System

Abstract

An object of the system according to the embodiment is to analyze a comment or a behavior log and to evaluate and improve the acceptability of a service.SOLUTION: A system according to an embodiment includes a comment analysis unit, an action log analysis unit, a learning unit, an evaluation unit, and an improvement proposal unit. The comment analysis unit analyzes the content, text amount, and style of the comment. The action log analysis unit analyzes an action log of a user. The learning unit causes the system to learn based on the analysis results of the comment analysis unit and the action log analysis unit. The evaluation unit sets features of an assumed service and a user and evaluates an acceptability of the service. The improvement proposal unit finds out an improvement point of the service based on the evaluation result.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 technologies have not effectively utilized comments and behavior logs in evaluating service quality, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze comments and action logs to evaluate and improve the acceptability of a service. [Means for solving the problem]

[0006] The system according to the embodiment includes a comment analysis unit, an action log analysis unit, a learning unit, an evaluation unit, and an improvement proposal unit. The comment analysis unit analyzes the content, length, and style of comments. The action log analysis unit analyzes the user's action log. The learning unit trains the system based on the analysis results of the comment analysis unit and the action log analysis unit. The evaluation unit sets the expected service and user characteristics, and evaluates the acceptance of the service. The improvement proposal unit identifies areas for improvement in the service based on the evaluation results. [Effects of the Invention]

[0007] The system according to the embodiment can analyze comments and action logs to evaluate and improve the acceptability of the service. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The quality evaluation system according to an embodiment of the present invention is a system that evaluates the quality of a service using LY's proprietary generative AI. This system uses comments posted to LY's services, analyzes the content, length, and style of the comments, and combines them with a behavioral log (PV, CTR, number of reactions, positive / negative tendency, etc.), and trains the system to learn from them. This allows the quality evaluation system to comprehensively evaluate the quality of the service and increase its acceptance by users.

[0029] The quality evaluation system according to the embodiment includes a comment analysis unit, a behavior log analysis unit, a learning unit, an evaluation unit, and an improvement suggestion unit. The comment analysis unit analyzes the content, length, and style of a comment. For example, the comment analysis unit evaluates whether the content of a comment is positive or negative. The comment analysis unit can also evaluate whether the length of the comment is appropriate. The comment analysis unit can also evaluate whether the style is polite or casual. The behavior log analysis unit analyzes a user's behavior log. For example, the behavior log analysis unit analyzes page views and click-through rates. The behavior log analysis unit can also analyze the number of reactions. The behavior log analysis unit can also analyze positive / negative trends. The learning unit trains the system based on the analysis results of the comment analysis unit and the behavior log analysis unit. For example, the learning unit learns that services with many positive comments tend to receive high ratings. The learning unit can also learn that services with many negative comments tend to receive low ratings. The learning unit can also learn that specific behavior logs lead to high ratings. The evaluation unit sets the expected service and user characteristics and evaluates the service's acceptance. For example, the evaluation unit sets whether the service is aimed at young people or elderly people and performs the evaluation based on that. The evaluation unit can also evaluate the service's acceptance among specific user groups. The evaluation unit can also quantify the service's acceptance. The improvement suggestion unit identifies areas for improvement of the service based on the evaluation results. For example, if there are many negative comments, the improvement suggestion unit can identify the cause and propose improvements. If there are few positive comments, the improvement suggestion unit can also identify the cause and propose improvements. If a specific behavior log leads to a low rating, the improvement suggestion unit can also identify the cause and propose improvements. This allows the quality evaluation system according to the embodiment to comprehensively evaluate the quality of the service and increase its acceptance by users. For example, the output unit displays the evaluation results via a web application or a mobile application. If feedback is desired in paper form, the results are printed using a printer.Emailing provides immediate feedback by sending results directly to the user.

[0030] The comment analysis unit can analyze the writing style of comments and perform a detailed analysis of the impact of a particular writing style on user behavior. The comment analysis unit, for example, analyzes the writing style of comments and evaluates the impact of a polite or casual writing style on user behavior. For example, if there are many comments written in a polite style, it determines that the user's trustworthiness increases. The comment analysis unit also sets categories such as formal, informal, and emotional as a method for analyzing writing style. For example, it determines that comments written in a formal style have the effect of increasing the user's trustworthiness. The comment analysis unit also measures behavioral changes to evaluate the impact of writing style on user behavior. For example, it evaluates that if there are many comments written in a polite style, the user's click rate increases. This allows for a detailed analysis of the impact on user behavior through analysis of comment writing style.

[0031] The comment analysis unit classifies the content of comments using a topic model and can evaluate the impact of each topic on service quality. For example, the comment analysis unit classifies the content of comments using a topic model and evaluates the impact of each topic on service quality. For example, it determines that a service will be evaluated more highly if there are a lot of positive topics. The comment analysis unit also uses LDA (Latent Dirichlet Allocation) and NMF (Non-negative Matrix Factorization) as topic model types. For example, it uses LDA to classify comment topics and evaluate the impact of each topic. The comment analysis unit also sets major themes and sub-themes as a topic classification method. For example, it sets "ease of use of service" as the major theme and "interface design" as the sub-theme. This makes it possible to classify the content of comments using a topic model and evaluate the impact on service quality.

