System

Abstract

An object of a system according to an embodiment is to monitor evaluation data of a customer in real time and to quickly and appropriately respond to a market trend or consumer satisfaction.SOLUTION: A system includes an evaluation data aggregation part, a trend analysis part, a graph display part, an alert notification part, and an interactive analysis part. The evaluation data aggregation unit aggregates the evaluation data along a time axis. The trend analysis unit performs trend analysis based on the evaluation data aggregated by the evaluation data aggregation unit. The graph display unit generates and displays a transition graph based on the result obtained by the trend analysis unit. The alert notification unit detects an abnormal evaluation from the evaluation data and performs alert notification. The interactive analysis unit analyzes the evaluation data through interaction with the user.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 had the problem of making it difficult to monitor customer evaluation data in real time and respond quickly and appropriately to market trends and consumer satisfaction levels.

[0005] The system according to the embodiment aims to monitor customer evaluation data in real time and respond quickly and appropriately to market trends and consumer satisfaction. [Means for solving the problem]

[0006] The system according to the embodiment includes an evaluation data aggregation unit, a trend analysis unit, a graph display unit, an alert notification unit, and an interactive analysis unit. The evaluation data aggregation unit aggregates evaluation data along a time axis. The trend analysis unit performs trend analysis based on the evaluation data aggregated by the evaluation data aggregation unit. The graph display unit generates and displays a transition graph based on the results obtained by the trend analysis unit. The alert notification unit detects abnormal evaluations from the evaluation data and issues an alert notification. The interactive analysis unit analyzes the evaluation data through dialogue with the user. [Effects of the Invention]

[0007] The system according to the embodiment can monitor customer evaluation data in real time and respond quickly and appropriately to market trends and consumer satisfaction. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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 evaluation monitoring system according to an embodiment of the present invention aggregates customer evaluations of products and services over time, and provides trend analysis, graph display of changes, alert notifications for abnormal evaluations, and interactive analysis functions. This allows the evaluation monitoring system to monitor evaluation changes in real time and respond quickly and appropriately to market trends and consumer satisfaction.

[0029] A rating monitoring system according to an embodiment includes a rating data aggregation unit, a trend analysis unit, a graph display unit, an alert notification unit, and an interactive analysis unit. The rating data aggregation unit aggregates rating data along a time axis. For example, the generation AI collects rating data from online reviews, survey results, social media comments, etc., and aggregates it along a time axis. The generation AI receives a prompt including, for example, an instruction such as "Please aggregate rating data from January 2023 to December 2023," and aggregates the data based on the instruction. The trend analysis unit performs trend analysis based on the aggregated rating data. For example, the generation AI receives a prompt including an instruction such as "Please analyze the rating trends over the past six months," and analyzes upward or downward trends in ratings based on the instruction. The generation AI analyzes trends using techniques such as moving averages and regression analysis. The graph display unit generates and displays a trend graph based on the results of the trend analysis. For example, the generation AI receives a prompt including an instruction such as "Please display the rating trends in a graph," and visually displays the rating trends based on the instruction. The generation AI generates a trend graph in the form of a line graph or bar graph. The alert notification unit detects abnormal ratings from the rating data and issues an alert. For example, the generation AI receives a prompt including the instruction "Detect abnormal ratings and issue an alert." Based on the instruction, the generation AI detects abnormal ratings and notifies the responsible party. The generation AI detects abnormal ratings using techniques such as statistical outlier detection and rule-based anomaly detection. The interactive analysis unit analyzes the rating data through dialogue with the user. For example, in response to a user's question, "What are the recent rating trends?", the generation AI analyzes the question and generates an appropriate answer. The generation AI uses natural language processing technology to analyze the user's question and generate an appropriate answer. This allows the rating monitoring system according to the embodiment to monitor rating changes in real time and respond quickly and appropriately to market trends and consumer satisfaction. For example, if the ratings of a new product suddenly drop, the cause can be quickly identified and improvement measures can be implemented. Furthermore, by understanding the upward trend in ratings, successful measures can be continuously implemented.

[0030] The evaluation data aggregation unit can collect evaluation data from online reviews, survey results, and social media comments. The evaluation data aggregation unit, for example, collects evaluation data from online review sites. For example, it collects data from sites such as Amazon reviews and Google reviews. The evaluation data aggregation unit also collects survey results. For example, it collects data from online surveys and paper-based surveys. The evaluation data aggregation unit also collects social media comments. For example, it collects comments from platforms such as Twitter and Facebook. This allows for more comprehensive evaluation by collecting evaluation data from a variety of sources.

[0031] The evaluation data aggregating unit can simultaneously collect background information (age, gender, region) of the rater when collecting evaluation data. The evaluation data aggregating unit, for example, collects the age of the rater when collecting evaluation data. For example, it adds a field for entering the rater's age to an online review submission form and stores that information together with the evaluation data. The evaluation data aggregating unit also collects the gender of the rater. For example, it adds a field for entering the rater's gender when collecting survey results and stores that information together with the evaluation data. The evaluation data aggregating unit also collects the region of the rater. For example, it obtains the region information of the rater when collecting social media comments and stores that information together with the evaluation data. This enables multifaceted analysis of the evaluation data.

[0032] The evaluation data aggregation unit collects evaluation data in real time and can instantly reflect the evaluations in the database each time they are posted. The evaluation data aggregation unit, for example, collects evaluation data in real time. For example, by using the API of an online review site or social media, the evaluations are stored in the database as soon as they are posted. The evaluation data aggregation unit also instantly reflects the evaluations in the database each time they are posted. For example, by using real-time data processing technology, the evaluation data is instantly stored in the database. The evaluation data aggregation unit also updates the evaluation data in real time. For example, the evaluation data is updated and immediately reflected in the database. This allows for rapid response by collecting evaluation data in real time and instantly reflecting it.

[0033] The evaluation data aggregation unit can integrate evaluation data from different platforms and perform comprehensive evaluation aggregation. The evaluation data aggregation unit integrates evaluation data from social media, for example. For example, it uses the APIs of Twitter and Facebook to collect customer evaluation comments and store them in a database. The evaluation data aggregation unit also integrates evaluation data from blogs. For example, it uses the RSS feed of a blog to collect evaluation comments and store them in a database. The evaluation data aggregation unit also integrates evaluation data from forums. For example, it collects forum posting data and stores it in a database. In this way, by integrating evaluation data from different platforms, more comprehensive evaluations are possible.

