comments, thereby reflecting platform-specific emotions. The comment classification unit, for example, uses a generation AI to set classification criteria for different platforms when classifying comments, thereby reflecting platform-specific emotions. The generation AI sets classification criteria for different platforms to reflect platform-specific emotions. For example, it classifies comments on social media and blogs separately. It is also possible to build a system that adjusts the emotion classification algorithm taking into account the characteristics of each platform. For example, it reflects the evaluation criteria of review sites. Furthermore, it is also possible to develop an algorithm that analyzes the emotional characteristics of each platform and sets classification criteria. For example, it analyzes short comments on social media and long comments on blogs separately. This makes it possible to classify comments while reflecting platform-specific emotions.

[0042] The comment analysis unit can use the generation AI to analyze the frequency of specific keywords when analyzing comments and identify the emotional trends for each keyword. For example, the comment analysis unit can use the generation AI to analyze the frequency of specific keywords when analyzing comments and identify the emotional trends for each keyword. The generation AI analyzes the frequency of specific keywords in comments and identify the emotional trends for each keyword. For example, it analyzes keywords such as "fee" and "connection speed." It is also possible to develop an algorithm for analyzing the frequency of keyword appearances and identifying emotional trends. For example, it analyzes the relationship between frequently occurring keywords and emotional scores. Furthermore, it is possible to build a system that identifies emotional trends based on the frequency of occurrence of specific keywords. For example, it classifies keywords into positive and negative. This makes it possible to analyze the frequency of occurrence of specific keywords and identify the emotional trends for each keyword.

[0043] When analyzing comments using the generation AI, the comment analysis unit can take into account the length and level of detail of the comment and prioritize analysis of detailed comments. For example, when analyzing comments using the generation AI, the comment analysis unit can take into account the length and level of detail of the comment and prioritize analysis of detailed comments. The generation AI analyzes the length and level of detail of the comment and prioritizes analysis of detailed comments. For example, it can prioritize analysis of long comments. It is also possible to develop an algorithm that evaluates the level of detail of comments and build a system that prioritizes analysis of detailed comments. For example, it can prioritize comments that include specific examples. Furthermore, it is also possible to select comments to be analyzed with priority based on the length and level of detail of the comment. For example, it can prioritize analysis of comments that include detailed feedback. This makes it possible to prioritize analysis of detailed comments with consideration of the length and level of detail of the comment.

[0044] The comment analysis unit can use generative AI to analyze visual information contained in images and videos and identify the impact of visual elements on emotions. For example, the comment analysis unit can use generative AI to analyze visual information contained in images and videos and identify the impact of visual elements on emotions. The generative AI uses image recognition technology to analyze the visual information contained in images and identify the impact of visual elements on emotions. For example, it analyzes the color and composition of the image. It is also possible to build a system that uses video analysis technology to analyze visual information in videos and identify the impact on emotions. For example, it analyzes the scenes and cuts of the video. Furthermore, it is also possible to develop an algorithm to identify the impact on emotions based on visual information. For example, it analyzes the association between visual elements and emotion scores. This makes it possible to identify the impact of visual elements on emotions.

[0045] The comment analysis unit can use a generation AI to automatically translate comments in different languages ​​and perform an integrated analysis of multilingual comments. The comment analysis unit can, for example, use a generation AI to automatically translate comments in different languages ​​and perform an integrated analysis of multilingual comments. The generation AI can automatically translate comments in different languages ​​and perform an integrated analysis of multilingual comments. For example, it can analyze comments in English, French, and Chinese. It is also possible to use an automatic translation function to build a system that translates comments in different languages ​​in real time and performs an integrated analysis. For example, it can analyze multilingual comments on social media. Furthermore, it is possible to build a multilingual comment analysis system and perform an integrated analysis of comments in different languages. For example, it can collect opinions from international users. This makes it possible to perform an integrated analysis of multilingual comments.

[0046] The report generation unit can use the generation AI to compare a report with past reports when generating a report and visualize changes in emotions. The report generation unit, for example, uses the generation AI to compare a report with past reports when generating a report and visualize changes in emotions. The generation AI can compare a report with past reports when generating a report and visualize changes in emotions. For example, it can generate a graph that compares past data with current data. It is also possible to develop an algorithm for comparing with past reports and visualizing changes in emotions. For example, it can generate a chart that shows changes in emotion scores. It is also possible to build a system that references past data when generating a report and visualizes changes in emotions. For example, it can display past reports and current reports side by side. This makes it possible to visualize changes in emotions.

[0047] The report generation unit can use the generation AI to extract comments related to a specific period or event when generating a report and show changes in emotion over time. For example, the report generation unit can use the generation AI to extract comments related to a specific period or event when generating a report and show changes in emotion over time. The generation AI extracts comments related to a specific period or event and generates a report showing changes in emotion over time. For example, it analyzes changes in emotion before and after an event. It is also possible to develop an algorithm for extracting comments related to a specific period or event and showing changes in emotion over time. For example, it generates a graph showing changes in emotion scores for each period. Furthermore, it is also possible to extract comments related to a specific period or event when generating a report and build a system that shows changes in emotion over time. For example, it visualizes changes in emotion for each event. This makes it possible to extract comments related to a specific period or event and show changes in emotion over time.