[0032] The behavior log analysis unit analyzes temporal fluctuations in the behavior log and can clarify the user's behavior pattern during a specific time period. The behavior log analysis unit, for example, analyzes temporal fluctuations in the behavior log and can clarify the user's behavior pattern during a specific time period. For example, it analyzes page views and click-through rates (CTR) during peak hours. The behavior log analysis unit also sets behavior patterns by time period in order to analyze temporal fluctuations. For example, it analyzes behavior patterns for morning, afternoon, and nighttime. The behavior log analysis unit also aggregates behavior logs during a specific time period in order to identify peak times. For example, it analyzes fluctuations in page views and CTR during a specific time period. This allows the analysis of temporal fluctuations in the behavior log and can clarify the user's behavior pattern during a specific time period.

[0033] The behavior log analysis unit can create user segments based on the behavior logs and evaluate the behavioral characteristics of each segment. The behavior log analysis unit, for example, creates user segments based on the behavior logs and evaluates the behavioral characteristics of each segment. For example, it creates segments based on age and gender. In addition, the behavior log analysis unit sets categories such as age, gender, and interests to create user segments. For example, it segments users by age and evaluates the behavioral characteristics of each segment. In addition, the behavior log analysis unit analyzes click history and viewing time to evaluate the behavioral characteristics of each segment. For example, it evaluates the click rate and viewing time in a specific segment. This makes it possible to create user segments based on the behavior logs and evaluate the behavioral characteristics of each segment.

[0034] The learning unit can enhance the training data and improve the evaluation accuracy under different scenarios and conditions. The learning unit, for example, enhances the training data and improves the evaluation accuracy under different scenarios and conditions. For example, data from different user demographics or time periods is added for training. The learning unit also sets the type of dataset and the data preprocessing method as the content of the training data. For example, user behavior logs and comment data are used as the type of dataset. The learning unit also uses algorithms and evaluation metrics for improving the evaluation accuracy. For example, precision, recall, F-measure, etc. are used as evaluation metrics. This makes it possible to improve the evaluation accuracy under different scenarios and conditions.

[0035] The evaluation unit can create an individual user profile based on the user's behavioral history and perform an individual evaluation. The evaluation unit, for example, creates an individual user profile based on the user's behavioral history and performs an individual evaluation. For example, the evaluation unit evaluates the user's interests and concerns based on past behavioral data. The evaluation unit also sets categories such as age, gender, and interests as a method of creating a user profile. For example, the evaluation unit profiles users by age and evaluates the behavioral characteristics of each profile. The evaluation unit also performs individual user behavior analysis and individual satisfaction evaluation as a method of individual evaluation. For example, it evaluates the degree to which a specific user is satisfied with a specific service. This makes it possible to create an individual user profile based on the user's behavioral history and perform an individual evaluation.

[0036] The evaluation unit can set the service features in detail and evaluate them under different service scenarios. For example, the evaluation unit sets the service features in detail and evaluates them under different service scenarios. For example, the evaluation unit sets the service functions and design in detail and evaluates them. The evaluation unit also sets a function list and a user interface as a method for setting the service features. For example, it creates a list of service functions and evaluates each function. The evaluation unit also sets a user scenario and a usage scenario as a method for setting the service scenario. For example, it evaluates the service based on a specific user scenario. This makes it possible to set the service features in detail and evaluate them under different service scenarios.

[0037] The improvement suggestion unit can set priorities for improvements and identify the most effective improvement measures. The improvement suggestion unit, for example, sets priorities for improvements and identifies the most effective improvement measures. For example, it sets priorities for improvements based on user feedback. The improvement suggestion unit also sets importance and urgency as a method for setting priorities. For example, it preferentially proposes improvements with high importance. The improvement suggestion unit also evaluates improvements to user satisfaction and performance improvements in order to identify effective improvement measures. For example, it identifies improvement measures that will increase user satisfaction. This makes it possible to set priorities for improvements and identify the most effective improvement measures.

[0038] The improvement suggestion unit can automatically generate improvement proposals and provide a specific action plan. For example, the improvement suggestion unit automatically generates improvement proposals and provides a specific action plan. For example, a generation AI automatically proposes improvements and indicates specific implementation steps. The improvement suggestion unit also uses a machine learning algorithm or a rule-based generation method to automatically generate proposals. For example, a machine learning algorithm is used to automatically generate improvements and provide a list of executable tasks. The improvement suggestion unit also sets a step-by-step guide or a list of executable tasks as the content of the action plan. For example, a step-by-step guide is provided and specific implementation steps are indicated. In this way, improvement proposals can be automatically generated and a specific action plan can be provided.