[0034] The trend analysis unit can perform trend prediction with higher accuracy by taking into account the seasonality of the evaluation data and the influence of events. The trend analysis unit, for example, takes into account the seasonality of the evaluation data. For example, it analyzes seasonal evaluation trends based on past data and predicts seasonal trends. The trend analysis unit also takes into account the influence of events. For example, it reflects the influence of promotional events and social events in the evaluation data. The trend analysis unit also performs trend prediction with higher accuracy by taking into account the seasonality of the evaluation data and the influence of events. For example, it uses techniques such as moving average and regression analysis to perform trend prediction with higher accuracy by taking into account the influence of seasonality and events.

[0035] The trend analysis unit can generate a prediction model for future ratings based on the trend analysis results and provide the prediction results. The trend analysis unit, for example, generates a prediction model for future ratings based on the trend analysis results. For example, it trains a machine learning model using past rating data to predict future ratings. The trend analysis unit also provides the prediction results. For example, it predicts future ratings using the generated prediction model and provides the results to the user. The trend analysis unit also suggests countermeasures based on the prediction results. For example, it suggests measures to prevent a decline in ratings based on the prediction results. This makes it possible to take countermeasures in advance by predicting future ratings.

[0036] The trend analysis unit displays the trend analysis results separately for different regions or market segments, thereby clarifying the trends for each region. The trend analysis unit, for example, displays the trend analysis results separately for different regions. For example, it analyzes trends based on the evaluation data for each region and displays the evaluation trends for each region. The trend analysis unit also displays the trend analysis results for each market segment. For example, it classifies the evaluation data by age group or income group and displays the trends for each segment. The trend analysis unit also displays the evaluation data on a map to clarify the trends for each region. For example, it plots the evaluation data for each region on a map to visually display the evaluation trends for each region. This makes it possible to understand trends specific to each region by clarifying the trends for each region.

[0037] The trend analysis unit can integrate the trend analysis results with other business data (sales data, marketing data) to provide comprehensive business insights. The trend analysis unit, for example, integrates the trend analysis results with sales data. For example, it combines evaluation data and sales data to analyze the impact of changes in evaluation on sales. The trend analysis unit also integrates the trend analysis results with marketing data. For example, it combines evaluation data with marketing campaign data to evaluate the effectiveness of the campaign. The trend analysis unit also integrates multiple business data to provide comprehensive business insights. For example, it combines evaluation data, sales data, and marketing data to provide comprehensive business insights. This makes it possible to provide comprehensive business insights by integrating with business data.

[0038] The graph display unit can add interactive elements to the transition graph, allowing the user to select a specific period or evaluation item to view details. The graph display unit, for example, adds interactive elements to the transition graph. For example, a user can drag to select a specific period on the graph and display detailed data for that period. The graph display unit also allows the user to select a specific evaluation item to view details. For example, a filtering function can be added for each evaluation item to display detailed data related to a specific item. The graph display unit also uses interactive elements to make it easier for the user to operate the graph. For example, clickable data points or tooltips can be added to display detailed information. This allows the user to select a specific period or evaluation item to view details, enabling more detailed analysis.

[0039] The graph display unit can display the attributes of the evaluators (age, gender, region) on a transition graph, enabling the transition of evaluations to be analyzed from multiple angles. The graph display unit, for example, displays the attributes of the evaluators on the transition graph. For example, the evaluation data and the attribute data of the evaluators are linked, and the attribute information is displayed on the graph. The graph display unit also displays the transition of evaluations for each attribute of the evaluators. For example, the evaluation data is classified by age group or gender, and the transition of evaluations for each attribute is displayed. The graph display unit also uses the attributes of the evaluators to analyze the transition of evaluations from multiple angles. For example, the evaluation data for each region is plotted on a map, and the evaluation trends for each region are visually displayed. In this way, by displaying the attributes of the evaluators, the transition of evaluations can be analyzed from multiple angles.

[0040] The graph display unit can employ a responsive design so that the transition graph can be optimally displayed on different devices (smartphones, tablets, and PCs). The graph display unit employs a responsive design so that the transition graph can be optimally displayed on different devices. For example, the graph layout can be automatically adjusted according to the screen size of the smartphone, tablet, or PC. The graph display unit also supports touch and mouse operations to improve operability on different devices. For example, the graph can be operated by touch on a smartphone or tablet, and by mouse on a PC. The graph display unit also provides the optimal display format for each device. For example, a portrait display format can be used on a smartphone, and a landscape display format can be used on a PC. This improves user convenience by providing optimal display on different devices.

[0041] The graph display unit can link the transition graph with other business data (sales data, marketing data) to provide comprehensive business insights. The graph display unit, for example, links the transition graph with sales data. For example, it combines evaluation data and sales data to analyze the impact of changes in evaluation on sales and displays the results in a graph. The graph display unit also links the transition graph with marketing data. For example, it combines evaluation data and marketing campaign data to evaluate the effectiveness of the campaign and displays the results in a graph. The graph display unit also links multiple business data to provide comprehensive business insights. For example, it combines evaluation data, sales data, and marketing data to provide comprehensive business insights. This makes it possible to provide comprehensive business insights by linking with business data.

[0042] The alert notification unit improves the anomaly evaluation detection algorithm and can detect anomaly patterns in the evaluation data with higher accuracy. The alert notification unit, for example, improves the anomaly evaluation detection algorithm. For example, it uses machine learning technology to automatically learn anomaly patterns and improve detection accuracy. The alert notification unit also detects anomaly patterns in the evaluation data with higher accuracy. For example, it improves statistical outliers or rule-based anomaly detection algorithms to improve the accuracy of detecting anomaly patterns. The alert notification unit also issues an alert based on the detection results of the anomaly evaluation. For example, if an anomaly pattern is detected, it notifies the responsible person of that information. This makes it possible to detect anomaly patterns with higher accuracy and take prompt and appropriate action.

[0043] The alert notification unit can include background information of the evaluator (age, gender, region) in the alert notification of an abnormality evaluation, enabling a multifaceted analysis of the cause of the abnormality. The alert notification unit, for example, includes background information of the evaluator in the alert notification of an abnormality evaluation. For example, the evaluation data and attribute data of the evaluator are linked, and the background information is displayed when the alert notification is sent. The alert notification unit also utilizes the background information of the evaluator to analyze the cause of the abnormality from multiple angles. For example, it analyzes the cause of the abnormal evaluation by age group or gender, and notifies the results. The alert notification unit also includes region information in the alert notification of an abnormality evaluation. For example, it analyzes the cause of the abnormal evaluation by region, and notifies the results. This enables a more accurate response by analyzing the cause of the abnormality from multiple angles.

[0044] The alert notification unit can make it possible to receive alert notifications of abnormal evaluations on different devices (smartphones, tablets, PCs). The alert notification unit, for example, makes it possible to receive alert notifications of abnormal evaluations on different devices. For example, an alert notification app compatible with smartphones, tablets, and PCs can be developed to immediately notify users of abnormalities in the evaluation data. The alert notification unit also optimizes the notification method for different devices. For example, it uses push notifications for smartphones and email notifications for PCs. The alert notification unit also provides notification settings customized for each device. For example, it allows users to set the priority and method of notifications for each device. This allows alert notifications to be received on different devices, enabling quick responses.

