system

Abstract

The system according to this embodiment aims to effectively analyze customer evaluation data along a time axis and to quickly detect anomaly evaluations. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a display unit, a notification unit, and a dialogue unit. The collection unit aggregates customer evaluation data for products and services along a time axis. The analysis unit performs trend analysis based on the evaluation data aggregated by the collection unit. The display unit displays a graph showing the changes in the evaluation data analyzed by the analysis unit. The notification unit provides an alert notification when an abnormal evaluation is detected by the analysis unit. The dialogue unit provides insights in a dialogue format based on the results of the analysis unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to effectively analyze customer evaluation data along the time axis and quickly detect abnormal evaluations.

[0005] The system according to the embodiment aims to effectively analyze customer evaluation data along the time axis and quickly detect abnormal evaluations.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, an analysis unit, a display unit, a notification unit, and a dialogue unit. The data collection unit aggregates customer evaluation data for products and services along a time axis. The analysis unit performs trend analysis based on the evaluation data aggregated by the data collection unit. The display unit displays a graph showing the changes in the evaluation data analyzed by the analysis unit. The notification unit provides an alert notification when an abnormal evaluation is detected by the analysis unit. The dialogue unit provides insights in a dialogue format based on the results of the analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can effectively analyze customer evaluation data along a time axis and quickly detect anomalies in evaluations. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The review analysis system according to an embodiment of the present invention is a powerful review analysis tool for business owners and marketers. This review analysis system aggregates customer evaluations of products and services over time and provides trend analysis, display of change graphs, alert notifications for anomaly evaluations, and interactive analysis functions. For example, the review analysis system aggregates customer evaluations of products and services over time. In this process, it collects detailed data such as what kind of evaluations customers made and when those evaluations were made. For example, it collects data on customer evaluations and reviews of products on an e-commerce site. This allows customer evaluation data to be aggregated over time. Next, the review analysis system performs trend analysis based on the aggregated evaluation data. The AI ​​analyzes the collected evaluation data and grasps the evaluation trends. For example, it can analyze how evaluations of a particular product change over time. This allows for grasping evaluation trends and taking appropriate action. Furthermore, the review analysis system displays a graph of the changes in evaluation data. The AI ​​visualizes the evaluation data and displays the changes in evaluations as a graph. For example, it can display a graph showing how evaluations of a particular product change over time. This allows for a quick grasp of the changes in evaluations. Furthermore, the review analysis system provides alert notifications when anomaly ratings are detected. The AI ​​analyzes the rating data and issues alerts in real time if anomalies are detected. For example, it can issue an alert if there is a sudden increase in low ratings for a particular product. This allows for a quick response to anomaly ratings. Finally, the review analysis system provides interactive analysis capabilities. The AI ​​analyzes rating data in a conversational format and provides insights to marketers. For example, it can analyze the reasons why ratings for a particular product are declining and explain those reasons to marketers. This allows marketers to take appropriate action based on the rating data. This system enables business owners and marketers to monitor changes in ratings in real time and respond quickly and appropriately to market trends and consumer satisfaction.For example, it's possible to identify trends based on evaluation data and formulate appropriate marketing strategies. Furthermore, rapid response to anomaly reviews can improve consumer satisfaction. Additionally, by utilizing interactive analytical functions, insights based on evaluation data can be gained and used to improve the business. In this way, review analysis systems can efficiently aggregate, analyze, display, notify, and provide insights in an interactive format based on customer evaluation data.

[0029] The review analysis system according to the embodiment comprises a collection unit, an analysis unit, a display unit, a notification unit, and an interaction unit. The collection unit aggregates customer evaluation data for products and services along a time axis. The collection unit collects, for example, data on evaluations and reviews made by customers on e-commerce sites. The collection unit can collect, for example, data on evaluations and reviews made by customers on products and aggregate it along a time axis. The collection unit can collect, for example, data on evaluations and reviews made by customers on products and aggregate it in aggregation units such as daily, weekly, and monthly. The analysis unit performs trend analysis based on the evaluation data aggregated by the collection unit. The analysis unit can, for example, analyze the collected evaluation data and grasp the evaluation trend. The analysis unit can, for example, analyze the collected evaluation data and grasp how evaluations for a particular product change over time. The analysis unit can, for example, analyze the collected evaluation data and grasp the trend of increase or decrease in evaluations and seasonal fluctuations. The display unit displays a graph of the changes in evaluation data analyzed by the analysis unit. The display unit visualizes evaluation data and displays changes in evaluations as graphs. The display unit can visualize evaluation data and display it in formats such as line graphs, bar graphs, and heatmaps. The display unit visualizes evaluation data, allowing users to grasp changes in evaluations at a glance. The notification unit provides alert notifications when the analysis unit detects abnormal evaluations. The notification unit analyzes evaluation data and sends real-time alerts when abnormal evaluations are detected. The notification unit can analyze evaluation data and send alerts when there is a sudden increase in low evaluations for a particular product. The notification unit can analyze evaluation data and send alerts via email, SMS, app notifications, etc., when abnormal evaluations are detected. The dialogue unit provides insights in a dialogue format based on the results of the analysis unit. The dialogue unit analyzes evaluation data in a dialogue format and provides insights to marketers. The dialogue unit can analyze evaluation data in a dialogue format, analyze the reasons why evaluations for a particular product are declining, and explain those reasons to marketers.The dialogue component can, for example, analyze evaluation data in a conversational format and provide insights using chatbots or voice assistants. This enables the review analysis system to efficiently aggregate, analyze, display, notify, and provide insights in a conversational format based on customer evaluation data.

[0030] The data collection unit aggregates customer evaluation data for products and services along a timeline. Specifically, it collects data on customer ratings and reviews of products on e-commerce sites. For example, the data collection unit can collect customer ratings and reviews and aggregate them in daily, weekly, or monthly increments. This allows the data collection unit to efficiently collect customer evaluation data and organize it along a timeline. Furthermore, the data collection unit can collect data from multiple e-commerce sites and social media platforms. For example, the data collection unit can use APIs to retrieve data from each platform and store it in a unified format. This allows for centralized management of data from different platforms and provides comprehensive evaluation data. In addition, the data collection unit can use natural language processing technology to extract evaluation elements from text data. For example, it can automatically classify positive and negative ratings from customer reviews and understand evaluation trends. This allows the data collection unit to extract useful information not only from numerical data but also from text data, improving the quality of evaluation data. Furthermore, the data collection unit can adjust the frequency and accuracy of data collection, enabling flexible responses to specific situations and conditions. For example, if there is a sudden surge in reviews for a particular product or service, the collection frequency can be increased to collect data in real time. This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0031] The analysis department performs trend analysis based on evaluation data aggregated by the collection department. Specifically, it analyzes the collected evaluation data to understand evaluation trends. For example, it can understand how evaluations for a particular product change over time. The analysis department can use AI to analyze the data and understand trends in increases and decreases in evaluations, as well as seasonal fluctuations. The AI ​​uses machine learning algorithms to learn patterns from past data and predict future evaluation fluctuations. For example, if evaluations tend to increase in relation to a particular season or event, it can predict future evaluations based on that pattern. Furthermore, the analysis department can use anomaly detection algorithms to detect unusual patterns and abnormal data. For example, if there is a sudden increase in low evaluations for a particular product, it can identify the cause and take countermeasures early. In addition, the analysis department can segment the evaluation data to understand evaluation trends for different customer segments and regions. For example, it can classify evaluation data based on attributes such as age, gender, and region, and analyze evaluation trends for each segment. This allows the analysis department to obtain more detailed insights, which can be used to formulate marketing strategies. Furthermore, the analysis unit visualizes the evaluation data and displays it as graphs and charts, allowing for an intuitive understanding of changes in the evaluation. This enables the analysis unit to quickly and accurately analyze the collected data and grasp the surrounding risk situation in real time.