[0039] The improvement suggestion unit can add image data to the proposed improvement points and propose improvement measures that take visual elements into consideration. For example, the improvement suggestion unit adds image data to the proposed improvement points and proposes improvement measures that take visual elements into consideration. For example, it provides a visual prototype of the improvement points. Furthermore, the improvement suggestion unit sets screenshots or photographs as the content of the image data. For example, it provides a visual prototype of the improvement points using screenshots. Furthermore, the improvement suggestion unit evaluates the beauty and visual impact of the design to take visual elements into consideration. For example, it evaluates the beauty of the design and proposes improvement measures that have a high visual impact. In this way, it is possible to add image data to the proposed improvement points and propose improvement measures that take visual elements into consideration.

[0040] The improvement proposal department can repurpose the improvement proposals for other services and systems to develop general-purpose improvement measures. The improvement proposal department, for example, repurposes the improvement proposals for other services and systems to develop general-purpose improvement measures. For example, it creates improvement measures that can be applied to different industries or fields. The improvement proposal department also sets services of other companies in the same industry or related systems as the content of the other services. For example, it proposes improvement measures that can be applied to services of other companies in the same industry. The improvement proposal department also evaluates applicability in multiple systems to develop general-purpose improvement measures. For example, it evaluates applicability in different systems and develops general-purpose improvement measures. In this way, the improvement proposals can be repurposed for other services and systems to develop general-purpose improvement measures.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The quality evaluation system may further include a biometric information acquisition unit that acquires the user's biometric information. The biometric information acquisition unit measures, for example, the heart rate and electrodermal response to evaluate the user's stress level and excitement level. This allows for a more detailed evaluation of the service's acceptability based on the user's biometric information. For example, if the heart rate is elevated, it may be determined that the user is excited, suggesting that a particular element of the service is having a strong impact on the user. Furthermore, if the electrodermal response is high, it may be determined that the user is likely feeling stressed, and areas for improvement in the service may be identified. This allows for a more precise evaluation of the quality of the service by utilizing the user's biometric information.

[0043] The quality evaluation system may further include a geographic information acquisition unit that acquires geographic information of users. The geographic information acquisition unit, for example, acquires user location information and evaluates the acceptance of services by region. This makes it possible to identify the popularity and problems of services in specific regions. For example, it evaluates the difference in the acceptance of services between urban and rural areas and proposes improvement measures for each region. The geographic information acquisition unit can also analyze user behavior patterns based on the location information. For example, it analyzes user movement patterns in specific regions and evaluates service usage. This makes it possible to perform quality evaluation that takes geographical factors into account.

[0044] The behavior log analysis unit analyzes temporal fluctuations in the behavior log and can clarify the user's behavior pattern during a specific time period. For example, the behavior log analysis unit analyzes temporal fluctuations in the behavior log and can clarify the user's behavior pattern during a specific time period. For example, it analyzes page views and click-through rates (CTR) during peak hours. In addition, the behavior log analysis unit sets behavior patterns by time period in order to analyze temporal fluctuations. For example, it analyzes behavior patterns for morning, afternoon, and nighttime. In addition, the behavior log analysis unit aggregates behavior logs during a specific time period in order to identify peak times. For example, it analyzes fluctuations in page views and CTR during a specific time period. This allows the behavior log analysis unit to analyze temporal fluctuations in the behavior log and can clarify the user's behavior pattern during a specific time period.

[0045] The quality evaluation system can further include a purchase history analysis unit that analyzes the user's purchase history. The purchase history analysis unit, for example, analyzes the user's past purchase history and evaluates purchasing patterns and preferences. This makes it possible to evaluate the acceptability of a service based on the user's purchasing behavior. For example, a user who frequently purchases a particular product can be determined to have a high opinion of that product. The purchase history analysis unit can also create user segments based on the purchase history and evaluate the purchasing characteristics of each segment. For example, segments can be created based on age and gender, and the purchasing characteristics of each segment can be evaluated. This makes it possible to utilize the user's purchase history to evaluate the quality of a service.

[0046] The learning unit can enhance the training data and improve the evaluation accuracy under different scenarios and conditions. For example, the training data can be enhanced to improve the evaluation accuracy under different scenarios and conditions. For example, data from different user demographics or time periods can be added for training. The learning unit also sets the type of dataset and the data preprocessing method as the content of the training data. For example, user behavior logs and comment data can be used as the type of dataset. The learning unit also uses algorithms and evaluation metrics for improving the evaluation accuracy. For example, precision, recall, F-measure, etc. can be used as evaluation metrics. This makes it possible to improve the evaluation accuracy under different scenarios and conditions.

[0047] The processing flow of the first embodiment will be briefly explained below.