[0045] The alert notification unit can link the alert notification of an abnormal evaluation with other business data (sales data, marketing data) to provide comprehensive business insights. The alert notification unit, for example, links the alert notification of an abnormal evaluation with sales data. For example, it combines evaluation data and sales data to analyze the impact of the abnormal evaluation on sales and notifies the results. The alert notification unit also links the alert notification of an abnormal evaluation with marketing data. For example, it combines evaluation data with marketing campaign data to evaluate the effectiveness of the campaign and notify the results. The alert notification unit also links multiple business data to provide comprehensive business insights. For example, it combines evaluation data, sales data, and marketing data to provide comprehensive business insights. This makes it possible to provide comprehensive business insights by linking with business data.

[0046] The dialogue analysis unit introduces natural language processing technology into the dialogue analysis function, enabling it to generate more natural responses to user questions. The dialogue analysis unit, for example, introduces natural language processing technology into the dialogue analysis function. For example, it analyzes user questions using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The dialogue analysis unit also generates more natural responses to user questions. For example, the generation AI understands the user's question and generates an appropriate answer. The dialogue analysis unit also regularly updates the learning data of the generation AI to improve the quality of the responses. For example, it retrains the generation AI based on new evaluation data and user feedback. In this way, the introduction of natural language processing technology makes it possible to generate more natural responses to user questions.

[0047] The interactive analysis unit can provide more detailed analysis results by including the evaluator's background information (age, gender, region) in the interactive analysis function. The interactive analysis unit, for example, includes the evaluator's background information in the interactive analysis function. For example, it links the evaluation data with the evaluator's attribute data and provides detailed analysis results in response to the user's questions. The interactive analysis unit also uses the evaluator's background information to perform more detailed analysis. For example, it classifies the evaluation data by age group or gender and provides analysis results for each attribute. The interactive analysis unit also uses evaluation data by region to provide region-specific analysis results. For example, it analyzes evaluation trends by region and provides the results to the user. In this way, by including the evaluator's background information, it becomes possible to provide more detailed analysis results.

[0048] The interactive analysis unit can make the interactive analysis function available on different devices (smartphones, tablets, PCs). The interactive analysis unit makes the interactive analysis function available on different devices. For example, it develops an interactive analysis app compatible with smartphones, tablets, and PCs, and provides the analysis results of evaluation data. The interactive analysis unit also provides the optimal user interface for each device. For example, it provides an interface optimized for touch operation on smartphones, and an interface optimized for mouse operation on PCs. The interactive analysis unit also provides functions customized for each device. For example, it provides a voice input function on smartphones and a keyboard input function on PCs. This allows the function to be used on different devices, improving user convenience.

[0049] The interactive analysis unit can link the interactive analysis function with other business data (sales data, marketing data) to provide comprehensive business insights. The interactive analysis unit, for example, links the interactive analysis function with sales data. For example, it combines evaluation data and sales data to analyze the impact of changes in evaluation on sales and provides the results to the user. The interactive analysis unit also links the interactive analysis function with marketing data. For example, it combines evaluation data with marketing campaign data to evaluate the effectiveness of the campaign and provides the results to the user. The interactive analysis unit also links multiple business data to provide comprehensive business insights. For example, it combines evaluation data, sales data, and marketing data to provide comprehensive business insights. This makes it possible to provide comprehensive business insights by linking with business data.

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

[0051] The evaluation data aggregation unit can also collect the purchase history of the evaluator at the same time as collecting the evaluation data. For example, the evaluator's purchase history is linked to the online review submission form, and that information is stored together with the evaluation data. The evaluation data aggregation unit can also collect the purchase frequency of the evaluator. For example, when collecting survey results, a field for entering the evaluator's purchase frequency is added, and that information is stored together with the evaluation data. The evaluation data aggregation unit can also collect the purchase amount of the evaluator. For example, when collecting social media comments, information on the purchase amount of the evaluator is obtained, and that information is stored together with the evaluation data. This enables multifaceted analysis of the evaluation data.

[0052] The evaluation data aggregating unit can also collect the evaluator's purchasing intentions at the same time as collecting evaluation data. For example, a field for inputting the evaluator's purchasing intentions can be added to an online review submission form, and the information can be saved together with the evaluation data. The evaluation data aggregating unit can also collect the evaluator's purchasing motivations. For example, a field for inputting the evaluator's purchasing motivations can be added when collecting survey results, and the information can be saved together with the evaluation data. The evaluation data aggregating unit can also collect the evaluator's purchasing plans. For example, when collecting social media comments, information on the evaluator's purchasing plans can be obtained, and the information can be saved together with the evaluation data. This enables multifaceted analysis of the evaluation data.

[0053] The evaluation data aggregation unit can also collect the evaluator's purchasing channel (online or offline) at the same time as collecting evaluation data. For example, it can add a field to the online review submission form for entering the evaluator's purchasing channel, and store that information together with the evaluation data. The evaluation data aggregation unit can also collect the evaluator's evaluation for each purchasing channel. For example, it can add a field to enter the evaluator's purchasing channel when collecting survey results, and store that information together with the evaluation data. The evaluation data aggregation unit can also analyze the evaluator's evaluation for each purchasing channel. For example, it can obtain the evaluator's purchasing channel information when collecting social media comments, and store that information together with the evaluation data. This enables multifaceted analysis of the evaluation data.

[0054] The trend analysis unit can also generate a predictive model for future ratings based on the trend analysis results and provide prediction results for different market segments. For example, a machine learning model is trained using past rating data to predict future ratings. The trend analysis unit also provides prediction results for each market segment. For example, rating data is classified by age group or income group, and prediction results are provided for each segment. The trend analysis unit also suggests countermeasures based on the prediction results. For example, based on the prediction results, it suggests measures to prevent a decline in ratings. This makes it possible to take countermeasures in advance by predicting future ratings.