[0048] The report generation unit can use the generation AI to provide the report in different formats (e.g., an interactive web page or a dashboard) to enable the user to intuitively understand. The report generation unit can, for example, use the generation AI to provide the report in different formats (e.g., an interactive web page or a dashboard) to enable the user to intuitively understand. The generation AI can provide the report in an interactive web page or dashboard format to enable the user to intuitively understand. For example, by allowing access to detailed information by clicking or zooming. A system can also be built to provide the report in different formats to enable the user to intuitively understand. For example, by providing interactive graphs and charts. Furthermore, an algorithm can be developed to provide the report in an interactive format to enable the user to intuitively understand. For example, the display content can be dynamically changed in response to user operations. This makes it possible to provide the report in different formats to enable the user to intuitively understand.

[0049] The report generation unit can use the generation AI to compare the report with data from different industries or regions when generating the report and provide a relative evaluation. For example, the report generation unit can use the generation AI to compare the report with data from different industries or regions when generating the report and provide a relative evaluation. The generation AI can compare the report with data from different industries or regions when generating the report and provide a relative evaluation. For example, it can compare with NPS scores from other industries or regions. It is also possible to develop an algorithm for comparing with data from different industries or regions and build a system that provides a relative evaluation. For example, it can compare NPS scores by industry. Furthermore, it is also possible to refer to data from different industries or regions when generating the report and provide a relative evaluation. For example, it can compare NPS scores by region. This makes it possible to compare with data from different industries or regions and provide a relative evaluation.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The NPS comment collection and analysis system can further include a behavior collection unit that collects user behavioral data. The behavior collection unit collects the user's actions and browsing history on websites and applications and analyzes the user's interests based on this data. For example, if a user frequently visits a particular page, it can prioritize collecting NPS comments related to that page. The behavior collection unit can also collect information on the links the user clicks and the files they download, and optimize the NPS comment collection strategy based on this behavioral data. Furthermore, the behavior collection unit can collect data such as the user's dwell time and scrolling depth, and evaluate the user's level of interest based on this data. This allows for more accurate collection and analysis of NPS comments by utilizing user behavioral data.

[0052] The NPS comment collection and analysis system may further include a feedback collection unit that collects user feedback in real time. The feedback collection unit collects feedback provided by users on a website or application in real time and collects and analyzes NPS comments based on this data. For example, the feedback collection unit may collect user feedback using a pop-up window or a chatbot. The feedback collection unit may also analyze the content of the feedback provided by users and distinguish between positive and negative feedback. Furthermore, the feedback collection unit may optimize the NPS comment collection strategy based on the user feedback and propose measures to improve user satisfaction. This allows user feedback to be collected in real time and used for collecting and analyzing NPS comments.

[0053] The NPS comment collection and analysis system can further include a behavioral analysis unit that optimizes the NPS comment collection strategy based on user behavioral data. The behavioral analysis unit analyzes user behavioral data on websites and applications and optimizes the NPS comment collection strategy based on this data. For example, the behavioral analysis unit analyzes information about pages frequently visited by users and links clicked by users, and optimizes the NPS comment collection strategy based on this data. The behavioral analysis unit can also analyze data such as user dwell time and scroll depth, and optimize the NPS comment collection strategy based on this data. Furthermore, the behavioral analysis unit can optimize the NPS comment collection strategy based on user behavioral data and propose measures to improve user satisfaction. This makes it possible to optimize the NPS comment collection strategy by utilizing user behavioral data.

[0054] The NPS comment collection and analysis system may further include a feedback analysis unit that optimizes the NPS comment collection strategy based on user feedback. The feedback analysis unit analyzes the content of feedback provided by users and optimizes the NPS comment collection strategy based on this data. For example, the feedback analysis unit analyzes the content of feedback provided by users and distinguishes between positive and negative feedback. The feedback analysis unit may also optimize the NPS comment collection strategy based on user feedback and propose measures to improve user satisfaction. The feedback analysis unit may also optimize the NPS comment collection strategy based on user feedback and propose measures to improve user satisfaction. In this way, the NPS comment collection strategy can be optimized by utilizing user feedback.

[0055] The NPS comment collection and analysis system can further include a report customization unit that customizes the content of reports based on user behavior data. The report customization unit analyzes user behavior data on websites and applications and customizes the content of reports based on this data. For example, the report customization unit analyzes information about pages frequently visited by users and links clicked by users, and customizes the content of reports based on this data. The report customization unit can also analyze data such as user dwell time and scrolling depth, and customize the content of reports based on this data. Furthermore, the report customization unit can customize the content of reports based on user behavior data and propose measures to improve user satisfaction. This makes it possible to customize the content of reports by utilizing user behavior data.

[0056] The NPS comment collection and analysis system may further include a report customization unit that customizes the content of the report based on user feedback. The report customization unit analyzes the content of the feedback provided by the user and customizes the content of the report based on this data. For example, the report customization unit may analyze the content of the feedback provided by the user and distinguish between positive feedback and negative feedback. The report customization unit may also customize the content of the report based on the user feedback and suggest measures to improve user satisfaction. The report customization unit may also customize the content of the report based on the user feedback and suggest measures to improve user satisfaction. In this way, the content of the report can be customized by utilizing user feedback.