[0048] Step 1: The comment analysis unit analyzes the content, length, and style of the comment. For example, the comment analysis unit evaluates whether the content of the comment is positive or negative, whether the length is appropriate, and whether the style is polite or casual. Step 2: The behavior log analysis unit analyzes the user's behavior log. For example, the behavior log analysis unit analyzes page views and click-through rates, as well as the number of reactions and positive / negative trends. Step 3: The learning unit trains the system based on the analysis results of the comment analysis unit and the behavior log analysis unit. For example, the learning unit learns that services with many positive comments tend to receive high ratings, and that services with many negative comments tend to receive low ratings. It also learns that certain behavior logs lead to high ratings. Step 4: The evaluation unit determines the expected service and user characteristics and evaluates the service's acceptability. For example, the evaluation unit determines whether the service is aimed at young people or elderly people and evaluates it based on that. The evaluation unit also evaluates the service's acceptability for specific user groups and quantifies the service's acceptability. Step 5: The Improvement Proposal Department identifies areas for improvement in the service based on the evaluation results. For example, if there are many negative comments, the Improvement Proposal Department will identify the cause and propose improvements. Also, if there are few positive comments or if a specific behavioral log leads to a low rating, the department will identify the cause and propose improvements.

[0049] (Example 2) The quality evaluation system according to an embodiment of the present invention is a system that evaluates the quality of a service using LY's proprietary generative AI. This system uses comments posted to LY's services, analyzes the content, length, and style of the comments, and combines them with a behavioral log (PV, CTR, number of reactions, positive / negative tendency, etc.), and trains the system to learn from them. This allows the quality evaluation system to comprehensively evaluate the quality of the service and increase its acceptance by users.

[0050] The quality evaluation system according to the embodiment includes a comment analysis unit, a behavior log analysis unit, a learning unit, an evaluation unit, and an improvement suggestion unit. The comment analysis unit analyzes the content, length, and style of a comment. For example, the comment analysis unit evaluates whether the content of a comment is positive or negative. The comment analysis unit can also evaluate whether the length of the comment is appropriate. The comment analysis unit can also evaluate whether the style is polite or casual. The behavior log analysis unit analyzes a user's behavior log. For example, the behavior log analysis unit analyzes page views and click-through rates. The behavior log analysis unit can also analyze the number of reactions. The behavior log analysis unit can also analyze positive / negative trends. The learning unit trains the system based on the analysis results of the comment analysis unit and the behavior log analysis unit. For example, the learning unit learns that services with many positive comments tend to receive high ratings. The learning unit can also learn that services with many negative comments tend to receive low ratings. The learning unit can also learn that specific behavior logs lead to high ratings. The evaluation unit sets the expected service and user characteristics and evaluates the service's acceptance. For example, the evaluation unit sets whether the service is aimed at young people or elderly people and performs the evaluation based on that. The evaluation unit can also evaluate the service's acceptance among specific user groups. The evaluation unit can also quantify the service's acceptance. The improvement suggestion unit identifies areas for improvement of the service based on the evaluation results. For example, if there are many negative comments, the improvement suggestion unit can identify the cause and propose improvements. If there are few positive comments, the improvement suggestion unit can also identify the cause and propose improvements. If a specific behavior log leads to a low rating, the improvement suggestion unit can also identify the cause and propose improvements. This allows the quality evaluation system according to the embodiment to comprehensively evaluate the quality of the service and increase its acceptance by users. For example, the output unit displays the evaluation results via a web application or a mobile application. If feedback is desired in paper form, the results are printed using a printer.Emailing provides immediate feedback by sending results directly to the user.

[0051] The comment analysis unit can estimate the emotion of a comment and evaluate the impact of the comment based on the intensity and type of emotion. The comment analysis unit, for example, estimates the emotion of a comment and quantifies the intensity and type of emotion. For example, it scores emotions such as joy, sadness, and anger, and prioritizes evaluation of comments with high scores for a particular emotion. The comment analysis unit also sets an intensity level of emotion to evaluate the intensity of emotion. For example, it evaluates the intensity of emotion on a scale of 1 to 5. The comment analysis unit also sets categories of positive, negative, and neutral to classify the type of emotion. For example, it determines that positive comments tend to receive high ratings. This makes it possible to evaluate the impact of a comment by estimating the emotion of the comment.

[0052] The comment analysis unit can analyze the writing style of comments and perform a detailed analysis of the impact of a particular writing style on user behavior. The comment analysis unit, for example, analyzes the writing style of comments and evaluates the impact of a polite or casual writing style on user behavior. For example, if there are many comments written in a polite style, it determines that the user's trustworthiness increases. The comment analysis unit also sets categories such as formal, informal, and emotional as a method for analyzing writing style. For example, it determines that comments written in a formal style have the effect of increasing the user's trustworthiness. The comment analysis unit also measures behavioral changes to evaluate the impact of writing style on user behavior. For example, it evaluates that if there are many comments written in a polite style, the user's click rate increases. This allows for a detailed analysis of the impact on user behavior through analysis of comment writing style.