[0032] The display unit shows a graph of the changes in evaluation data analyzed by the analysis unit. Specifically, it visualizes the evaluation data and displays changes in evaluation as a graph. The display unit can visualize the evaluation data and display it in formats such as line graphs, bar graphs, and heatmaps. This allows users to grasp fluctuations in evaluation data at a glance. Furthermore, the display unit provides interactive graphs, allowing users to focus on specific periods or products to view detailed data. For example, if a user selects a specific period, the evaluation data for that period will be displayed in detail. The display unit also provides a filtering function for evaluation data, allowing users to narrow down the data based on specific conditions. For example, it can display only reviews containing a specific evaluation score range or specific keywords. This allows users to quickly obtain the necessary information and efficiently analyze evaluation data. In addition, the display unit can update fluctuations in evaluation data in real time, always providing the latest information. For example, when new evaluation data is collected, the graph is automatically updated to reflect the latest evaluation status. This allows the display unit to always provide users with the latest information and support quick decision-making.

[0033] The notification unit issues alerts when the analysis unit detects anomaly evaluations. Specifically, it analyzes evaluation data and issues real-time alerts when anomaly evaluations are detected. For example, it can issue an alert if there is a sudden increase in low evaluations for a particular product. The notification unit can send alerts via email, SMS, app notifications, etc. This allows stakeholders to respond quickly to anomaly evaluations. Furthermore, the notification unit can set alert priorities and select different notification methods depending on the importance. For example, if a serious anomaly evaluation is detected, it will immediately notify via SMS or phone, while for minor anomalies, it will notify via email or app notifications. The notification unit can also save alert history and analyze past anomaly evaluation trends. This allows for the prediction of future anomalies and the planning of countermeasures based on past alert data. In addition, the notification unit can collect user feedback and continuously improve the accuracy and effectiveness of alerts. For example, it can review the content of alerts and notification methods based on feedback from users who have received alerts. This allows the notification unit to provide alerts to users quickly and reliably, supporting rapid responses to anomaly evaluations.

[0034] The dialogue unit provides insights in a conversational format based on the results from the analysis unit. Specifically, it analyzes evaluation data in a conversational format and provides insights to marketers. For example, it can analyze the reasons why the evaluation of a particular product is declining and explain those reasons to marketers. The dialogue unit can provide insights using chatbots and voice assistants. This allows marketers to quickly develop concrete countermeasures in response to fluctuations in evaluation data. Furthermore, the dialogue unit can answer user questions in real time and provide advice based on evaluation data. For example, if a marketer wants to know the evaluation trend for a particular product, the dialogue unit will explain the trend based on the latest evaluation data and propose future countermeasures. The dialogue unit can also utilize historical data and statistical information to perform long-term risk assessments and trend analysis. For example, based on historical evaluation data, it can predict evaluation fluctuations related to specific seasons or events and propose future countermeasures. This allows the dialogue unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, improving the reliability and security of the entire system. Furthermore, the dialogue unit can collect user feedback and continuously improve the accuracy and effectiveness of the dialogue content. For example, the dialogue algorithm and response content can be reviewed based on feedback obtained through the dialogue. This allows the dialogue unit to provide users with quick and accurate insights and support the analysis of evaluation data and the development of countermeasures.

[0035] The data collection unit can collect data on customer ratings and reviews of products on e-commerce sites. For example, the data collection unit can collect data on customer ratings and reviews of products on e-commerce sites and aggregate it along a timeline. For example, the data collection unit can collect data on customer ratings and reviews of products on e-commerce sites and aggregate it in units such as daily, weekly, or monthly. This allows for detailed customer evaluations to be obtained by collecting rating data from e-commerce sites. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input rating data obtained from e-commerce sites into a generating AI and have the generating AI perform the aggregation of the rating data.

[0036] The analysis unit can analyze the collected evaluation data and grasp the trends in evaluations. For example, the analysis unit can analyze the collected evaluation data and grasp the trends in evaluations. For example, the analysis unit can analyze the collected evaluation data and grasp how evaluations for a particular product change over time. For example, the analysis unit can analyze the collected evaluation data and grasp the trends in increases and decreases in evaluations and seasonal fluctuations. This allows for appropriate responses by grasping the trends in evaluation data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the collected evaluation data into a generating AI and have the generating AI perform an analysis of evaluation trends.

[0037] The display unit can visualize evaluation data and display changes in evaluation as a graph. For example, the display unit can visualize evaluation data and display changes in evaluation as a graph. For example, the display unit can visualize evaluation data and display it in the form of a line graph, bar graph, heatmap, etc. For example, the display unit can visualize evaluation data, allowing users to grasp changes in evaluation at a glance. This allows users to visually grasp changes in evaluation data. Some or all of the above-described processes in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input evaluation data into a generating AI and have the generating AI perform the visualization of the evaluation data.

[0038] The notification unit can issue alerts in real time when abnormal ratings are detected. For example, the notification unit can analyze rating data and issue alerts in real time when abnormal ratings are detected. For example, the notification unit can analyze rating data and issue alerts when there is a sudden increase in low ratings for a particular product. For example, the notification unit can analyze rating data and issue alerts via means such as email, SMS, or app notifications when abnormal ratings are detected. This allows for a quick response to abnormal ratings. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input rating data into a generating AI and have the generating AI perform abnormal rating detection and alert issuance.

[0039] The dialogue unit can analyze evaluation data in a conversational format and provide insights to marketers. For example, the dialogue unit can analyze evaluation data in a conversational format and provide insights to marketers. For example, the dialogue unit can analyze evaluation data in a conversational format, analyze the reasons why the evaluation of a particular product has declined, and explain those reasons to marketers. For example, the dialogue unit can analyze evaluation data in a conversational format and provide insights using a chatbot or voice assistant. This allows marketers to take appropriate action by providing insights in a conversational format. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input evaluation data into a generating AI and have the generating AI provide insights.

[0040] The data collection unit can analyze a customer's past rating history and select the optimal data collection method. For example, if a customer has given many high ratings in the past, the data collection unit will select a collection method that includes detailed questions. For example, if a customer has given many low ratings in the past, the data collection unit will select a collection method that includes concise questions. For example, based on the customer's rating history, the data collection unit will select a collection method that focuses on specific rating items. This enables efficient data collection by selecting the optimal data collection method based on the customer's past rating history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the customer's past rating history into a generating AI and have the generating AI select the optimal data collection method.