[0057] The NPS comment collection and analysis system may further include a feedback providing unit that provides feedback based on user behavior data. The feedback providing unit analyzes user behavior data on websites and applications and provides feedback based on this data. For example, the feedback providing unit may analyze information about pages frequently visited by users and links clicked by users and provide feedback based on this data. The feedback providing unit may also analyze data such as the user's stay time and scrolling depth and provide feedback based on this data. Furthermore, the feedback providing unit may provide feedback based on the user behavior data and suggest measures to improve user satisfaction. In this way, feedback can be provided by utilizing user behavior data.

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

[0059] Step 1: The comment collection unit automatically collects NPS comments about MNOs and MVNOs from multiple platforms on the Internet. For example, comments are collected from social media, blogs, review sites, etc. The comment collection unit can collect comments using web scraping technology or APIs. Step 2: The comment classification unit classifies the comments collected by the comment collection unit into positive and negative comments. For example, it uses a generation AI to analyze the sentiment of the comments and distinguish between comments that show positive sentiment and comments that show negative sentiment. The generation AI analyzes the sentiment of the comments using natural language processing technology. Step 3: The comment analysis unit performs a more detailed analysis of the comments classified by the comment classification unit. For example, if factors such as "price," "connection speed," and "customer support" appear frequently among positive comments, it determines that these are the factors that led to high ratings. Generative AI can then be used to analyze the content of the comments and quantify the intensity of their sentiment. Step 4: The report generation unit generates a result report based on the results analyzed by the comment analysis unit. For example, the report may include the ratio of positive and negative comments, evaluation factors, and specific comment examples. The generation AI can use emotion estimation functions to highlight the information that users are most interested in when generating the report.

[0060] (Example 2) The NPS comment collection and analysis system according to an embodiment of the present invention is a system that automatically collects NPS comments about MNOs and MVNOs from multiple platforms on the Internet, and uses a generation AI to classify and analyze the comments and generate a result report. As a result, the NPS comment collection and analysis system can efficiently collect and analyze NPS comments about MNOs and MVNOs and generate a result report.

[0061] An NPS comment collection and analysis system according to an embodiment includes a comment collection unit, a comment classification unit, a comment analysis unit, and a report generation unit. The comment collection unit automatically collects NPS comments about MNOs and MVNOs from multiple platforms on the Internet. For example, the comment collection unit collects comments from social media, blogs, review sites, etc. The comment collection unit can collect comments using web scraping technology. The comment collection unit can also collect comments using an API. The comment classification unit classifies the comments collected by the comment collection unit into positive and negative comments. For example, the comment classification unit uses a generation AI to analyze the sentiment of the comments and distinguish between comments that indicate positive sentiment and comments that indicate negative sentiment. The generation AI analyzes the sentiment of the comments using natural language processing technology. The comment analysis unit further analyzes the comments classified by the comment classification unit. For example, if factors such as "price," "connection speed," and "customer support" appear frequently among positive comments, the comment analysis unit determines that these are factors that contributed to the high rating. The comment analysis unit can use the generation AI to analyze the content of comments and quantify the intensity of emotions. The report generation unit generates a result report based on the results analyzed by the comment analysis unit. For example, the report generation unit generates a result report including the ratio of positive and negative comments, evaluation factors, specific comment examples, and the like. The report generation unit can use the generation AI and an emotion estimation function when generating the report to highlight information that users are most interested in. As a result, the NPS comment collection and analysis system according to the embodiment can efficiently collect and analyze NPS comments for MNOs and MVNOs and generate a result report. For example, telecommunications carriers can use this report to identify areas for service improvement and take measures to improve customer satisfaction.

[0062] The comment collection unit can filter related comments using specific keywords or hashtags. The comment collection unit, for example, filters related comments using specific keywords or hashtags. For example, the comment collection unit filters comments using keywords such as "MNO service is good" and "MVNO fees are high." The comment collection unit can also use a generation AI to estimate the poster's emotions in real time when collecting comments and set the priority of comments based on the intensity of the emotions. For example, when collecting comments, the generation AI analyzes the poster's emotions in real time and sets the priority of comments based on the intensity of the emotions. This allows related comments to be collected efficiently.

[0063] The comment classification unit can use the generation AI to analyze the sentiment of comments and distinguish between comments that express positive sentiment and comments that express negative sentiment. For example, the comment classification unit can use the generation AI to analyze the sentiment of comments and distinguish between comments that express positive sentiment and comments that express negative sentiment. The generation AI analyzes the sentiment of comments using natural language processing technology. For example, the generation AI classifies comments such as "great service" and "very satisfied" as positive, and comments such as "slow connection" and "unsatisfied" as negative. The comment classification unit can also identify issues and trends specific to a region by limiting the comments collected by the generation AI to specific regions or time periods. For example, the generation AI can limit the collection of comments to specific regions and identify issues and trends specific to those regions. This allows the sentiment of comments to be accurately classified.

[0064] The comment analysis unit can determine that factors such as price, connection speed, and customer support are factors that contribute to a high rating if they appear frequently among positive comments. For example, the comment analysis unit can determine that factors such as price, connection speed, and customer support are factors that contribute to a high rating if they appear frequently among positive comments. The comment analysis unit can use the generation AI to analyze the content of the comments and quantify the intensity of emotions. For example, the generation AI can quantify the emotions of the comments and compare the intensity of positive and negative emotions. The comment analysis unit can also refer to the poster's past posting history and prioritize the collection of highly reliable comments among the comments collected by the generation AI. For example, the generation AI can analyze the poster's past posting history and prioritize the collection of highly reliable comments. This makes it possible to identify the factors that contribute to a high rating.