[0053] The comment analysis unit classifies the content of comments using a topic model and can evaluate the impact of each topic on service quality. For example, the comment analysis unit classifies the content of comments using a topic model and evaluates the impact of each topic on service quality. For example, it determines that a service will be evaluated more highly if there are a lot of positive topics. The comment analysis unit also uses LDA (Latent Dirichlet Allocation) and NMF (Non-negative Matrix Factorization) as topic model types. For example, it uses LDA to classify comment topics and evaluate the impact of each topic. The comment analysis unit also sets major themes and sub-themes as a topic classification method. For example, it sets "ease of use of service" as the major theme and "interface design" as the sub-theme. This makes it possible to classify the content of comments using a topic model and evaluate the impact on service quality.

[0054] The behavior log analysis unit analyzes temporal fluctuations in the behavior log and can clarify the user's behavior pattern during a specific time period. The behavior log analysis unit, for example, analyzes temporal fluctuations in the behavior log and can clarify the user's behavior pattern during a specific time period. For example, it analyzes page views and click-through rates (CTR) during peak hours. The behavior log analysis unit also sets behavior patterns by time period in order to analyze temporal fluctuations. For example, it analyzes behavior patterns for morning, afternoon, and nighttime. The behavior log analysis unit also aggregates behavior logs during a specific time period in order to identify peak times. For example, it analyzes fluctuations in page views and CTR during a specific time period. This allows the analysis of temporal fluctuations in the behavior log and can clarify the user's behavior pattern during a specific time period.

[0055] The behavior log analysis unit can create user segments based on the behavior logs and evaluate the behavioral characteristics of each segment. The behavior log analysis unit, for example, creates user segments based on the behavior logs and evaluates the behavioral characteristics of each segment. For example, it creates segments based on age and gender. In addition, the behavior log analysis unit sets categories such as age, gender, and interests to create user segments. For example, it segments users by age and evaluates the behavioral characteristics of each segment. In addition, the behavior log analysis unit analyzes click history and viewing time to evaluate the behavioral characteristics of each segment. For example, it evaluates the click rate and viewing time in a specific segment. This makes it possible to create user segments based on the behavior logs and evaluate the behavioral characteristics of each segment.

[0056] The behavior log analysis unit can perform emotion estimation from the behavior log and analyze the impact of specific behaviors on the user's emotions. The behavior log analysis unit, for example, performs emotion estimation from the behavior log and analyzes the impact of specific behaviors on the user's emotions. For example, it evaluates whether specific behaviors cause positive emotions. The behavior log analysis unit also uses emotion analysis and natural language processing technology as a method of emotion estimation. For example, it uses emotion analysis to estimate emotions from the behavior log and evaluates the impact of specific behaviors on the user's emotions. The behavior log analysis unit also sets clicks, purchases, views, etc. as the content of specific behaviors. For example, it evaluates whether click behaviors cause positive emotions. In this way, it is possible to analyze the impact of specific behaviors on the user's emotions by estimating emotions from the behavior log.

[0057] The learning unit can add emotion estimation results to training data and build a quality evaluation model that takes emotional elements into consideration. The learning unit, for example, adds emotion estimation results to training data and builds a quality evaluation model that takes emotional elements into consideration. For example, data with a high percentage of positive emotions is preferentially trained. The learning unit also sets emotion scores and emotion types as the content of the emotion estimation results. For example, the learning unit classifies training data based on the emotion scores and builds a quality evaluation model that takes emotional elements into consideration. The learning unit also uses machine learning models and evaluation indices as a method for building the quality evaluation model. For example, a quality evaluation model that takes emotional elements into consideration is built using a machine learning model. In this way, a quality evaluation model that takes emotional elements into consideration can be built.

[0058] The learning unit can enhance the training data and improve the evaluation accuracy under different scenarios and conditions. The learning unit, for example, enhances the training data and improves the evaluation accuracy under different scenarios and conditions. For example, data from different user demographics or time periods is added for training. The learning unit also sets the type of dataset and the data preprocessing method as the content of the training data. For example, user behavior logs and comment data are used as the type of dataset. The learning unit also uses algorithms and evaluation metrics for improving the evaluation accuracy. For example, precision, recall, F-measure, etc. are used as evaluation metrics. This makes it possible to improve the evaluation accuracy under different scenarios and conditions.

[0059] The evaluation unit can estimate a user's emotions and evaluate the degree of service acceptance for a user in a specific emotional state. The evaluation unit, for example, estimates a user's emotions and evaluates the degree of service acceptance for a user in a specific emotional state. For example, it evaluates the degree to which a user in a positive emotional state will accept a service. The evaluation unit also uses emotion analysis and natural language processing technology as a method of emotion estimation. For example, it estimates a user's emotional state using emotion analysis and evaluates the degree of service acceptance for a user in a specific emotional state. The evaluation unit also sets positive, negative, and neutral categories as a method of classifying emotional states. For example, it determines that users in a positive emotional state tend to rate a service highly. This makes it possible to evaluate the degree of service acceptance for a user in a specific emotional state.