[0041] The data collection unit can filter evaluation data based on the customer's current purchasing behavior and areas of interest. For example, the data collection unit may prioritize collecting evaluation data related to products recently purchased by the customer. For example, the data collection unit may collect evaluation data for products in categories that the customer has shown interest in. For example, the data collection unit may filter and collect highly relevant evaluation data based on the customer's purchase history. This allows for the collection of highly relevant evaluation data by filtering based on the customer's purchasing behavior and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit may input customer purchasing behavior data into a generating AI and have the generating AI perform the filtering.

[0042] The data collection unit can prioritize the collection of highly relevant data based on the customer's geographical location information when collecting evaluation data. For example, if the customer is in a specific region, the data collection unit will prioritize the collection of evaluation data related to that region. For example, if the customer is traveling, the data collection unit will prioritize the collection of evaluation data related to the travel destination. For example, the data collection unit will filter and collect region-specific evaluation data based on the customer's geographical location information. This allows for the collection of highly relevant evaluation data based on the customer's geographical location information, thereby obtaining region-specific evaluation data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the customer's geographical location information into a generating AI and have the generating AI perform the collection of highly relevant data.

[0043] The data collection unit can analyze customers' social media activity and collect relevant data when collecting evaluation data. For example, the data collection unit can collect evaluations shared by customers on social media. For example, the data collection unit can collect evaluation data for products and services that customers are interested in from their social media activity. For example, the data collection unit can analyze comments and reviews on customers' social media and collect relevant evaluation data. This allows for more detailed data to be obtained by collecting relevant evaluation data based on customers' social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input customer social media activity data into a generating AI and have the generating AI perform the collection of relevant data.

[0044] The analysis unit can adjust the level of detail of the analysis based on the importance of the evaluation data during the analysis. For example, the analysis unit performs a detailed analysis on evaluation data with high importance. For example, the analysis unit performs a simplified analysis on evaluation data with low importance. The analysis unit dynamically adjusts the level of detail of the analysis according to the importance of the evaluation data. This enables efficient analysis by adjusting the level of detail of the analysis according to the importance of the evaluation data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis based on importance.

[0045] The analysis unit can apply different analysis algorithms depending on the category of the evaluation data during analysis. For example, the analysis unit can apply different analysis algorithms for each product category. For example, the analysis unit can apply different analysis algorithms for each service category. For example, the analysis unit can select the optimal analysis algorithm according to the category of the evaluation data. By applying the optimal analysis algorithm according to the category of the evaluation data, highly accurate analysis becomes possible. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input evaluation data into a generating AI and have the generating AI execute the application of a category-based analysis algorithm.

[0046] The analysis unit can determine the priority of analysis based on the submission date of the evaluation data during the analysis. For example, the analysis unit may prioritize the analysis of the most recent evaluation data. For example, the analysis unit may postpone the analysis of older evaluation data. For example, the analysis unit may dynamically adjust the priority of analysis based on the submission date. This enables efficient analysis by determining the priority of analysis based on the submission date of the evaluation data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input evaluation data into a generating AI and have the generating AI perform the determination of priority based on the submission date.

[0047] The analysis unit can adjust the order of analysis based on the relevance of the evaluation data during the analysis. For example, the analysis unit prioritizes the analysis of highly relevant evaluation data. For example, the analysis unit postpones the analysis of less relevant evaluation data. For example, the analysis unit dynamically adjusts the order of analysis based on the relevance of the evaluation data. This enables efficient analysis by adjusting the order of analysis based on the relevance of the evaluation data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the analysis order based on relevance.

[0048] The display unit can adjust the level of detail displayed based on the importance of the evaluation data when displaying graphs. For example, the display unit displays a detailed graph for evaluation data with high importance. For example, the display unit displays a simplified graph for evaluation data with low importance. The display unit dynamically adjusts the level of detail displayed according to the importance of the evaluation data. This enables efficient display by adjusting the level of detail displayed according to the importance of the evaluation data. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the level of detail displayed based on importance.

[0049] The display unit can apply different display formats depending on the category of the evaluation data when displaying graphs. For example, the display unit can apply different display formats for each product category. For example, the display unit can apply different display formats for each service category. For example, the display unit can select the optimal display format depending on the category of the evaluation data. By applying the optimal display format according to the category of the evaluation data, a visually easy-to-understand display becomes possible. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input evaluation data into a generating AI and have the generating AI perform the application of a display format based on the category.

[0050] The display unit can determine the display priority based on the submission date of the evaluation data when displaying graphs. For example, the display unit may prioritize displaying the most recent evaluation data. For example, the display unit may postpone displaying older evaluation data. For example, the display unit may dynamically adjust the display priority based on the submission date. This enables efficient display by determining the display priority based on the submission date of the evaluation data. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input evaluation data into a generating AI and have the generating AI perform the determination of priority based on the submission date.

[0051] The display unit can adjust the display order based on the relevance of evaluation data when displaying graphs. For example, the display unit can prioritize displaying highly relevant evaluation data. For example, the display unit can postpone displaying less relevant evaluation data. For example, the display unit can dynamically adjust the display order based on the relevance of the evaluation data. This enables efficient display by adjusting the display order based on the relevance of the evaluation data. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the display order based on relevance.

[0052] The notification unit can adjust the level of detail of an alert notification based on the importance of the evaluation data. For example, the notification unit provides a detailed alert notification for high-importance evaluation data. For example, the notification unit provides a concise alert notification for low-importance evaluation data. The notification unit dynamically adjusts the level of detail of the notification according to the importance of the evaluation data. This enables efficient notifications by adjusting the level of detail of the notification according to the importance of the evaluation data. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the level of detail of the notification based on importance.

[0053] The notification unit can apply different notification algorithms depending on the category of the evaluation data when an alert is issued. For example, the notification unit can apply a different notification algorithm for each product category. For example, the notification unit can apply a different notification algorithm for each service category. For example, the notification unit can select the optimal notification algorithm depending on the category of the evaluation data. This enables efficient notification by applying the optimal notification algorithm according to the category of the evaluation data. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input evaluation data into a generating AI and have the generating AI execute the application of a category-based notification algorithm.

[0054] The notification unit can determine the priority of notifications based on the submission date of evaluation data when an alert is issued. For example, the notification unit may prioritize alert notifications based on the most recent evaluation data. For example, the notification unit may postpone notifications for older evaluation data. For example, the notification unit may dynamically adjust the notification priority based on the submission date. This enables efficient notifications by determining the notification priority based on the submission date of evaluation data. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit may input evaluation data into a generating AI and have the generating AI perform the determination of notification priority based on the submission date.

[0055] The notification unit can adjust the order of notifications based on the relevance of evaluation data when an alert is issued. For example, the notification unit may prioritize alert notifications based on highly relevant evaluation data. For example, the notification unit may postpone notifications for less relevant evaluation data. For example, the notification unit may dynamically adjust the order of notifications based on the relevance of evaluation data. This enables efficient notifications by adjusting the order of notifications based on the relevance of evaluation data. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit may input evaluation data into a generating AI and have the generating AI perform the adjustment of the notification order based on relevance.