[0055] The trend analysis unit can also display the trend analysis results separately for different regions or market segments to clarify regional trends. For example, it analyzes trends based on the evaluation data for each region and displays the evaluation trends for each region. The trend analysis unit also displays the trend analysis results for each market segment. For example, it classifies the evaluation data by age group or income group and displays the trends for each segment. The trend analysis unit also displays the evaluation data on a map to clarify regional trends. For example, it plots the evaluation data for each region on a map to visually display the evaluation trends for each region. This makes it possible to understand regional trends by clarifying regional trends.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The evaluation data aggregation unit aggregates evaluation data along a time axis. For example, the generation AI collects evaluation data from online reviews, survey results, social media comments, etc., and aggregates it along a time axis. For example, the generation AI receives a prompt including an instruction such as "Please aggregate evaluation data from January 2023 to December 2023," and aggregates the data based on that instruction. Step 2: The trend analysis unit performs trend analysis based on the aggregated evaluation data. For example, the generation AI receives a prompt that includes the instruction, "Analyze the evaluation trend over the past six months," and analyzes the upward or downward trend of the evaluation based on that instruction. The generation AI analyzes the trend using techniques such as moving averages and regression analysis. Step 3: The graph display unit generates and displays a transition graph based on the results of the trend analysis. For example, the generation AI receives a prompt including the instruction "Please display the transition of the evaluation in a graph," and visually displays the transition of the evaluation based on that instruction. The generation AI generates the transition graph in the form of a line graph, bar graph, or the like. Step 4: The alert notification unit detects abnormal ratings from the rating data and issues an alert notification. For example, the generation AI receives a prompt containing the instruction "Detect abnormal ratings and issue an alert," and based on that instruction, detects abnormal ratings and notifies the responsible person. The generation AI detects abnormal ratings using techniques such as statistical outlier detection and rule-based anomaly detection. Step 5: The interactive analysis unit analyzes the evaluation data through dialogue with the user. For example, when a user asks, "What are the recent evaluation trends?", the generation AI analyzes the question and generates an appropriate answer. The generation AI uses natural language processing technology to analyze the user's question and generate an appropriate answer.

[0058] (Example 2) The evaluation monitoring system according to an embodiment of the present invention aggregates customer evaluations of products and services over time, and provides trend analysis, graph display of changes, alert notifications for abnormal evaluations, and interactive analysis functions. This allows the evaluation monitoring system to monitor evaluation changes in real time and respond quickly and appropriately to market trends and consumer satisfaction.

[0059] A rating monitoring system according to an embodiment includes a rating data aggregation unit, a trend analysis unit, a graph display unit, an alert notification unit, and an interactive analysis unit. The rating data aggregation unit aggregates rating data along a time axis. For example, the generation AI collects rating data from online reviews, survey results, social media comments, etc., and aggregates it along a time axis. The generation AI receives a prompt including, for example, an instruction such as "Please aggregate rating data from January 2023 to December 2023," and aggregates the data based on the instruction. The trend analysis unit performs trend analysis based on the aggregated rating data. For example, the generation AI receives a prompt including an instruction such as "Please analyze the rating trends over the past six months," and analyzes upward or downward trends in ratings based on the instruction. The generation AI analyzes trends using techniques such as moving averages and regression analysis. The graph display unit generates and displays a trend graph based on the results of the trend analysis. For example, the generation AI receives a prompt including an instruction such as "Please display the rating trends in a graph," and visually displays the rating trends based on the instruction. The generation AI generates a trend graph in the form of a line graph or bar graph. The alert notification unit detects abnormal ratings from the rating data and issues an alert. For example, the generation AI receives a prompt including the instruction "Detect abnormal ratings and issue an alert." Based on the instruction, the generation AI detects abnormal ratings and notifies the responsible party. The generation AI detects abnormal ratings using techniques such as statistical outlier detection and rule-based anomaly detection. The interactive analysis unit analyzes the rating data through dialogue with the user. For example, in response to a user's question, "What are the recent rating trends?", the generation AI analyzes the question and generates an appropriate answer. The generation AI uses natural language processing technology to analyze the user's question and generate an appropriate answer. This allows the rating monitoring system according to the embodiment to monitor rating changes in real time and respond quickly and appropriately to market trends and consumer satisfaction. For example, if the ratings of a new product suddenly drop, the cause can be quickly identified and improvement measures can be implemented. Furthermore, by understanding the upward trend in ratings, successful measures can be continuously implemented.

[0060] The evaluation data aggregation unit can collect evaluation data from online reviews, survey results, and social media comments. The evaluation data aggregation unit, for example, collects evaluation data from online review sites. For example, it collects data from sites such as Amazon reviews and Google reviews. The evaluation data aggregation unit also collects survey results. For example, it collects data from online surveys and paper-based surveys. The evaluation data aggregation unit also collects social media comments. For example, it collects comments from platforms such as Twitter and Facebook. This allows for more comprehensive evaluation by collecting evaluation data from a variety of sources.

[0061] The evaluation data aggregating unit can simultaneously collect background information (age, gender, region) of the rater when collecting evaluation data. The evaluation data aggregating unit, for example, collects the age of the rater when collecting evaluation data. For example, it adds a field for entering the rater's age to an online review submission form and stores that information together with the evaluation data. The evaluation data aggregating unit also collects the gender of the rater. For example, it adds a field for entering the rater's gender when collecting survey results and stores that information together with the evaluation data. The evaluation data aggregating unit also collects the region of the rater. For example, it obtains the region information of the rater when collecting social media comments and stores that information together with the evaluation data. This enables multifaceted analysis of the evaluation data.

[0062] The evaluation data aggregation unit can use the emotion estimation function to analyze the emotional nuances of the evaluation data and prioritize aggregation of evaluations with strong positive emotions. The evaluation data aggregation unit, for example, uses the emotion estimation function to analyze the emotional nuances of the evaluation data. For example, it uses text analysis technology to extract keywords and phrases that indicate positive emotions from the evaluation comments and classifies the evaluation data based on their scores. The evaluation data aggregation unit also prioritizes aggregation of evaluations with strong positive emotions. For example, it prioritizes storing evaluation data with high positive emotion scores in the database. The evaluation data aggregation unit also filters out evaluations with strong negative emotions. For example, it excludes evaluation data with high negative emotion scores. This allows for a more accurate understanding of customer satisfaction by prioritizing aggregation of positive evaluations.

[0063] The evaluation data aggregation unit collects evaluation data in real time and can instantly reflect the evaluations in the database each time they are posted. The evaluation data aggregation unit, for example, collects evaluation data in real time. For example, by using the API of an online review site or social media, the evaluations are stored in the database as soon as they are posted. The evaluation data aggregation unit also instantly reflects the evaluations in the database each time they are posted. For example, by using real-time data processing technology, the evaluation data is instantly stored in the database. The evaluation data aggregation unit also updates the evaluation data in real time. For example, the evaluation data is updated and immediately reflected in the database. This allows for rapid response by collecting evaluation data in real time and instantly reflecting it.