[0065] The report generation unit can generate a result report including the ratio of positive and negative comments, factors for evaluation, and specific example comments. The report generation unit can generate a result report including, for example, the ratio of positive and negative comments, factors for evaluation, and specific example comments. The report generation unit can also use the generation AI to collect text information contained in images and videos and extract NPS comments from visual information. For example, the generation AI can use image recognition technology to extract text information contained in images and collect it as NPS comments. The report generation unit can also use the generation AI to automatically translate comments in different languages ​​and collect comments in multiple languages. For example, the generation AI can automatically translate comments in different languages ​​and collect comments in multiple languages. This makes it possible to generate a detailed result report.

[0066] The comment collection unit can use the generation AI to estimate the poster's emotions in real time when collecting comments, and set the priority of comments based on the intensity of the emotions. The comment collection unit can, for example, use the generation AI to estimate the poster's emotions in real time when collecting comments, and set the priority of comments based on the intensity of the emotions. When collecting comments, the generation AI analyzes the poster's emotions in real time and sets the priority of comments based on the intensity of the emotions. For example, it prioritizes collecting comments with strong positive emotions. It can also estimate the poster's emotions in real time and determine the order in which comments are collected based on the intensity of the emotions. For example, it puts comments with strong negative emotions last. This makes it possible to set the priority of comments based on the intensity of the emotions.

[0067] The comment collection unit can use the generation AI to collect comments limited to a specific region or time period. For example, the comment collection unit uses the generation AI to collect comments limited to a specific region or time period. The generation AI collects comments limited to a specific region to identify issues and trends specific to that region. For example, it analyzes differences between urban and rural areas. It can also collect comments limited to a specific time period to identify trends by time period. For example, it can collect comments related to connection speeds at night. Furthermore, it can filter comments based on region or time period to collect user opinions under specific conditions. For example, it can collect comments during a specific event period. This makes it possible to collect comments limited to a specific region or time period.

[0068] The comment collection unit can use the generation AI to refer to the poster's past posting history and preferentially collect highly reliable comments. The comment collection unit, for example, uses the generation AI to refer to the poster's past posting history and preferentially collect highly reliable comments. The generation AI analyzes the poster's past posting history and preferentially collects highly reliable comments. For example, it gives priority to comments from users who have posted many useful comments in the past. It is also possible to build a system that filters highly reliable comments based on the poster's history data. For example, it collects comments from users with high past evaluation scores. Furthermore, it is also possible to introduce a filtering function that refers to the past posting history and eliminates low-reliability comments. For example, it automatically filters out spam comments. This allows highly reliable comments to be preferentially collected.

[0069] The comment collection unit uses a generation AI to collect text information contained in images and videos, and can extract NPS comments from visual information. The comment collection unit, for example, uses a generation AI to collect text information contained in images and videos and extract NPS comments from visual information. The generation AI uses image recognition technology to extract text information contained in images and collect it as NPS comments. For example, it analyzes text contained in screenshots. It can also use video analysis technology to extract subtitles and text information from videos and collect it as NPS comments. For example, it analyzes YouTube video comments. Furthermore, it is possible to build a system that automatically analyzes text information contained in images and videos and extracts NPS comments from visual information. For example, it collects text contained in infographics. This makes it possible to extract NPS comments from visual information.

[0070] The comment collection unit can use the generation AI to automatically translate comments in different languages ​​and collect comments in multiple languages. The comment collection unit can, for example, use the generation AI to automatically translate comments in different languages ​​and collect comments in multiple languages. The generation AI can automatically translate comments in different languages ​​and collect comments in multiple languages. For example, it can collect comments in English, French, and Chinese. It can also use an automatic translation function to translate comments in different languages ​​in real time and collect them as NPS comments. For example, it can analyze multilingual comments on social media. Furthermore, it can build a multilingual comment collection system and comprehensively analyze comments in different languages. For example, it can collect opinions from international users. This makes it possible to collect comments in multiple languages.

[0071] The comment collection unit can use the emotion estimation function to analyze the emotions of the collected comments and propose a comment collection method for eliciting positive emotions. The comment collection unit, for example, uses the emotion estimation function to analyze the emotions of the collected comments and propose a comment collection method for eliciting positive emotions. The emotion estimation function analyzes the emotions of the collected comments in real time and proposes a comment collection method for eliciting positive emotions. For example, comments with strong positive emotions are preferentially collected. Furthermore, a collection strategy for eliciting positive emotions can be formulated based on the emotion data of the collected comments. For example, comments containing positive keywords are collected. Furthermore, a system can be constructed that proposes a comment collection method for eliciting positive emotions based on the emotion analysis results. For example, comments from users with positive emotions are preferentially collected. This makes it possible to propose a comment collection method for eliciting positive emotions.

[0072] When analyzing the sentiment of comments using the generation AI, the comment classification unit can track changes in sentiment over time and identify emotional trends. When analyzing the sentiment of comments using the generation AI, for example, the comment classification unit can track changes in sentiment over time and identify emotional trends. The generation AI analyzes the sentiment of comments over time and tracks changes in sentiment. For example, it analyzes the increase or decrease in positive sentiment over a specific period of time. It is also possible to build a system that identifies emotional trends based on time series data. For example, it analyzes changes in sentiment by season. It is also possible to develop an algorithm that tracks changes in sentiment over time and identifies trends. For example, it analyzes changes in sentiment before and after an event. This makes it possible to identify emotional trends.