[0056] The dialogue unit can adjust the level of detail of insights based on the importance of the evaluation data when providing insights in a dialogue format. For example, the dialogue unit provides detailed insights for evaluation data with high importance. For example, the dialogue unit provides concise insights for evaluation data with low importance. The dialogue unit dynamically adjusts the level of detail of insights according to the importance of the evaluation data. This enables efficient insight provision by adjusting the level of detail of insights according to the importance of the evaluation data. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the level of detail of insights based on importance.

[0057] The dialogue unit can apply different insight-providing algorithms depending on the category of the evaluation data when providing insights in a dialogue format. For example, the dialogue unit can apply different insight-providing algorithms for each product category. For example, the dialogue unit can apply different insight-providing algorithms for each service category. For example, the dialogue unit can select the optimal insight-providing algorithm depending on the category of the evaluation data. This enables efficient insight provision by applying the optimal insight-providing algorithm according to the category of the evaluation data. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input evaluation data into a generating AI and cause the generating AI to execute the application of a category-based insight-providing algorithm.

[0058] The dialogue unit can determine the priority of insight provision based on the submission timing of evaluation data when providing insights in a dialogue format. For example, the dialogue unit may prioritize providing insights based on the most recent evaluation data. For example, the dialogue unit may postpone providing older evaluation data. For example, the dialogue unit may dynamically adjust the priority of insight provision based on the submission timing. This enables efficient insight provision by determining the priority of insight provision based on the submission timing of evaluation data. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input evaluation data into a generating AI and have the generating AI perform the determination of the priority of insight provision based on the submission timing.

[0059] The dialogue unit can adjust the order in which insights are provided based on the relevance of evaluation data when providing insights in a dialogue format. For example, the dialogue unit may prioritize providing insights based on highly relevant evaluation data. For example, the dialogue unit may postpone providing less relevant evaluation data. For example, the dialogue unit may dynamically adjust the order in which insights are provided based on the relevance of evaluation data. This enables efficient insight provision by adjusting the order in which insights are provided based on the relevance of evaluation data. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit may input evaluation data into a generating AI and have the generating AI perform the adjustment of the order in which insights are provided based on relevance.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The data collection unit can analyze the customer's purchase history when collecting customer evaluation data and adjust the data collection method based on specific purchase patterns. For example, if a customer frequently purchases products in a particular category, the unit can prioritize collecting detailed evaluation data related to that category. Furthermore, if a customer has given many high ratings in the past, the unit can select a collection method that includes detailed questions. Conversely, if a customer has given many low ratings in the past, the unit can select a collection method that includes concise questions. This enables efficient data collection by selecting the optimal collection method based on the customer's purchase history. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input customer purchase history data into a generating AI and have the generating AI select the optimal collection method.

[0062] The analysis unit can determine the priority of analysis based on the submission date of the collected evaluation data. For example, it can prioritize the analysis of the most recent evaluation data and postpone the analysis of older data. It can also dynamically adjust the analysis priority based on the submission date of the evaluation data. This enables efficient analysis by determining the analysis priority based on the submission date of the evaluation data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input evaluation data into a generating AI and have the generating AI perform the determination of priority based on the submission date.

[0063] The display unit can apply different display formats depending on the category of the evaluation data when visualizing it. For example, it can apply different display formats for each product category and different display formats for each service category. It can also select the optimal display format depending on the category of the evaluation data. By applying the optimal display format according to the category of the evaluation data, a visually easy-to-understand display becomes possible. Some or all of the above processing in the display unit may be performed using AI or not. For example, the display unit can input evaluation data into a generating AI and have the generating AI perform the application of a display format based on the category.

[0064] The notification unit can adjust the level of detail of notifications based on the importance of the evaluation data when it detects an abnormal evaluation and issues an alert in real time. For example, it can send detailed alert notifications for high-importance evaluation data and concise alert notifications for low-importance evaluation data. It can also dynamically adjust the level of detail of notifications according to the importance of the evaluation data. This allows for efficient notifications by adjusting the level of detail of notifications according to the importance of the evaluation data. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of notification detail based on importance.

[0065] The dialogue unit analyzes evaluation data in a conversational format and provides insights to marketers, adjusting the order in which insights are provided based on the relevance of the evaluation data. For example, insights can be prioritized based on highly relevant evaluation data, while less relevant data can be provided later. The order in which insights are provided can also be dynamically adjusted based on the relevance of the evaluation data. This allows for efficient insight provision by adjusting the order in which insights are provided based on the relevance of the evaluation data. Some or all of the above processing in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the order in which insights are provided based on relevance.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The data collection unit aggregates customer evaluation data for products and services along a timeline. For example, it can collect customer ratings and reviews of products on e-commerce sites and aggregate them on a daily, weekly, or monthly basis. Step 2: The analysis unit performs trend analysis based on the evaluation data collected by the data collection unit. For example, by analyzing the collected evaluation data, it is possible to understand how evaluations of a particular product change over time, the trend of increases or decreases in evaluations, and seasonal fluctuations. Step 3: The display unit displays a graph showing the changes in the evaluation data analyzed by the analysis unit. For example, the evaluation data can be visualized and displayed in formats such as line graphs, bar graphs, and heatmaps. Step 4: The notification unit issues an alert notification when the analysis unit detects an abnormal evaluation. For example, by analyzing evaluation data, if there is a sudden increase in low ratings for a particular product, an alert can be sent in real time via email, SMS, app notification, etc. Step 5: The dialogue unit provides insights in a conversational format based on the results from the analysis unit. For example, it can analyze evaluation data in a conversational format, analyze the reasons why the evaluation of a particular product has declined, and explain those reasons to marketers. It is also possible to provide insights using chatbots or voice assistants.

[0068] (Example of form 2) The review analysis system according to an embodiment of the present invention is a powerful review analysis tool for business owners and marketers. This review analysis system aggregates customer evaluations of products and services over time and provides trend analysis, display of change graphs, alert notifications for anomaly evaluations, and interactive analysis functions. For example, the review analysis system aggregates customer evaluations of products and services over time. In this process, it collects detailed data such as what kind of evaluations customers made and when those evaluations were made. For example, it collects data on customer evaluations and reviews of products on an e-commerce site. This allows customer evaluation data to be aggregated over time. Next, the review analysis system performs trend analysis based on the aggregated evaluation data. The AI ​​analyzes the collected evaluation data and grasps the evaluation trends. For example, it can analyze how evaluations of a particular product change over time. This allows for grasping evaluation trends and taking appropriate action. Furthermore, the review analysis system displays a graph of the changes in evaluation data. The AI ​​visualizes the evaluation data and displays the changes in evaluations as a graph. For example, it can display a graph showing how evaluations of a particular product change over time. This allows for a quick grasp of the changes in evaluations. Furthermore, the review analysis system provides alert notifications when anomaly ratings are detected. The AI ​​analyzes the rating data and issues alerts in real time if anomalies are detected. For example, it can issue an alert if there is a sudden increase in low ratings for a particular product. This allows for a quick response to anomaly ratings. Finally, the review analysis system provides interactive analysis capabilities. The AI ​​analyzes rating data in a conversational format and provides insights to marketers. For example, it can analyze the reasons why ratings for a particular product are declining and explain those reasons to marketers. This allows marketers to take appropriate action based on the rating data. This system enables business owners and marketers to monitor changes in ratings in real time and respond quickly and appropriately to market trends and consumer satisfaction.For example, it's possible to identify trends based on evaluation data and formulate appropriate marketing strategies. Furthermore, rapid response to anomaly reviews can improve consumer satisfaction. Additionally, by utilizing interactive analytical functions, insights based on evaluation data can be gained and used to improve the business. In this way, review analysis systems can efficiently aggregate, analyze, display, notify, and provide insights in an interactive format based on customer evaluation data.