[0060] The evaluation unit can create an individual user profile based on the user's behavioral history and perform an individual evaluation. The evaluation unit, for example, creates an individual user profile based on the user's behavioral history and performs an individual evaluation. For example, the evaluation unit evaluates the user's interests and concerns based on past behavioral data. The evaluation unit also sets categories such as age, gender, and interests as a method of creating a user profile. For example, the evaluation unit profiles users by age and evaluates the behavioral characteristics of each profile. The evaluation unit also performs individual user behavior analysis and individual satisfaction evaluation as a method of individual evaluation. For example, it evaluates the degree to which a specific user is satisfied with a specific service. This makes it possible to create an individual user profile based on the user's behavioral history and perform an individual evaluation.

[0061] The evaluation unit can set the service features in detail and evaluate them under different service scenarios. For example, the evaluation unit sets the service features in detail and evaluates them under different service scenarios. For example, the evaluation unit sets the service functions and design in detail and evaluates them. The evaluation unit also sets a function list and a user interface as a method for setting the service features. For example, it creates a list of service functions and evaluates each function. The evaluation unit also sets a user scenario and a usage scenario as a method for setting the service scenario. For example, it evaluates the service based on a specific user scenario. This makes it possible to set the service features in detail and evaluate them under different service scenarios.

[0062] The improvement suggestion unit can reflect the emotion estimation results in the improvement proposals and propose emotionally positive improvement measures. For example, the improvement suggestion unit reflects the emotion estimation results in the improvement proposals and proposes emotionally positive improvement measures. For example, it prioritizes the proposals of improvement measures that involve a lot of positive emotions. Furthermore, the improvement suggestion unit sets an emotion score or an emotion type as the content of the emotion estimation results. For example, it classifies improvement measures based on the emotion score and proposes improvement measures that involve a lot of positive emotions. Furthermore, the improvement suggestion unit sets a method for reflecting the emotion analysis results in order to take emotional factors into consideration. For example, it sets the priority of improvement measures based on the emotion analysis results. In this way, it is possible to reflect the emotion estimation results and propose emotionally positive improvement measures.

[0063] The improvement suggestion unit can set priorities for improvements and identify the most effective improvement measures. The improvement suggestion unit, for example, sets priorities for improvements and identifies the most effective improvement measures. For example, it sets priorities for improvements based on user feedback. The improvement suggestion unit also sets importance and urgency as a method for setting priorities. For example, it preferentially proposes improvements with high importance. The improvement suggestion unit also evaluates improvements to user satisfaction and performance improvements in order to identify effective improvement measures. For example, it identifies improvement measures that will increase user satisfaction. This makes it possible to set priorities for improvements and identify the most effective improvement measures.

[0064] The improvement suggestion unit can automatically generate improvement proposals and provide a specific action plan. For example, the improvement suggestion unit automatically generates improvement proposals and provides a specific action plan. For example, a generation AI automatically proposes improvements and indicates specific implementation steps. The improvement suggestion unit also uses a machine learning algorithm or a rule-based generation method to automatically generate proposals. For example, a machine learning algorithm is used to automatically generate improvements and provide a list of executable tasks. The improvement suggestion unit also sets a step-by-step guide or a list of executable tasks as the content of the action plan. For example, a step-by-step guide is provided and specific implementation steps are indicated. In this way, improvement proposals can be automatically generated and a specific action plan can be provided.

[0065] The improvement suggestion unit can add image data to the proposed improvement points and propose improvement measures that take visual elements into consideration. For example, the improvement suggestion unit adds image data to the proposed improvement points and proposes improvement measures that take visual elements into consideration. For example, it provides a visual prototype of the improvement points. Furthermore, the improvement suggestion unit sets screenshots or photographs as the content of the image data. For example, it provides a visual prototype of the improvement points using screenshots. Furthermore, the improvement suggestion unit evaluates the beauty and visual impact of the design to take visual elements into consideration. For example, it evaluates the beauty of the design and proposes improvement measures that have a high visual impact. In this way, it is possible to add image data to the proposed improvement points and propose improvement measures that take visual elements into consideration.

[0066] The improvement proposal department can repurpose the improvement proposals for other services and systems to develop general-purpose improvement measures. The improvement proposal department, for example, repurposes the improvement proposals for other services and systems to develop general-purpose improvement measures. For example, it creates improvement measures that can be applied to different industries or fields. The improvement proposal department also sets services of other companies in the same industry or related systems as the content of the other services. For example, it proposes improvement measures that can be applied to services of other companies in the same industry. The improvement proposal department also evaluates applicability in multiple systems to develop general-purpose improvement measures. For example, it evaluates applicability in different systems and develops general-purpose improvement measures. In this way, the improvement proposals can be repurposed for other services and systems to develop general-purpose improvement measures.