[0073] The comment classification unit uses a generative AI to understand the context of a comment and to perform detailed classification of comments containing multiple emotions. For example, the comment classification unit uses a generative AI to understand the context of a comment and to perform detailed classification of comments containing multiple emotions. The generative AI analyzes the context of a comment and performs detailed classification of comments containing multiple emotions. For example, it separates the positive and negative elements contained in a single comment. Detailed emotion classification can also be performed using natural language processing technology to understand the context of a comment. For example, it evaluates the intensity of the emotion based on the context. Furthermore, it is possible to develop an algorithm for detailed classification of comments containing multiple emotions. For example, it analyzes the mixture of emotions and identifies the proportion of each emotion. This allows for detailed classification of comments containing multiple emotions.

[0074] The comment classification unit uses generation AI to classify comments, taking into account the poster's background information and enabling more precise classification. The comment classification unit, for example, uses generation AI to classify comments, taking into account the poster's background information and enabling more precise classification. The generation AI analyzes the poster's background information and reflects it in the classification of comments. For example, it analyzes differences in emotions based on age and gender. It is also possible to build a system that takes into account the poster's regional information and classifies regionally specific emotional trends. For example, it compares emotional trends between urban and rural areas. Furthermore, it is possible to develop an algorithm that performs more precise emotional classification based on the poster's background information. For example, it analyzes emotions specific to specific age groups and gender. This allows for more precise classification by taking into account the poster's background information.

[0075] The comment classification unit can use a generation AI to convert voice comments into text and classify NPS comments from the voice data as well. The comment classification unit can, for example, use a generation AI to convert voice comments into text and classify NPS comments from the voice data as well. The generation AI can use voice recognition technology to convert voice comments into text and classify them as NPS comments. For example, feedback over the phone can be converted into text. It is also possible to build a system that analyzes voice data and extracts text information including emotions. For example, the tone and intonation of the voice can be analyzed. Furthermore, it is also possible to develop an algorithm for converting voice comments into text and classifying them as NPS comments. For example, emotions can be extracted from the voice data and classified as positive or negative. This makes it possible to classify NPS comments from the voice data as well.

[0076] The comment classification unit uses a generation AI to set classification criteria for different platforms (such as social media, blogs, and review sites) when classifying comments, thereby reflecting platform-specific emotions. The comment classification unit, for example, uses a generation AI to set classification criteria for different platforms when classifying comments, thereby reflecting platform-specific emotions. The generation AI sets classification criteria for different platforms to reflect platform-specific emotions. For example, it classifies comments on social media and blogs separately. It is also possible to build a system that adjusts the emotion classification algorithm taking into account the characteristics of each platform. For example, it reflects the evaluation criteria of review sites. Furthermore, it is also possible to develop an algorithm that analyzes the emotional characteristics of each platform and sets classification criteria. For example, it analyzes short comments on social media and long comments on blogs separately. This makes it possible to classify comments while reflecting platform-specific emotions.

[0077] The comment classification unit can use the emotion estimation function to analyze the emotion of comments in real time and prioritize classify comments with positive emotions. The comment classification unit, for example, uses the emotion estimation function to analyze the emotion of comments in real time and prioritize classifying comments with positive emotions. The emotion estimation function analyzes the emotion of comments in real time and prioritize classifying comments with positive emotions. For example, comments with a high positive emotion score are prioritized. It is also possible to build a system that analyzes emotions in real time and prioritize classifying positive comments. For example, comments with positive emotions are instantly stored in a database. Furthermore, it is also possible to develop an algorithm that prioritizes classifying comments with positive emotions based on the emotion estimation data. For example, comments with a high positive emotion score are displayed preferentially. This makes it possible to prioritize classifying comments with positive emotions.

[0078] The comment analysis unit can use the generation AI to quantify the intensity of emotions and compare the intensity of positive and negative emotions when analyzing the content of comments. For example, the comment analysis unit can use the generation AI to quantify the intensity of emotions and compare the intensity of positive and negative emotions when analyzing the content of comments. The generation AI quantifies the emotions of comments and compares the intensity of positive and negative emotions. For example, it can evaluate the intensity of comments based on emotion scores. It is also possible to develop an algorithm to quantify the intensity of emotions and build a system to compare positive and negative emotions. For example, it can calculate the average emotion score. It is also possible to quantify the emotional intensity of comments and build a database to compare the intensity of positive and negative emotions. For example, it can analyze the distribution of emotion scores. This makes it possible to quantify the intensity of emotions and compare the intensity of positive and negative emotions.

[0079] The comment analysis unit can use the generation AI to analyze the frequency of specific keywords when analyzing comments and identify the emotional trends for each keyword. For example, the comment analysis unit can use the generation AI to analyze the frequency of specific keywords when analyzing comments and identify the emotional trends for each keyword. The generation AI analyzes the frequency of specific keywords in comments and identify the emotional trends for each keyword. For example, it analyzes keywords such as "fee" and "connection speed." It is also possible to develop an algorithm for analyzing the frequency of keyword appearances and identifying emotional trends. For example, it analyzes the relationship between frequently occurring keywords and emotional scores. Furthermore, it is possible to build a system that identifies emotional trends based on the frequency of occurrence of specific keywords. For example, it classifies keywords into positive and negative. This makes it possible to analyze the frequency of occurrence of specific keywords and identify the emotional trends for each keyword.