[0069] The review analysis system according to the embodiment comprises a collection unit, an analysis unit, a display unit, a notification unit, and an interaction unit. The collection unit aggregates customer evaluation data for products and services along a time axis. The collection unit collects, for example, data on evaluations and reviews made by customers on e-commerce sites. The collection unit can collect, for example, data on evaluations and reviews made by customers on products and aggregate it along a time axis. The collection unit can collect, for example, data on evaluations and reviews made by customers on products and aggregate it in aggregation units such as daily, weekly, and monthly. The analysis unit performs trend analysis based on the evaluation data aggregated by the collection unit. The analysis unit can, for example, analyze the collected evaluation data and grasp the evaluation trend. The analysis unit can, for example, analyze the collected evaluation data and grasp how evaluations for a particular product change over time. The analysis unit can, for example, analyze the collected evaluation data and grasp the trend of increase or decrease in evaluations and seasonal fluctuations. The display unit displays a graph of the changes in evaluation data analyzed by the analysis unit. The display unit visualizes evaluation data and displays changes in evaluations as graphs. The display unit can visualize evaluation data and display it in formats such as line graphs, bar graphs, and heatmaps. The display unit visualizes evaluation data, allowing users to grasp changes in evaluations at a glance. The notification unit provides alert notifications when the analysis unit detects abnormal evaluations. The notification unit analyzes evaluation data and sends real-time alerts when abnormal evaluations are detected. The notification unit can analyze evaluation data and send alerts when there is a sudden increase in low evaluations for a particular product. The notification unit can analyze evaluation data and send alerts via email, SMS, app notifications, etc., when abnormal evaluations are detected. The dialogue unit provides insights in a dialogue format based on the results of the analysis unit. The dialogue unit analyzes evaluation data in a dialogue format and provides insights to marketers. The dialogue unit can analyze evaluation data in a dialogue format, analyze the reasons why evaluations for a particular product are declining, and explain those reasons to marketers.The dialogue component can, for example, analyze evaluation data in a conversational format and provide insights using chatbots or voice assistants. This enables the review analysis system to efficiently aggregate, analyze, display, notify, and provide insights in a conversational format based on customer evaluation data.

[0070] The data collection unit aggregates customer evaluation data for products and services along a timeline. Specifically, it collects data on customer ratings and reviews of products on e-commerce sites. For example, the data collection unit can collect customer ratings and reviews and aggregate them in daily, weekly, or monthly increments. This allows the data collection unit to efficiently collect customer evaluation data and organize it along a timeline. Furthermore, the data collection unit can collect data from multiple e-commerce sites and social media platforms. For example, the data collection unit can use APIs to retrieve data from each platform and store it in a unified format. This allows for centralized management of data from different platforms and provides comprehensive evaluation data. In addition, the data collection unit can use natural language processing technology to extract evaluation elements from text data. For example, it can automatically classify positive and negative ratings from customer reviews and understand evaluation trends. This allows the data collection unit to extract useful information not only from numerical data but also from text data, improving the quality of evaluation data. Furthermore, the data collection unit can adjust the frequency and accuracy of data collection, enabling flexible responses to specific situations and conditions. For example, if there is a sudden surge in reviews for a particular product or service, the collection frequency can be increased to collect data in real time. This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0071] The analysis department performs trend analysis based on evaluation data aggregated by the collection department. Specifically, it analyzes the collected evaluation data to understand evaluation trends. For example, it can understand how evaluations for a particular product change over time. The analysis department can use AI to analyze the data and understand trends in increases and decreases in evaluations, as well as seasonal fluctuations. The AI ​​uses machine learning algorithms to learn patterns from past data and predict future evaluation fluctuations. For example, if evaluations tend to increase in relation to a particular season or event, it can predict future evaluations based on that pattern. Furthermore, the analysis department can use anomaly detection algorithms to detect unusual patterns and abnormal data. For example, if there is a sudden increase in low evaluations for a particular product, it can identify the cause and take countermeasures early. In addition, the analysis department can segment the evaluation data to understand evaluation trends for different customer segments and regions. For example, it can classify evaluation data based on attributes such as age, gender, and region, and analyze evaluation trends for each segment. This allows the analysis department to obtain more detailed insights, which can be used to formulate marketing strategies. Furthermore, the analysis unit visualizes the evaluation data and displays it as graphs and charts, allowing for an intuitive understanding of changes in the evaluation. This enables the analysis unit to quickly and accurately analyze the collected data and grasp the surrounding risk situation in real time.

[0072] The display unit shows a graph of the changes in evaluation data analyzed by the analysis unit. Specifically, it visualizes the evaluation data and displays changes in evaluation as a graph. The display unit can visualize the evaluation data and display it in formats such as line graphs, bar graphs, and heatmaps. This allows users to grasp fluctuations in evaluation data at a glance. Furthermore, the display unit provides interactive graphs, allowing users to focus on specific periods or products to view detailed data. For example, if a user selects a specific period, the evaluation data for that period will be displayed in detail. The display unit also provides a filtering function for evaluation data, allowing users to narrow down the data based on specific conditions. For example, it can display only reviews containing a specific evaluation score range or specific keywords. This allows users to quickly obtain the necessary information and efficiently analyze evaluation data. In addition, the display unit can update fluctuations in evaluation data in real time, always providing the latest information. For example, when new evaluation data is collected, the graph is automatically updated to reflect the latest evaluation status. This allows the display unit to always provide users with the latest information and support quick decision-making.

[0073] The notification unit issues alerts when the analysis unit detects anomaly evaluations. Specifically, it analyzes evaluation data and issues real-time alerts when anomaly evaluations are detected. For example, it can issue an alert if there is a sudden increase in low evaluations for a particular product. The notification unit can send alerts via email, SMS, app notifications, etc. This allows stakeholders to respond quickly to anomaly evaluations. Furthermore, the notification unit can set alert priorities and select different notification methods depending on the importance. For example, if a serious anomaly evaluation is detected, it will immediately notify via SMS or phone, while for minor anomalies, it will notify via email or app notifications. The notification unit can also save alert history and analyze past anomaly evaluation trends. This allows for the prediction of future anomalies and the planning of countermeasures based on past alert data. In addition, the notification unit can collect user feedback and continuously improve the accuracy and effectiveness of alerts. For example, it can review the content of alerts and notification methods based on feedback from users who have received alerts. This allows the notification unit to provide alerts to users quickly and reliably, supporting rapid responses to anomaly evaluations.