[0064] The evaluation data aggregation unit can integrate evaluation data from different platforms and perform comprehensive evaluation aggregation. The evaluation data aggregation unit integrates evaluation data from social media, for example. For example, it uses the APIs of Twitter and Facebook to collect customer evaluation comments and store them in a database. The evaluation data aggregation unit also integrates evaluation data from blogs. For example, it uses the RSS feed of a blog to collect evaluation comments and store them in a database. The evaluation data aggregation unit also integrates evaluation data from forums. For example, it collects forum posting data and stores it in a database. In this way, by integrating evaluation data from different platforms, more comprehensive evaluations are possible.

[0065] The evaluation data aggregating unit can monitor the emotional trends of the evaluation data in real time using the emotion estimation function and aggregate the data according to changes in emotion. The evaluation data aggregating unit, for example, monitors the emotional trends of the evaluation data in real time using the emotion estimation function. For example, it uses text analysis technology to calculate the emotion scores of the evaluation comments in real time and reflects the trends in the database. The evaluation data aggregating unit also aggregates the data according to changes in emotion. For example, if positive emotions are increasing, it prioritizes aggregating that evaluation data. Also, if negative emotions are increasing, it filters that evaluation data. This makes it possible to aggregate the evaluation data according to changes in emotion.

[0066] The trend analysis unit can perform trend prediction with higher accuracy by taking into account the seasonality of the evaluation data and the influence of events. The trend analysis unit, for example, takes into account the seasonality of the evaluation data. For example, it analyzes seasonal evaluation trends based on past data and predicts seasonal trends. The trend analysis unit also takes into account the influence of events. For example, it reflects the influence of promotional events and social events in the evaluation data. The trend analysis unit also performs trend prediction with higher accuracy by taking into account the seasonality of the evaluation data and the influence of events. For example, it uses techniques such as moving average and regression analysis to perform trend prediction with higher accuracy by taking into account the influence of seasonality and events.

[0067] The trend analysis unit can generate a prediction model for future ratings based on the trend analysis results and provide the prediction results. The trend analysis unit, for example, generates a prediction model for future ratings based on the trend analysis results. For example, it trains a machine learning model using past rating data to predict future ratings. The trend analysis unit also provides the prediction results. For example, it predicts future ratings using the generated prediction model and provides the results to the user. The trend analysis unit also suggests countermeasures based on the prediction results. For example, it suggests measures to prevent a decline in ratings based on the prediction results. This makes it possible to take countermeasures in advance by predicting future ratings.

[0068] The trend analysis unit can use the emotion estimation function to analyze the emotional trend of the evaluation data and evaluate the impact of changes in emotion on the trend. The trend analysis unit, for example, uses the emotion estimation function to analyze the emotional trend of the evaluation data. For example, it uses text analysis technology to calculate emotion scores of evaluation comments and analyze the trend. The trend analysis unit also evaluates the impact of changes in emotion on the trend. For example, if positive emotions are increasing, the impact is reflected in the trend. Also, if negative emotions are increasing, the impact is reflected in the trend. This enables more accurate trend analysis by evaluating the impact of changes in emotion on the trend.

[0069] The trend analysis unit displays the trend analysis results separately for different regions or market segments, thereby clarifying the trends for each region. The trend analysis unit, for example, displays the trend analysis results separately for different regions. For example, it analyzes trends based on the evaluation data for each region and displays the evaluation trends for each region. The trend analysis unit also displays the trend analysis results for each market segment. For example, it classifies the evaluation data by age group or income group and displays the trends for each segment. The trend analysis unit also displays the evaluation data on a map to clarify the trends for each region. For example, it plots the evaluation data for each region on a map to visually display the evaluation trends for each region. This makes it possible to understand trends specific to each region by clarifying the trends for each region.

[0070] The trend analysis unit can integrate the trend analysis results with other business data (sales data, marketing data) to provide comprehensive business insights. The trend analysis unit, for example, integrates the trend analysis results with sales data. For example, it combines evaluation data and sales data to analyze the impact of changes in evaluation on sales. The trend analysis unit also integrates the trend analysis results with marketing data. For example, it combines evaluation data with marketing campaign data to evaluate the effectiveness of the campaign. The trend analysis unit also integrates multiple business data to provide comprehensive business insights. For example, it combines evaluation data, sales data, and marketing data to provide comprehensive business insights. This makes it possible to provide comprehensive business insights by integrating with business data.

[0071] The trend analysis unit can use the emotion estimation function to monitor the emotional trends of the evaluation data in real time and perform trend analysis according to changes in emotion. The trend analysis unit, for example, uses the emotion estimation function to monitor the emotional trends of the evaluation data in real time. For example, it uses text analysis technology to calculate the emotion scores of the evaluation comments in real time and reflects the trends in the database. The trend analysis unit also performs trend analysis according to changes in emotion. For example, if positive emotions are increasing, the influence of this is reflected in the trend. Also, if negative emotions are increasing, the influence of this is reflected in the trend. In this way, by performing trend analysis according to changes in emotion, more accurate trend prediction is possible.

[0072] The graph display unit can add interactive elements to the transition graph, allowing the user to select a specific period or evaluation item to view details. The graph display unit, for example, adds interactive elements to the transition graph. For example, a user can drag to select a specific period on the graph and display detailed data for that period. The graph display unit also allows the user to select a specific evaluation item to view details. For example, a filtering function can be added for each evaluation item to display detailed data related to a specific item. The graph display unit also uses interactive elements to make it easier for the user to operate the graph. For example, clickable data points or tooltips can be added to display detailed information. This allows the user to select a specific period or evaluation item to view details, enabling more detailed analysis.

[0073] The graph display unit can display the attributes of the evaluators (age, gender, region) on a transition graph, enabling the transition of evaluations to be analyzed from multiple angles. The graph display unit, for example, displays the attributes of the evaluators on the transition graph. For example, the evaluation data and the attribute data of the evaluators are linked, and the attribute information is displayed on the graph. The graph display unit also displays the transition of evaluations for each attribute of the evaluators. For example, the evaluation data is classified by age group or gender, and the transition of evaluations for each attribute is displayed. The graph display unit also uses the attributes of the evaluators to analyze the transition of evaluations from multiple angles. For example, the evaluation data for each region is plotted on a map, and the evaluation trends for each region are visually displayed. In this way, by displaying the attributes of the evaluators, the transition of evaluations can be analyzed from multiple angles.

[0074] The graph display unit can use the emotion estimation function to display the emotional transition of the evaluation data on a graph, allowing the changes in emotion to be visually confirmed. The graph display unit, for example, uses the emotion estimation function to display the emotional transition of the evaluation data on a graph. For example, it uses text analysis technology to calculate emotion scores of evaluation comments and displays the transition on a graph. The graph display unit also allows the changes in emotion to be visually confirmed. For example, it displays the temporal change in emotion score as a line graph or a bar graph. The graph display unit also uses colors and animations to emphasize the changes in emotion. For example, it displays positive emotions in green and negative emotions in red to visually emphasize the changes in emotion. This makes it possible to visually confirm the changes in emotion and more intuitively grasp the changes in evaluation.