[0067] The improvement suggestion unit uses the emotion estimation function to monitor the user's emotional reactions to the improvement points in real time, and can continuously search for optimal improvement measures. The improvement suggestion unit, for example, uses the emotion estimation function to monitor the user's emotional reactions to the improvement points in real time. For example, it prioritizes the adoption of improvement points that have a high proportion of positive emotions. The improvement suggestion unit also sets emotion analysis and natural language processing technology as the content of the emotion estimation function. For example, it uses emotion analysis to monitor the user's emotional reactions in real time. The improvement suggestion unit also sets real-time emotion scores and emotion types to monitor the emotional reactions. For example, it evaluates the improvement points based on the real-time emotion scores. The improvement suggestion unit also sets a feedback loop and continuous evaluation and improvement to continuously search for optimal improvement measures. For example, it uses a feedback loop to continuously evaluate the improvement points and search for optimal improvement measures. In this way, it is possible to use the emotion estimation function to monitor the user's emotional reactions to the improvement points in real time, and continuously search for optimal improvement measures.

[0068] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0069] The quality evaluation system may further include a biometric information acquisition unit that acquires the user's biometric information. The biometric information acquisition unit measures, for example, the heart rate and electrodermal response to evaluate the user's stress level and excitement level. This allows for a more detailed evaluation of the service's acceptability based on the user's biometric information. For example, if the heart rate is elevated, it may be determined that the user is excited, suggesting that a particular element of the service is having a strong impact on the user. Furthermore, if the electrodermal response is high, it may be determined that the user is likely feeling stressed, and areas for improvement in the service may be identified. This allows for a more precise evaluation of the quality of the service by utilizing the user's biometric information.

[0070] The comment analysis unit can estimate the emotion of a comment and evaluate the impact of the comment based on the intensity and type of emotion. For example, it estimates the emotion of a comment and quantifies the intensity and type of emotion. For example, it scores emotions such as joy, sadness, and anger, and prioritizes comments with high scores for a particular emotion. The comment analysis unit also sets an intensity level of emotion to evaluate the intensity of the emotion. For example, it rates the intensity of emotion on a scale of 1 to 5. The comment analysis unit also sets categories of positive, negative, and neutral to classify the type of emotion. For example, it determines that positive comments tend to receive high ratings. This makes it possible to evaluate the impact of a comment by estimating the emotion of the comment.

[0071] The quality evaluation system may further include a geographic information acquisition unit that acquires geographic information of users. The geographic information acquisition unit, for example, acquires user location information and evaluates the acceptance of services by region. This makes it possible to identify the popularity and problems of services in specific regions. For example, it evaluates the difference in the acceptance of services between urban and rural areas and proposes improvement measures for each region. The geographic information acquisition unit can also analyze user behavior patterns based on the location information. For example, it analyzes user movement patterns in specific regions and evaluates service usage. This makes it possible to perform quality evaluation that takes geographical factors into account.

[0072] The comment analysis unit classifies the content of comments using a topic model and can evaluate the impact of each topic on service quality. For example, the content of comments can be classified using a topic model and the impact of each topic on service quality can be evaluated. For example, if there are many positive topics, it can be determined that the service will be evaluated highly. The comment analysis unit also uses LDA (Latent Dirichlet Allocation) and NMF (Non-negative Matrix Factorization) as topic model types. For example, it can use LDA to classify comment topics and evaluate the impact of each topic. The comment analysis unit also sets major themes and sub-themes as a method of classifying topics. For example, it can set "ease of use of service" as the major theme and "interface design" as the sub-theme. This makes it possible to classify the content of comments using a topic model and evaluate the impact on service quality.

[0073] The behavior log analysis unit analyzes temporal fluctuations in the behavior log and can clarify the user's behavior pattern during a specific time period. For example, the behavior log analysis unit analyzes temporal fluctuations in the behavior log and can clarify the user's behavior pattern during a specific time period. For example, it analyzes page views and click-through rates (CTR) during peak hours. In addition, the behavior log analysis unit sets behavior patterns by time period in order to analyze temporal fluctuations. For example, it analyzes behavior patterns for morning, afternoon, and nighttime. In addition, the behavior log analysis unit aggregates behavior logs during a specific time period in order to identify peak times. For example, it analyzes fluctuations in page views and CTR during a specific time period. This allows the behavior log analysis unit to analyze temporal fluctuations in the behavior log and can clarify the user's behavior pattern during a specific time period.

[0074] The quality evaluation system may further include a voice analysis unit that analyzes the user's voice data. The voice analysis unit, for example, analyzes the user's voice data and evaluates the tone and speed of the voice. This makes it possible to estimate the user's emotional state and stress level. For example, if the voice tone is high, it may be determined that the user is excited, suggesting that a particular element of the service is having a strong impact on the user. Also, if the voice speed is fast, it may be determined that the user is impatient, making it possible to identify areas for improvement in the service. This makes it possible to utilize the user's voice data to more precisely evaluate the quality of the service.