[0074] The dialogue unit provides insights in a conversational format based on the results from the analysis unit. Specifically, it analyzes evaluation data in a conversational format and provides insights to marketers. For example, it can analyze the reasons why the evaluation of a particular product is declining and explain those reasons to marketers. The dialogue unit can provide insights using chatbots and voice assistants. This allows marketers to quickly develop concrete countermeasures in response to fluctuations in evaluation data. Furthermore, the dialogue unit can answer user questions in real time and provide advice based on evaluation data. For example, if a marketer wants to know the evaluation trend for a particular product, the dialogue unit will explain the trend based on the latest evaluation data and propose future countermeasures. The dialogue unit can also utilize historical data and statistical information to perform long-term risk assessments and trend analysis. For example, based on historical evaluation data, it can predict evaluation fluctuations related to specific seasons or events and propose future countermeasures. This allows the dialogue unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, improving the reliability and security of the entire system. Furthermore, the dialogue unit can collect user feedback and continuously improve the accuracy and effectiveness of the dialogue content. For example, the dialogue algorithm and response content can be reviewed based on feedback obtained through the dialogue. This allows the dialogue unit to provide users with quick and accurate insights and support the analysis of evaluation data and the development of countermeasures.

[0075] The data collection unit can collect data on customer ratings and reviews of products on e-commerce sites. For example, the data collection unit can collect data on customer ratings and reviews of products on e-commerce sites and aggregate it along a timeline. For example, the data collection unit can collect data on customer ratings and reviews of products on e-commerce sites and aggregate it in units such as daily, weekly, or monthly. This allows for detailed customer evaluations to be obtained by collecting rating data from e-commerce sites. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input rating data obtained from e-commerce sites into a generating AI and have the generating AI perform the aggregation of the rating data.

[0076] The analysis unit can analyze the collected evaluation data and grasp the trends in evaluations. For example, the analysis unit can analyze the collected evaluation data and grasp the trends in evaluations. For example, the analysis unit can analyze the collected evaluation data and grasp how evaluations for a particular product change over time. For example, the analysis unit can analyze the collected evaluation data and grasp the trends in increases and decreases in evaluations and seasonal fluctuations. This allows for appropriate responses by grasping the trends in evaluation data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the collected evaluation data into a generating AI and have the generating AI perform an analysis of evaluation trends.

[0077] The display unit can visualize evaluation data and display changes in evaluation as a graph. For example, the display unit can visualize evaluation data and display changes in evaluation as a graph. For example, the display unit can visualize evaluation data and display it in the form of a line graph, bar graph, heatmap, etc. For example, the display unit can visualize evaluation data, allowing users to grasp changes in evaluation at a glance. This allows users to visually grasp changes in evaluation data. Some or all of the above-described processes in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input evaluation data into a generating AI and have the generating AI perform the visualization of the evaluation data.

[0078] The notification unit can issue alerts in real time when abnormal ratings are detected. For example, the notification unit can analyze rating data and issue alerts in real time when abnormal ratings are detected. For example, the notification unit can analyze rating data and issue alerts when there is a sudden increase in low ratings for a particular product. For example, the notification unit can analyze rating data and issue alerts via means such as email, SMS, or app notifications when abnormal ratings are detected. This allows for a quick response to abnormal ratings. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input rating data into a generating AI and have the generating AI perform abnormal rating detection and alert issuance.

[0079] The dialogue unit can analyze evaluation data in a conversational format and provide insights to marketers. For example, the dialogue unit can analyze evaluation data in a conversational format and provide insights to marketers. For example, the dialogue unit can analyze evaluation data in a conversational format, analyze the reasons why the evaluation of a particular product has declined, and explain those reasons to marketers. For example, the dialogue unit can analyze evaluation data in a conversational format and provide insights using a chatbot or voice assistant. This allows marketers to take appropriate action by providing insights in a conversational format. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input evaluation data into a generating AI and have the generating AI provide insights.

[0080] The data collection unit can estimate the user's emotions and adjust the timing of evaluation data collection based on the estimated emotions. For example, if the user is showing positive emotions, the data collection unit will collect evaluation data more frequently to obtain detailed feedback. For example, if the user is showing negative emotions, the data collection unit will delay the collection timing to reduce the user's stress. For example, if the user is showing neutral emotions, the data collection unit will collect evaluation data at the normal collection timing. This allows for more appropriate data collection by adjusting the timing of evaluation data collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, or not using AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI adjust the collection timing based on emotions.

[0081] The data collection unit can analyze a customer's past rating history and select the optimal data collection method. For example, if a customer has given many high ratings in the past, the data collection unit will select a collection method that includes detailed questions. For example, if a customer has given many low ratings in the past, the data collection unit will select a collection method that includes concise questions. For example, based on the customer's rating history, the data collection unit will select a collection method that focuses on specific rating items. This enables efficient data collection by selecting the optimal data collection method based on the customer's past rating history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the customer's past rating history into a generating AI and have the generating AI select the optimal data collection method.

[0082] The data collection unit can filter evaluation data based on the customer's current purchasing behavior and areas of interest. For example, the data collection unit may prioritize collecting evaluation data related to products recently purchased by the customer. For example, the data collection unit may collect evaluation data for products in categories that the customer has shown interest in. For example, the data collection unit may filter and collect highly relevant evaluation data based on the customer's purchase history. This allows for the collection of highly relevant evaluation data by filtering based on the customer's purchasing behavior and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit may input customer purchasing behavior data into a generating AI and have the generating AI perform the filtering.

[0083] The data collection unit can estimate the user's emotions and determine the priority of evaluation data to collect based on the estimated user emotions. For example, if the user is showing positive emotions, the data collection unit will prioritize collecting detailed feedback. For example, if the user is showing negative emotions, the data collection unit will prioritize collecting concise feedback. For example, if the user is showing neutral emotions, the data collection unit will prioritize collecting normal feedback. This allows for more appropriate data collection by prioritizing evaluation data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform emotion-based priority determination.

[0084] The data collection unit can prioritize the collection of highly relevant data based on the customer's geographical location information when collecting evaluation data. For example, if the customer is in a specific region, the data collection unit will prioritize the collection of evaluation data related to that region. For example, if the customer is traveling, the data collection unit will prioritize the collection of evaluation data related to the travel destination. For example, the data collection unit will filter and collect region-specific evaluation data based on the customer's geographical location information. This allows for the collection of highly relevant evaluation data based on the customer's geographical location information, thereby obtaining region-specific evaluation data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the customer's geographical location information into a generating AI and have the generating AI perform the collection of highly relevant data.