[0075] The graph display unit can employ a responsive design so that the transition graph can be optimally displayed on different devices (smartphones, tablets, and PCs). The graph display unit employs a responsive design so that the transition graph can be optimally displayed on different devices. For example, the graph layout can be automatically adjusted according to the screen size of the smartphone, tablet, or PC. The graph display unit also supports touch and mouse operations to improve operability on different devices. For example, the graph can be operated by touch on a smartphone or tablet, and by mouse on a PC. The graph display unit also provides the optimal display format for each device. For example, a portrait display format can be used on a smartphone, and a landscape display format can be used on a PC. This improves user convenience by providing optimal display on different devices.

[0076] The graph display unit can link the transition graph with other business data (sales data, marketing data) to provide comprehensive business insights. The graph display unit, for example, links the transition graph with sales data. For example, it combines evaluation data and sales data to analyze the impact of changes in evaluation on sales and displays the results in a graph. The graph display unit also links the transition graph with marketing data. For example, it combines evaluation data and marketing campaign data to evaluate the effectiveness of the campaign and displays the results in a graph. The graph display unit also links multiple business data to provide comprehensive business insights. For example, it combines evaluation data, sales data, and marketing data to provide comprehensive business insights. This makes it possible to provide comprehensive business insights by linking with business data.

[0077] The graph display unit can monitor the emotional transition of the evaluation data in real time using the emotion estimation function and display a graph corresponding to the change in emotion. The graph display unit, for example, monitors the emotional transition of the evaluation data in real time using the emotion estimation function. For example, it uses text analysis technology to calculate the emotion score of the evaluation comment in real time and displays the change on a graph. The graph display unit also displays a graph corresponding to the change in emotion. For example, if positive emotion is increasing, the change is displayed in green, and if negative emotion is increasing, the change is displayed in red. The graph display unit also uses animation to emphasize the change in emotion. For example, it displays the change in emotion score using animation to visually emphasize the change in emotion. In this way, by displaying a graph corresponding to the change in emotion, it becomes possible to more accurately grasp the change in evaluation.

[0078] The alert notification unit improves the anomaly evaluation detection algorithm and can detect anomaly patterns in the evaluation data with higher accuracy. The alert notification unit, for example, improves the anomaly evaluation detection algorithm. For example, it uses machine learning technology to automatically learn anomaly patterns and improve detection accuracy. The alert notification unit also detects anomaly patterns in the evaluation data with higher accuracy. For example, it improves statistical outliers or rule-based anomaly detection algorithms to improve the accuracy of detecting anomaly patterns. The alert notification unit also issues an alert based on the detection results of the anomaly evaluation. For example, if an anomaly pattern is detected, it notifies the responsible person of that information. This makes it possible to detect anomaly patterns with higher accuracy and take prompt and appropriate action.

[0079] The alert notification unit can include background information of the evaluator (age, gender, region) in the alert notification of an abnormality evaluation, enabling a multifaceted analysis of the cause of the abnormality. The alert notification unit, for example, includes background information of the evaluator in the alert notification of an abnormality evaluation. For example, the evaluation data and attribute data of the evaluator are linked, and the background information is displayed when the alert notification is sent. The alert notification unit also utilizes the background information of the evaluator to analyze the cause of the abnormality from multiple angles. For example, it analyzes the cause of the abnormal evaluation by age group or gender, and notifies the results. The alert notification unit also includes region information in the alert notification of an abnormality evaluation. For example, it analyzes the cause of the abnormal evaluation by region, and notifies the results. This enables a more accurate response by analyzing the cause of the abnormality from multiple angles.

[0080] The alert notification unit can use the emotion estimation function to analyze the emotional nuances of the abnormal evaluations and prioritize alerts for emotionally negative evaluations. The alert notification unit, for example, uses the emotion estimation function to analyze the emotional nuances of the abnormal evaluations. For example, it uses text analysis technology to calculate emotion scores for evaluation comments and prioritizes alerts for evaluations with strong negative emotions. The alert notification unit also prioritizes alerts for emotionally negative evaluations. For example, it prioritizes notifying the responsible party of evaluation data with high negative emotion scores. The alert notification unit also filters out evaluations with strong positive emotions. For example, it excludes evaluation data with high positive emotion scores. This prioritizes alerts for emotionally negative evaluations, enabling a rapid response.

[0081] The alert notification unit can make it possible to receive alert notifications of abnormal evaluations on different devices (smartphones, tablets, PCs). The alert notification unit, for example, makes it possible to receive alert notifications of abnormal evaluations on different devices. For example, an alert notification app compatible with smartphones, tablets, and PCs can be developed to immediately notify users of abnormalities in the evaluation data. The alert notification unit also optimizes the notification method for different devices. For example, it uses push notifications for smartphones and email notifications for PCs. The alert notification unit also provides notification settings customized for each device. For example, it allows users to set the priority and method of notifications for each device. This allows alert notifications to be received on different devices, enabling quick responses.

[0082] The alert notification unit can link the alert notification of an abnormal evaluation with other business data (sales data, marketing data) to provide comprehensive business insights. The alert notification unit, for example, links the alert notification of an abnormal evaluation with sales data. For example, it combines evaluation data and sales data to analyze the impact of the abnormal evaluation on sales and notifies the results. The alert notification unit also links the alert notification of an abnormal evaluation with marketing data. For example, it combines evaluation data with marketing campaign data to evaluate the effectiveness of the campaign and notify the results. The alert notification unit also links multiple business data to provide comprehensive business insights. For example, it combines evaluation data, sales data, and marketing data to provide comprehensive business insights. This makes it possible to provide comprehensive business insights by linking with business data.

[0083] The alert notification unit can monitor the emotional nuances of the abnormal evaluations in real time using the emotion estimation function and issue alert notifications in response to changes in emotion. The alert notification unit, for example, uses the emotion estimation function to monitor the emotional nuances of the abnormal evaluations in real time. For example, it uses text analysis technology to calculate the emotion score of the evaluation comments in real time and monitors changes in the emotion score. The alert notification unit also issues alert notifications in response to changes in emotion. For example, if there is a sudden increase in negative emotions, the alert notification unit immediately notifies the responsible person of this information. The alert notification unit also customizes the content of the notification to emphasize changes in emotion. For example, it displays changes in the emotion score using a graph or color to visually emphasize changes in emotion. This allows alert notifications in response to changes in emotion, enabling quick and appropriate responses.