[0080] When analyzing comments using the generation AI, the comment analysis unit can take into account the length and level of detail of the comment and prioritize analysis of detailed comments. For example, when analyzing comments using the generation AI, the comment analysis unit can take into account the length and level of detail of the comment and prioritize analysis of detailed comments. The generation AI analyzes the length and level of detail of the comment and prioritizes analysis of detailed comments. For example, it can prioritize analysis of long comments. It is also possible to develop an algorithm that evaluates the level of detail of comments and build a system that prioritizes analysis of detailed comments. For example, it can prioritize comments that include specific examples. Furthermore, it is also possible to select comments to be analyzed with priority based on the length and level of detail of the comment. For example, it can prioritize analysis of comments that include detailed feedback. This makes it possible to prioritize analysis of detailed comments with consideration of the length and level of detail of the comment.

[0081] The comment analysis unit can use generative AI to analyze visual information contained in images and videos and identify the impact of visual elements on emotions. For example, the comment analysis unit can use generative AI to analyze visual information contained in images and videos and identify the impact of visual elements on emotions. The generative AI uses image recognition technology to analyze the visual information contained in images and identify the impact of visual elements on emotions. For example, it analyzes the color and composition of the image. It is also possible to build a system that uses video analysis technology to analyze visual information in videos and identify the impact on emotions. For example, it analyzes the scenes and cuts of the video. Furthermore, it is also possible to develop an algorithm to identify the impact on emotions based on visual information. For example, it analyzes the association between visual elements and emotion scores. This makes it possible to identify the impact of visual elements on emotions.

[0082] The comment analysis unit can use a generation AI to automatically translate comments in different languages ​​and perform an integrated analysis of multilingual comments. The comment analysis unit can, for example, use a generation AI to automatically translate comments in different languages ​​and perform an integrated analysis of multilingual comments. The generation AI can automatically translate comments in different languages ​​and perform an integrated analysis of multilingual comments. For example, it can analyze comments in English, French, and Chinese. It is also possible to use an automatic translation function to build a system that translates comments in different languages ​​in real time and performs an integrated analysis. For example, it can analyze multilingual comments on social media. Furthermore, it is possible to build a multilingual comment analysis system and perform an integrated analysis of comments in different languages. For example, it can collect opinions from international users. This makes it possible to perform an integrated analysis of multilingual comments.

[0083] The comment analysis unit can use the emotion estimation function to analyze the emotion of comments in real time and identify the factors that lead to comments with positive emotions. The comment analysis unit, for example, uses the emotion estimation function to analyze the emotion of comments in real time and identify the factors that lead to comments with positive emotions. The emotion estimation function analyzes the emotion of comments in real time and identifies the factors that lead to comments with positive emotions. For example, it analyzes commonalities between comments with high positive emotion scores. It is also possible to build a system that analyzes emotions in real time and identifies the factors that lead to positive comments. For example, it identifies keywords that elicit positive emotions. Furthermore, it is also possible to develop an algorithm that identifies the factors that lead to comments with positive emotions based on the emotion estimation data. For example, it analyzes the characteristics of comments with high positive emotion scores. This makes it possible to identify the factors that lead to comments with positive emotions.

[0084] The report generation unit can use the generation AI and the emotion estimation function when generating a report to emphasize information in which the user is most interested. The report generation unit, for example, uses the generation AI and the emotion estimation function when generating a report to emphasize information in which the user is most interested. The generation AI uses the emotion estimation function when generating a report to emphasize information in which the user is most interested. For example, information with a high positive emotion score can be displayed prominently. It is also possible to develop a report generation algorithm based on emotion estimation data to emphasize information in which the user is most interested. For example, information with a high emotion score can be displayed preferentially. Furthermore, it is also possible to build a system that uses the emotion estimation function when generating a report to emphasize information in which the user is most interested. For example, information that elicits positive emotions can be emphasized. This makes it possible to emphasize information in which the user is most interested.

[0085] The report generation unit can use the generation AI to compare a report with past reports when generating a report and visualize changes in emotions. The report generation unit, for example, uses the generation AI to compare a report with past reports when generating a report and visualize changes in emotions. The generation AI can compare a report with past reports when generating a report and visualize changes in emotions. For example, it can generate a graph that compares past data with current data. It is also possible to develop an algorithm for comparing with past reports and visualizing changes in emotions. For example, it can generate a chart that shows changes in emotion scores. It is also possible to build a system that references past data when generating a report and visualizes changes in emotions. For example, it can display past reports and current reports side by side. This makes it possible to visualize changes in emotions.

[0086] The report generation unit can use the generation AI to extract comments related to a specific period or event when generating a report and show changes in emotion over time. For example, the report generation unit can use the generation AI to extract comments related to a specific period or event when generating a report and show changes in emotion over time. The generation AI extracts comments related to a specific period or event and generates a report showing changes in emotion over time. For example, it analyzes changes in emotion before and after an event. It is also possible to develop an algorithm for extracting comments related to a specific period or event and showing changes in emotion over time. For example, it generates a graph showing changes in emotion scores for each period. Furthermore, it is also possible to extract comments related to a specific period or event when generating a report and build a system that shows changes in emotion over time. For example, it visualizes changes in emotion for each event. This makes it possible to extract comments related to a specific period or event and show changes in emotion over time.