[0085] The data collection unit can analyze customers' social media activity and collect relevant data when collecting evaluation data. For example, the data collection unit can collect evaluations shared by customers on social media. For example, the data collection unit can collect evaluation data for products and services that customers are interested in from their social media activity. For example, the data collection unit can analyze comments and reviews on customers' social media and collect relevant evaluation data. This allows for more detailed data to be obtained by collecting relevant evaluation data based on customers' social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input customer social media activity data into a generating AI and have the generating AI perform the collection of relevant data.

[0086] The analysis unit can estimate the user's emotions and adjust the trend analysis method based on the estimated user emotions. For example, if the user shows positive emotions, the analysis unit performs a detailed trend analysis. For example, if the user shows negative emotions, the analysis unit performs a concise trend analysis. For example, if the user shows neutral emotions, the analysis unit performs a normal trend analysis. This allows for more appropriate trend analysis by adjusting the trend analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI perform an adjustment of the trend analysis based on emotions.

[0087] The analysis unit can adjust the level of detail of the analysis based on the importance of the evaluation data during the analysis. For example, the analysis unit performs a detailed analysis on evaluation data with high importance. For example, the analysis unit performs a simplified analysis on evaluation data with low importance. The analysis unit dynamically adjusts the level of detail of the analysis according to the importance of the evaluation data. This enables efficient analysis by adjusting the level of detail of the analysis according to the importance of the evaluation data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis based on importance.

[0088] The analysis unit can apply different analysis algorithms depending on the category of the evaluation data during analysis. For example, the analysis unit can apply different analysis algorithms for each product category. For example, the analysis unit can apply different analysis algorithms for each service category. For example, the analysis unit can select the optimal analysis algorithm according to the category of the evaluation data. By applying the optimal analysis algorithm according to the category of the evaluation data, highly accurate analysis becomes possible. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input evaluation data into a generating AI and have the generating AI execute the application of a category-based analysis algorithm.

[0089] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is showing positive emotions, the analysis unit will display detailed analysis results. For example, if the user is showing negative emotions, the analysis unit will display concise analysis results. For example, if the user is showing neutral emotions, the analysis unit will display normal analysis results. This allows for a more appropriate display by adjusting the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI perform adjustments to the display method based on emotions.

[0090] The analysis unit can determine the priority of analysis based on the submission date of the evaluation data during the analysis. For example, the analysis unit may prioritize the analysis of the most recent evaluation data. For example, the analysis unit may postpone the analysis of older evaluation data. For example, the analysis unit may dynamically adjust the priority of analysis based on the submission date. This enables efficient analysis by determining the priority of analysis based on the submission date of the evaluation data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input evaluation data into a generating AI and have the generating AI perform the determination of priority based on the submission date.

[0091] The analysis unit can adjust the order of analysis based on the relevance of the evaluation data during the analysis. For example, the analysis unit prioritizes the analysis of highly relevant evaluation data. For example, the analysis unit postpones the analysis of less relevant evaluation data. For example, the analysis unit dynamically adjusts the order of analysis based on the relevance of the evaluation data. This enables efficient analysis by adjusting the order of analysis based on the relevance of the evaluation data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the analysis order based on relevance.

[0092] The display unit can estimate the user's emotions and adjust the graph display method based on the estimated user emotions. For example, if the user is showing positive emotions, the display unit will display a detailed graph. For example, if the user is showing negative emotions, the display unit will display a concise graph. For example, if the user is showing neutral emotions, the display unit will display a normal graph. This allows for a more appropriate display by adjusting the graph display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input user emotion data into the generative AI and have the generative AI perform adjustments to the display method based on emotions.

[0093] The display unit can adjust the level of detail displayed based on the importance of the evaluation data when displaying graphs. For example, the display unit displays a detailed graph for evaluation data with high importance. For example, the display unit displays a simplified graph for evaluation data with low importance. The display unit dynamically adjusts the level of detail displayed according to the importance of the evaluation data. This enables efficient display by adjusting the level of detail displayed according to the importance of the evaluation data. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the level of detail displayed based on importance.

[0094] The display unit can apply different display formats depending on the category of the evaluation data when displaying graphs. For example, the display unit can apply different display formats for each product category. For example, the display unit can apply different display formats for each service category. For example, the display unit can select the optimal display format depending on the category of the evaluation data. By applying the optimal display format according to the category of the evaluation data, a visually easy-to-understand display becomes possible. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input evaluation data into a generating AI and have the generating AI perform the application of a display format based on the category.

[0095] The display unit can estimate the user's emotions and adjust the display order of graphs based on the estimated emotions. For example, if the user is showing positive emotions, the display unit will prioritize displaying detailed graphs. For example, if the user is showing negative emotions, the display unit will prioritize displaying concise graphs. For example, if the user is showing neutral emotions, the display unit will prioritize displaying normal graphs. This allows for a more appropriate display by adjusting the display order of graphs according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the display order based on emotions.

[0096] The display unit can determine the display priority based on the submission date of the evaluation data when displaying graphs. For example, the display unit may prioritize displaying the most recent evaluation data. For example, the display unit may postpone displaying older evaluation data. For example, the display unit may dynamically adjust the display priority based on the submission date. This enables efficient display by determining the display priority based on the submission date of the evaluation data. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input evaluation data into a generating AI and have the generating AI perform the determination of priority based on the submission date.

[0097] The display unit can adjust the display order based on the relevance of evaluation data when displaying graphs. For example, the display unit can prioritize displaying highly relevant evaluation data. For example, the display unit can postpone displaying less relevant evaluation data. For example, the display unit can dynamically adjust the display order based on the relevance of the evaluation data. This enables efficient display by adjusting the display order based on the relevance of the evaluation data. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the display order based on relevance.

[0098] The notification unit can estimate the user's emotions and adjust the alert notification method based on the estimated emotions. For example, if the user is showing positive emotions, the notification unit will provide a detailed alert notification. For example, if the user is showing negative emotions, the notification unit will provide a concise alert notification. For example, if the user is showing neutral emotions, the notification unit will provide a normal alert notification. This allows for more appropriate notifications by adjusting the alert notification method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI, for example, or not using AI. For example, the notification unit can input user emotion data into a generative AI and have the generative AI adjust the notification method based on emotions.

[0099] The notification unit can adjust the level of detail of an alert notification based on the importance of the evaluation data. For example, the notification unit provides a detailed alert notification for high-importance evaluation data. For example, the notification unit provides a concise alert notification for low-importance evaluation data. The notification unit dynamically adjusts the level of detail of the notification according to the importance of the evaluation data. This enables efficient notifications by adjusting the level of detail of the notification according to the importance of the evaluation data. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the level of detail of the notification based on importance.

[0100] The notification unit can apply different notification algorithms depending on the category of the evaluation data when an alert is issued. For example, the notification unit can apply a different notification algorithm for each product category. For example, the notification unit can apply a different notification algorithm for each service category. For example, the notification unit can select the optimal notification algorithm depending on the category of the evaluation data. This enables efficient notification by applying the optimal notification algorithm according to the category of the evaluation data. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input evaluation data into a generating AI and have the generating AI execute the application of a category-based notification algorithm.