[0084] The dialogue analysis unit introduces natural language processing technology into the dialogue analysis function, enabling it to generate more natural responses to user questions. The dialogue analysis unit, for example, introduces natural language processing technology into the dialogue analysis function. For example, it analyzes user questions using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The dialogue analysis unit also generates more natural responses to user questions. For example, the generation AI understands the user's question and generates an appropriate answer. The dialogue analysis unit also regularly updates the learning data of the generation AI to improve the quality of the responses. For example, it retrains the generation AI based on new evaluation data and user feedback. In this way, the introduction of natural language processing technology makes it possible to generate more natural responses to user questions.

[0085] The interactive analysis unit can provide more detailed analysis results by including the evaluator's background information (age, gender, region) in the interactive analysis function. The interactive analysis unit, for example, includes the evaluator's background information in the interactive analysis function. For example, it links the evaluation data with the evaluator's attribute data and provides detailed analysis results in response to the user's questions. The interactive analysis unit also uses the evaluator's background information to perform more detailed analysis. For example, it classifies the evaluation data by age group or gender and provides analysis results for each attribute. The interactive analysis unit also uses evaluation data by region to provide region-specific analysis results. For example, it analyzes evaluation trends by region and provides the results to the user. In this way, by including the evaluator's background information, it becomes possible to provide more detailed analysis results.

[0086] The dialogue analysis unit can analyze the emotional nuances of a user's question using the emotion estimation function and generate an appropriate response according to the emotion. The dialogue analysis unit, for example, uses the emotion estimation function to analyze the emotional nuances of a user's question. For example, it uses text analysis technology to calculate an emotion score for the user's question and generates a response according to that emotion. The dialogue analysis unit also generates an appropriate response according to the emotion. For example, it generates an empathetic response for a question with a strong negative emotion, and generates an encouraging response for a question with a strong positive emotion. The dialogue analysis unit also monitors changes in emotion and adjusts the content of the response. For example, if the user's emotion changes, it updates the content of the response according to the change. In this way, by analyzing the emotional nuances of a user's question, it is possible to generate an appropriate response according to the emotion.

[0087] The interactive analysis unit can make the interactive analysis function available on different devices (smartphones, tablets, PCs). The interactive analysis unit makes the interactive analysis function available on different devices. For example, it develops an interactive analysis app compatible with smartphones, tablets, and PCs, and provides the analysis results of evaluation data. The interactive analysis unit also provides the optimal user interface for each device. For example, it provides an interface optimized for touch operation on smartphones, and an interface optimized for mouse operation on PCs. The interactive analysis unit also provides functions customized for each device. For example, it provides a voice input function on smartphones and a keyboard input function on PCs. This allows the function to be used on different devices, improving user convenience.

[0088] The interactive analysis unit can link the interactive analysis function with other business data (sales data, marketing data) to provide comprehensive business insights. The interactive analysis unit, for example, links the interactive analysis function with sales data. For example, it combines evaluation data and sales data to analyze the impact of changes in evaluation on sales and provides the results to the user. The interactive analysis unit also links the interactive analysis function with marketing data. For example, it combines evaluation data with marketing campaign data to evaluate the effectiveness of the campaign and provides the results to the user. The interactive analysis unit also links multiple business data to provide comprehensive business insights. For example, it combines evaluation data, sales data, and marketing data to provide comprehensive business insights. This makes it possible to provide comprehensive business insights by linking with business data.

[0089] The dialogue analysis unit can use the emotion estimation function to monitor the emotional nuances of a user's question in real time and generate an appropriate response based on the emotion. The dialogue analysis unit, for example, uses the emotion estimation function to monitor the emotional nuances of a user's question in real time. For example, it uses text analysis technology to calculate an emotion score for the user's question in real time and generates a response based on that emotion. The dialogue analysis unit also generates an appropriate response based on the emotion. For example, it generates an empathetic response for a question with a strong negative emotion, and generates an encouraging response for a question with a strong positive emotion. The dialogue analysis unit also monitors changes in emotion and adjusts the content of the response. For example, if the user's emotion changes, it updates the content of the response in accordance with the change. In this way, by monitoring the emotional nuances of a user's question in real time, it is possible to generate an appropriate response based on the emotion.

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

[0091] The evaluation data aggregation unit can also collect the purchase history of the evaluator at the same time as collecting the evaluation data. For example, the evaluator's purchase history is linked to the online review submission form, and that information is stored together with the evaluation data. The evaluation data aggregation unit can also collect the purchase frequency of the evaluator. For example, when collecting survey results, a field for entering the evaluator's purchase frequency is added, and that information is stored together with the evaluation data. The evaluation data aggregation unit can also collect the purchase amount of the evaluator. For example, when collecting social media comments, information on the purchase amount of the evaluator is obtained, and that information is stored together with the evaluation data. This enables multifaceted analysis of the evaluation data.

[0092] The evaluation data aggregation unit can also use an emotion estimation function to analyze the emotional nuances of the evaluation data and prioritize aggregation of evaluations with strong negative emotions. For example, it can use text analysis technology to extract keywords and phrases that indicate negative emotions from the evaluation comments and classify the evaluation data based on their scores. The evaluation data aggregation unit also prioritizes aggregation of evaluations with strong negative emotions. For example, it can prioritize evaluation data with high negative emotion scores and store them in the database. The evaluation data aggregation unit also filters out evaluations with strong positive emotions. For example, it can exclude evaluation data with high positive emotion scores. This allows for a more accurate understanding of problems by prioritizing aggregation of negative evaluations.

[0093] The evaluation data aggregating unit can also collect the evaluator's purchasing intentions at the same time as collecting evaluation data. For example, a field for inputting the evaluator's purchasing intentions can be added to an online review submission form, and the information can be saved together with the evaluation data. The evaluation data aggregating unit can also collect the evaluator's purchasing motivations. For example, a field for inputting the evaluator's purchasing motivations can be added when collecting survey results, and the information can be saved together with the evaluation data. The evaluation data aggregating unit can also collect the evaluator's purchasing plans. For example, when collecting social media comments, information on the evaluator's purchasing plans can be obtained, and the information can be saved together with the evaluation data. This enables multifaceted analysis of the evaluation data.

[0094] The evaluation data aggregation unit can also use an emotion estimation function to analyze the emotional nuances of the evaluation data and aggregate data according to changes in emotion. For example, it can use text analysis technology to calculate the emotion score of evaluation comments in real time and reflect those changes in the database. The evaluation data aggregation unit also aggregates data according to changes in emotion. For example, if positive emotion is increasing, that evaluation data is aggregated preferentially. Also, if negative emotion is increasing, that evaluation data is filtered. This makes it possible to aggregate evaluation data according to changes in emotion.