[0087] The report generation unit can use the generation AI to provide the report in different formats (e.g., an interactive web page or a dashboard) to enable the user to intuitively understand. The report generation unit can, for example, use the generation AI to provide the report in different formats (e.g., an interactive web page or a dashboard) to enable the user to intuitively understand. The generation AI can provide the report in an interactive web page or dashboard format to enable the user to intuitively understand. For example, by allowing access to detailed information by clicking or zooming. A system can also be built to provide the report in different formats to enable the user to intuitively understand. For example, by providing interactive graphs and charts. Furthermore, an algorithm can be developed to provide the report in an interactive format to enable the user to intuitively understand. For example, the display content can be dynamically changed in response to user operations. This makes it possible to provide the report in different formats to enable the user to intuitively understand.

[0088] The report generation unit can use the generation AI to compare the report with data from different industries or regions when generating the report and provide a relative evaluation. For example, the report generation unit can use the generation AI to compare the report with data from different industries or regions when generating the report and provide a relative evaluation. The generation AI can compare the report with data from different industries or regions when generating the report and provide a relative evaluation. For example, it can compare with NPS scores from other industries or regions. It is also possible to develop an algorithm for comparing with data from different industries or regions and build a system that provides a relative evaluation. For example, it can compare NPS scores by industry. Furthermore, it is also possible to refer to data from different industries or regions when generating the report and provide a relative evaluation. For example, it can compare NPS scores by region. This makes it possible to compare with data from different industries or regions and provide a relative evaluation.

[0089] The report generation unit can use the emotion estimation function to collect the user's emotional reactions to the report content and reflect them in the generation of the next report. The report generation unit, for example, uses the emotion estimation function to collect the user's emotional reactions to the report content and reflect them in the generation of the next report. The emotion estimation function collects the user's emotional reactions to the report content and reflects them in the generation of the next report. For example, information with a high number of positive emotional reactions can be displayed preferentially. An algorithm can also be developed based on the user's emotional reaction data to reflect them in the generation of the next report. For example, information with a high emotion score can be displayed preferentially. Furthermore, a system can be constructed that uses the emotion estimation function when generating a report to collect the user's emotional reactions and reflect them in the generation of the next report. For example, information that elicits positive emotions can be emphasized. In this way, the user's emotional reactions can be collected and reflected in the generation of the next report.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The NPS comment collection and analysis system can further include a behavior collection unit that collects user behavioral data. The behavior collection unit collects the user's actions and browsing history on websites and applications and analyzes the user's interests based on this data. For example, if a user frequently visits a particular page, it can prioritize collecting NPS comments related to that page. The behavior collection unit can also collect information on the links the user clicks and the files they download, and optimize the NPS comment collection strategy based on this behavioral data. Furthermore, the behavior collection unit can collect data such as the user's dwell time and scrolling depth, and evaluate the user's level of interest based on this data. This allows for more accurate collection and analysis of NPS comments by utilizing user behavioral data.

[0092] The NPS comment collection and analysis system may further include a feedback collection unit that collects user feedback in real time. The feedback collection unit collects feedback provided by users on a website or application in real time and collects and analyzes NPS comments based on this data. For example, the feedback collection unit may collect user feedback using a pop-up window or a chatbot. The feedback collection unit may also analyze the content of the feedback provided by users and distinguish between positive and negative feedback. Furthermore, the feedback collection unit may optimize the NPS comment collection strategy based on the user feedback and propose measures to improve user satisfaction. This allows user feedback to be collected in real time and used for collecting and analyzing NPS comments.

[0093] The NPS comment collection and analysis system may further include an emotion priority setting unit that estimates a user's emotions and sets comment priorities based on the estimated emotions. The emotion priority setting unit estimates a user's emotions in real time and prioritizes the collection of comments with positive emotions. For example, the emotion priority setting unit may analyze a user's facial expressions and tone of voice to estimate emotions. The emotion priority setting unit may also set comment priorities based on the user's emotion data and prioritize the analysis of comments with positive emotions. Furthermore, the emotion priority setting unit may optimize the NPS comment collection strategy based on the user's emotion data and propose measures to improve user satisfaction. This makes it possible to estimate a user's emotions and set comment priorities based on emotions.

[0094] The NPS comment collection and analysis system may further include a report customization unit that estimates a user's emotions and customizes the report content based on the estimated emotions. The report customization unit estimates a user's emotions in real time and emphasizes information associated with positive emotions. For example, the report customization unit may analyze a user's facial expressions and tone of voice to estimate emotions. The report customization unit may also customize the report content based on the user's emotional data and prioritize the display of information associated with positive emotions. Furthermore, the report customization unit may optimize the report generation strategy based on the user's emotional data and propose measures to improve user satisfaction. This makes it possible to estimate a user's emotions and customize the report content based on emotions.

[0095] The NPS comment collection and analysis system may further include a feedback providing unit that estimates a user's emotions and provides feedback based on the estimated emotions. The feedback providing unit estimates a user's emotions in real time and provides feedback to elicit positive emotions. For example, the feedback providing unit may analyze a user's facial expressions and tone of voice to estimate emotions. The feedback providing unit may also customize the content of feedback based on the user's emotional data and provide information to elicit positive emotions. Furthermore, the feedback providing unit may also optimize a feedback provision strategy based on the user's emotional data and suggest measures to improve user satisfaction. This makes it possible to estimate a user's emotions and provide feedback based on the emotions.