[0075] The behavior log analysis unit can perform emotion estimation from the behavior log and analyze the impact of specific behavior on the user's emotions. For example, it can perform emotion estimation from the behavior log and analyze the impact of specific behavior on the user's emotions. For example, it can evaluate whether specific behavior causes positive emotions. The behavior log analysis unit also uses emotion analysis and natural language processing technology as a method of emotion estimation. For example, it can estimate emotions from the behavior log using emotion analysis and evaluate the impact of specific behavior on the user's emotions. The behavior log analysis unit also sets clicks, purchases, views, etc. as the content of specific behavior. For example, it evaluates whether click behavior causes positive emotions. In this way, it is possible to analyze the impact of specific behavior on the user's emotions by estimating emotions from the behavior log.

[0076] The quality evaluation system can further include a purchase history analysis unit that analyzes the user's purchase history. The purchase history analysis unit, for example, analyzes the user's past purchase history and evaluates purchasing patterns and preferences. This makes it possible to evaluate the acceptability of a service based on the user's purchasing behavior. For example, a user who frequently purchases a particular product can be determined to have a high opinion of that product. The purchase history analysis unit can also create user segments based on the purchase history and evaluate the purchasing characteristics of each segment. For example, segments can be created based on age and gender, and the purchasing characteristics of each segment can be evaluated. This makes it possible to utilize the user's purchase history to evaluate the quality of a service.

[0077] The learning unit can enhance the training data and improve the evaluation accuracy under different scenarios and conditions. For example, the training data can be enhanced to improve the evaluation accuracy under different scenarios and conditions. For example, data from different user demographics or time periods can be added for training. The learning unit also sets the type of dataset and the data preprocessing method as the content of the training data. For example, user behavior logs and comment data can be used as the type of dataset. The learning unit also uses algorithms and evaluation metrics for improving the evaluation accuracy. For example, precision, recall, F-measure, etc. can be used as evaluation metrics. This makes it possible to improve the evaluation accuracy under different scenarios and conditions.

[0078] The quality evaluation system may further include a social media analysis unit that analyzes users' social media activities. The social media analysis unit may, for example, analyze users' posts and reactions on social media to evaluate their interests. This allows the acceptance of a service to be evaluated based on the users' social media activities. For example, a user who posts frequently on a particular topic may be determined to have a high interest in that topic. The social media analysis unit may also analyze users' emotions on social media to evaluate their emotional reactions. For example, it may be determined that posts with many positive reactions tend to receive high ratings. This allows the quality of a service to be evaluated by utilizing users' social media activities.

[0079] The processing flow of the second embodiment will be briefly explained below.

[0080] Step 1: The comment analysis unit analyzes the content, length, and style of the comment. For example, the comment analysis unit evaluates whether the content of the comment is positive or negative, whether the length is appropriate, and whether the style is polite or casual. Step 2: The behavior log analysis unit analyzes the user's behavior log. For example, the behavior log analysis unit analyzes page views and click-through rates, as well as the number of reactions and positive / negative trends. Step 3: The learning unit trains the system based on the analysis results of the comment analysis unit and the behavior log analysis unit. For example, the learning unit learns that services with many positive comments tend to receive high ratings, and that services with many negative comments tend to receive low ratings. It also learns that certain behavior logs lead to high ratings. Step 4: The evaluation unit determines the expected service and user characteristics and evaluates the service's acceptability. For example, the evaluation unit determines whether the service is aimed at young people or elderly people and evaluates it based on that. The evaluation unit also evaluates the service's acceptability for specific user groups and quantifies the service's acceptability. Step 5: The Improvement Proposal Department identifies areas for improvement in the service based on the evaluation results. For example, if there are many negative comments, the Improvement Proposal Department will identify the cause and propose improvements. Also, if there are few positive comments or if a specific behavioral log leads to a low rating, the department will identify the cause and propose improvements.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0085] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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).

[0090] 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.

[0091] 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.

[0092] 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.

[0093] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0094] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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).

[0105] 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.

[0106] 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.

[0107] 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.

[0108] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0109] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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).

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0125] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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."

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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]

[0148] 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 analysis unit that analyzes the content, length, and style of comments; a behavior log analysis unit that analyzes a user's behavior log; a learning unit that causes the system to learn based on the analysis results of the comment analysis unit and the action log analysis unit; an evaluation unit that sets assumed services and user characteristics and evaluates the acceptability of the services; An improvement proposal department that identifies areas for improvement in the service based on the evaluation results. A system characterized by:

2. The behavior log analysis unit Analyzing temporal fluctuations in the behavior log to clarify the behavioral patterns of the user during a specific time period 2. The system of claim 1.

3. The learning unit Add emotion estimation results to training data to build a quality assessment model that takes emotional factors into account 2. The system of claim 1.

4. The evaluation unit Estimating the user's emotions and evaluating the acceptability of the service to the user in a particular emotional state 2. The system of claim 1.

5. The improvement suggestion unit The results of emotion estimation are reflected in the proposed improvements, and emotionally positive improvements are proposed.

2. The system of claim 1.

Images