[0095] The evaluation data aggregation unit can also collect the evaluator's purchasing channel (online or offline) at the same time as collecting evaluation data. For example, it can add a field to the online review submission form for entering the evaluator's purchasing channel, and store that information together with the evaluation data. The evaluation data aggregation unit can also collect the evaluator's evaluation for each purchasing channel. For example, it can add a field to enter the evaluator's purchasing channel when collecting survey results, and store that information together with the evaluation data. The evaluation data aggregation unit can also analyze the evaluator's evaluation for each purchasing channel. For example, it can obtain the evaluator's purchasing channel information when collecting social media comments, and store that information together with the evaluation data. This enables multifaceted analysis of the evaluation data.

[0096] The trend analysis unit can also use an emotion estimation function to evaluate the impact of changes in emotion on trends, taking into account the seasonality of the evaluation data and the impact of events. For example, it uses text analysis technology to calculate emotion scores for evaluation comments and analyze their trends. The trend analysis unit also evaluates the impact of changes in emotion on trends. For example, if positive emotion is increasing, that impact is reflected in the trend. Also, if negative emotion is increasing, that impact is reflected in the trend. This enables more accurate trend analysis by evaluating the impact of changes in emotion on trends.

[0097] The trend analysis unit can also generate a predictive model for future ratings based on the trend analysis results and provide prediction results for different market segments. For example, a machine learning model is trained using past rating data to predict future ratings. The trend analysis unit also provides prediction results for each market segment. For example, rating data is classified by age group or income group, and prediction results are provided for each segment. The trend analysis unit also suggests countermeasures based on the prediction results. For example, based on the prediction results, it suggests measures to prevent a decline in ratings. This makes it possible to take countermeasures in advance by predicting future ratings.

[0098] The trend analysis unit can also use the emotion estimation function to analyze the emotional trends of the evaluation data and evaluate the impact of changes in emotion on the trend. For example, it uses text analysis technology to calculate emotion scores for evaluation comments and analyze their trends. The trend analysis unit also evaluates the impact of changes in emotion on the trend. For example, if positive emotions are increasing, the impact is reflected in the trend. Also, if negative emotions are increasing, the impact is reflected in the trend. This enables more accurate trend analysis by evaluating the impact of changes in emotion on the trend.

[0099] The trend analysis unit can also display the trend analysis results separately for different regions or market segments to clarify regional trends. For example, it analyzes trends based on the evaluation data for each region and displays the evaluation trends for each region. The trend analysis unit also displays the trend analysis results for each market segment. For example, it classifies the evaluation data by age group or income group and displays the trends for each segment. The trend analysis unit also displays the evaluation data on a map to clarify regional trends. For example, it plots the evaluation data for each region on a map to visually display the evaluation trends for each region. This makes it possible to understand regional trends by clarifying regional trends.

[0100] The trend analysis unit can also use the emotion estimation function to monitor the emotional trends of the evaluation data in real time and perform trend analysis in response to changes in emotion. For example, it can use text analysis technology to calculate the emotion scores of evaluation comments in real time and reflect the trends in the database. The trend analysis unit also performs trend analysis in response to changes in emotion. For example, if positive emotion is increasing, its influence is reflected in the trend. Also, if negative emotion is increasing, its influence is reflected in the trend. In this way, trend analysis in response to changes in emotion enables more accurate trend prediction.

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

[0102] Step 1: The evaluation data aggregation unit aggregates evaluation data along a time axis. For example, the generation AI collects evaluation data from online reviews, survey results, social media comments, etc., and aggregates it along a time axis. For example, the generation AI receives a prompt including an instruction such as "Please aggregate evaluation data from January 2023 to December 2023," and aggregates the data based on that instruction. Step 2: The trend analysis unit performs trend analysis based on the aggregated evaluation data. For example, the generation AI receives a prompt that includes the instruction, "Analyze the evaluation trend over the past six months," and analyzes the upward or downward trend of the evaluation based on that instruction. The generation AI analyzes the trend using techniques such as moving averages and regression analysis. Step 3: The graph display unit generates and displays a transition graph based on the results of the trend analysis. For example, the generation AI receives a prompt including the instruction "Please display the transition of the evaluation in a graph," and visually displays the transition of the evaluation based on that instruction. The generation AI generates the transition graph in the form of a line graph, bar graph, or the like. Step 4: The alert notification unit detects abnormal ratings from the rating data and issues an alert notification. For example, the generation AI receives a prompt containing the instruction "Detect abnormal ratings and issue an alert," and based on that instruction, detects abnormal ratings and notifies the responsible person. The generation AI detects abnormal ratings using techniques such as statistical outlier detection and rule-based anomaly detection. Step 5: The interactive analysis unit analyzes the evaluation data through dialogue with the user. For example, when a user asks, "What are the recent evaluation trends?", the generation AI analyzes the question and generates an appropriate answer. The generation AI uses natural language processing technology to analyze the user's question and generate an appropriate answer.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

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

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

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. 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.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

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

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0131] 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.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

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

[0139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

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

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

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

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0147] 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.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0155] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0160] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0161] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0162] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0163] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0164] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0165] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

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

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an evaluation data aggregating unit that aggregates evaluation data along a time axis; a trend analysis unit that performs trend analysis based on the evaluation data aggregated by the evaluation data aggregation unit; a graph display unit that generates and displays a transition graph based on the results obtained by the trend analysis unit; an alert notification unit that detects an abnormal evaluation from the evaluation data and issues an alert notification; An interactive analysis unit that analyzes the evaluation data through an interaction with the user. A system characterized by:

2. The evaluation data aggregation unit The emotional nuances of the evaluation data are analyzed using an emotion estimation function, and evaluations with strong positive emotions are aggregated preferentially.

2. The system of claim 1.

3. The evaluation data aggregation unit Using emotion estimation functionality, the emotional trends of the evaluation data are monitored in real time, and aggregation is performed according to changes in emotion.

2. The system of claim 1.

4. The trend analysis unit An emotion estimation function is used to analyze the emotional trends of the evaluation data and evaluate the impact of changes in emotion on the trends.

2. The system of claim 1.

5. The graph display unit The emotion estimation function is used to display the emotional transition of the evaluation data in a graph, allowing the changes in emotions to be visually confirmed.

2. The system of claim 1.

6. The alert notification unit The emotional nuances of abnormal evaluations are analyzed using an emotion estimation function, and the alert notification is sent with priority to the emotionally negative evaluations.

2. The system of claim 1.

7. The interactive analysis unit Using emotion estimation functionality, the emotional nuances of the user's question are analyzed and an appropriate response is generated according to the emotion.

2. The system of claim 1.

8. The interactive analysis unit Emotion estimation functionality is used to monitor the emotional nuances of the user's questions in real time and generate appropriate responses based on the emotions.

2. The system of claim 1.

Images