[0096] The NPS comment collection and analysis system can further include a behavioral analysis unit that optimizes the NPS comment collection strategy based on user behavioral data. The behavioral analysis unit analyzes user behavioral data on websites and applications and optimizes the NPS comment collection strategy based on this data. For example, the behavioral analysis unit analyzes information about pages frequently visited by users and links clicked by users, and optimizes the NPS comment collection strategy based on this data. The behavioral analysis unit can also analyze data such as user dwell time and scroll depth, and optimize the NPS comment collection strategy based on this data. Furthermore, the behavioral analysis unit can optimize the NPS comment collection strategy based on user behavioral data and propose measures to improve user satisfaction. This makes it possible to optimize the NPS comment collection strategy by utilizing user behavioral data.

[0097] The NPS comment collection and analysis system may further include a feedback analysis unit that optimizes the NPS comment collection strategy based on user feedback. The feedback analysis unit analyzes the content of feedback provided by users and optimizes the NPS comment collection strategy based on this data. For example, the feedback analysis unit analyzes the content of feedback provided by users and distinguishes between positive and negative feedback. The feedback analysis unit may also optimize the NPS comment collection strategy based on user feedback and propose measures to improve user satisfaction. The feedback analysis unit may also optimize the NPS comment collection strategy based on user feedback and propose measures to improve user satisfaction. In this way, the NPS comment collection strategy can be optimized by utilizing user feedback.

[0098] The NPS comment collection and analysis system can further include a report customization unit that customizes the content of reports based on user behavior data. The report customization unit analyzes user behavior data on websites and applications and customizes the content of reports based on this data. For example, the report customization unit analyzes information about pages frequently visited by users and links clicked by users, and customizes the content of reports based on this data. The report customization unit can also analyze data such as user dwell time and scrolling depth, and customize the content of reports based on this data. Furthermore, the report customization unit can customize the content of reports based on user behavior data and propose measures to improve user satisfaction. This makes it possible to customize the content of reports by utilizing user behavior data.

[0099] The NPS comment collection and analysis system may further include a report customization unit that customizes the content of the report based on user feedback. The report customization unit analyzes the content of the feedback provided by the user and customizes the content of the report based on this data. For example, the report customization unit may analyze the content of the feedback provided by the user and distinguish between positive feedback and negative feedback. The report customization unit may also customize the content of the report based on the user feedback and suggest measures to improve user satisfaction. The report customization unit may also customize the content of the report based on the user feedback and suggest measures to improve user satisfaction. In this way, the content of the report can be customized by utilizing user feedback.

[0100] The NPS comment collection and analysis system may further include a feedback providing unit that provides feedback based on user behavior data. The feedback providing unit analyzes user behavior data on websites and applications and provides feedback based on this data. For example, the feedback providing unit may analyze information about pages frequently visited by users and links clicked by users and provide feedback based on this data. The feedback providing unit may also analyze data such as the user's stay time and scrolling depth and provide feedback based on this data. Furthermore, the feedback providing unit may provide feedback based on the user behavior data and suggest measures to improve user satisfaction. In this way, feedback can be provided by utilizing user behavior data.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The comment collection unit automatically collects NPS comments about MNOs and MVNOs from multiple platforms on the Internet. For example, comments are collected from social media, blogs, review sites, etc. The comment collection unit can collect comments using web scraping technology or APIs. Step 2: The comment classification unit classifies the comments collected by the comment collection unit into positive and negative comments. For example, it uses a generation AI to analyze the sentiment of the comments and distinguish between comments that show positive sentiment and comments that show negative sentiment. The generation AI analyzes the sentiment of the comments using natural language processing technology. Step 3: The comment analysis unit performs a more detailed analysis of the comments classified by the comment classification unit. For example, if factors such as "price," "connection speed," and "customer support" appear frequently among positive comments, it determines that these are the factors that led to high ratings. Generative AI can then be used to analyze the content of the comments and quantify the intensity of their sentiment. Step 4: The report generation unit generates a result report based on the results analyzed by the comment analysis unit. For example, the report may include the ratio of positive and negative comments, evaluation factors, and specific comment examples. The generation AI can use emotion estimation functions to highlight the information that users are most interested in when generating the report.

[0103] 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.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] 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.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] 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.

[0130] 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.

[0131] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0132] 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.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The 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.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS 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).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] 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.

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 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 comment collection unit that automatically collects NPS comments about MNOs and MVNOs from multiple platforms on the Internet; a comment classification unit that classifies the comments collected by the comment collection unit into positive comments and negative comments; a comment analysis unit that analyzes the comments classified by the comment classification unit in more detail; a report generation unit that generates a result report based on the results of the analysis by the comment analysis unit. A system characterized by:

2. The comment collection unit Filter relevant comments using specific keywords or hashtags 2. The system of claim 1.

3. The comment classification unit The generative AI is used to analyze the sentiment of comments and distinguish between comments that express positive sentiment and comments that express negative sentiment.

2. The system of claim 1.

4. The comment analysis unit If factors such as price, connection speed, and customer support appear frequently among the positive comments, we will determine that these are the factors that led to high ratings.

2. The system of claim 1.

5. The report generation unit Generate a results report that includes the percentage of positive and negative comments, the factors that contributed to the evaluation, and specific examples of comments.

2. The system of claim 1.

Images