[0101] The notification unit can estimate the user's emotions and determine the priority of alert notifications based on the estimated emotions. For example, if the user is showing positive emotions, the notification unit will prioritize detailed alert notifications. For example, if the user is showing negative emotions, the notification unit will prioritize concise alert notifications. For example, if the user is showing neutral emotions, the notification unit will prioritize regular alert notifications. This allows for more appropriate notifications by determining the priority of alert notifications according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input user emotion data into a generative AI and have the generative AI perform the determination of notification priorities based on emotions.

[0102] The notification unit can determine the priority of notifications based on the submission date of evaluation data when an alert is issued. For example, the notification unit may prioritize alert notifications based on the most recent evaluation data. For example, the notification unit may postpone notifications for older evaluation data. For example, the notification unit may dynamically adjust the notification priority based on the submission date. This enables efficient notifications by determining the notification priority based on the submission date of evaluation data. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit may input evaluation data into a generating AI and have the generating AI perform the determination of notification priority based on the submission date.

[0103] The notification unit can adjust the order of notifications based on the relevance of evaluation data when an alert is issued. For example, the notification unit may prioritize alert notifications based on highly relevant evaluation data. For example, the notification unit may postpone notifications for less relevant evaluation data. For example, the notification unit may dynamically adjust the order of notifications based on the relevance of evaluation data. This enables efficient notifications by adjusting the order of notifications based on the relevance of evaluation data. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit may input evaluation data into a generating AI and have the generating AI perform the adjustment of the notification order based on relevance.

[0104] The dialogue unit can estimate the user's emotions and adjust the way it delivers insights in a dialogue format based on the estimated emotions. For example, if the user is showing positive emotions, the dialogue unit will provide detailed insights. For example, if the user is showing negative emotions, the dialogue unit will provide concise insights. For example, if the user is showing neutral emotions, the dialogue unit will provide standard insights. This allows for more appropriate insight delivery by adjusting the way insights are delivered according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or not using AI. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI adjust the way insights are delivered based on emotions.

[0105] The dialogue unit can adjust the level of detail of insights based on the importance of the evaluation data when providing insights in a dialogue format. For example, the dialogue unit provides detailed insights for evaluation data with high importance. For example, the dialogue unit provides concise insights for evaluation data with low importance. The dialogue unit dynamically adjusts the level of detail of insights according to the importance of the evaluation data. This enables efficient insight provision by adjusting the level of detail of insights according to the importance of the evaluation data. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the level of detail of insights based on importance.

[0106] The dialogue unit can apply different insight-providing algorithms depending on the category of the evaluation data when providing insights in a dialogue format. For example, the dialogue unit can apply different insight-providing algorithms for each product category. For example, the dialogue unit can apply different insight-providing algorithms for each service category. For example, the dialogue unit can select the optimal insight-providing algorithm depending on the category of the evaluation data. This enables efficient insight provision by applying the optimal insight-providing algorithm according to the category of the evaluation data. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input evaluation data into a generating AI and cause the generating AI to execute the application of a category-based insight-providing algorithm.

[0107] The dialogue unit can estimate the user's emotions and determine the priority of providing dialogue-based insights based on the estimated emotions. For example, if the user is showing positive emotions, the dialogue unit will prioritize providing detailed insights. For example, if the user is showing negative emotions, the dialogue unit will prioritize providing concise insights. For example, if the user is showing neutral emotions, the dialogue unit will prioritize providing standard insights. This allows for the provision of more appropriate insights by determining the priority of insight provision according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit may be performed using AI or not using AI. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI perform the determination of the priority of insight provision based on emotions.

[0108] The dialogue unit can determine the priority of insight provision based on the submission timing of evaluation data when providing insights in a dialogue format. For example, the dialogue unit may prioritize providing insights based on the most recent evaluation data. For example, the dialogue unit may postpone providing older evaluation data. For example, the dialogue unit may dynamically adjust the priority of insight provision based on the submission timing. This enables efficient insight provision by determining the priority of insight provision based on the submission timing of evaluation data. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input evaluation data into a generating AI and have the generating AI perform the determination of the priority of insight provision based on the submission timing.

[0109] The dialogue unit can adjust the order in which insights are provided based on the relevance of evaluation data when providing insights in a dialogue format. For example, the dialogue unit may prioritize providing insights based on highly relevant evaluation data. For example, the dialogue unit may postpone providing less relevant evaluation data. For example, the dialogue unit may dynamically adjust the order in which insights are provided based on the relevance of evaluation data. This enables efficient insight provision by adjusting the order in which insights are provided based on the relevance of evaluation data. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit may input evaluation data into a generating AI and have the generating AI perform the adjustment of the order in which insights are provided based on relevance.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The data collection unit can analyze the customer's purchase history when collecting customer evaluation data and adjust the data collection method based on specific purchase patterns. For example, if a customer frequently purchases products in a particular category, the unit can prioritize collecting detailed evaluation data related to that category. Furthermore, if a customer has given many high ratings in the past, the unit can select a collection method that includes detailed questions. Conversely, if a customer has given many low ratings in the past, the unit can select a collection method that includes concise questions. This enables efficient data collection by selecting the optimal collection method based on the customer's purchase history. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input customer purchase history data into a generating AI and have the generating AI select the optimal collection method.

[0112] The analysis unit can determine the priority of analysis based on the submission date of the collected evaluation data. For example, it can prioritize the analysis of the most recent evaluation data and postpone the analysis of older data. It can also dynamically adjust the analysis priority based on the submission date of the evaluation data. This enables efficient analysis by determining the analysis priority based on the submission date of the evaluation data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input evaluation data into a generating AI and have the generating AI perform the determination of priority based on the submission date.

[0113] The display unit can apply different display formats depending on the category of the evaluation data when visualizing it. For example, it can apply different display formats for each product category and different display formats for each service category. It can also select the optimal display format depending on the category of the evaluation data. By applying the optimal display format according to the category of the evaluation data, a visually easy-to-understand display becomes possible. Some or all of the above processing in the display unit may be performed using AI or not. For example, the display unit can input evaluation data into a generating AI and have the generating AI perform the application of a display format based on the category.

[0114] The notification unit can adjust the level of detail of notifications based on the importance of the evaluation data when it detects an abnormal evaluation and issues an alert in real time. For example, it can send detailed alert notifications for high-importance evaluation data and concise alert notifications for low-importance evaluation data. It can also dynamically adjust the level of detail of notifications according to the importance of the evaluation data. This allows for efficient notifications by adjusting the level of detail of notifications according to the importance of the evaluation data. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of notification detail based on importance.

[0115] The dialogue unit analyzes evaluation data in a conversational format and provides insights to marketers, adjusting the order in which insights are provided based on the relevance of the evaluation data. For example, insights can be prioritized based on highly relevant evaluation data, while less relevant data can be provided later. The order in which insights are provided can also be dynamically adjusted based on the relevance of the evaluation data. This allows for efficient insight provision by adjusting the order in which insights are provided based on the relevance of the evaluation data. Some or all of the above processing in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input evaluation data into a generating AI and have the generating AI perform the adjustment of the order in which insights are provided based on relevance.

[0116] The data collection unit can estimate the user's emotions and adjust the timing of evaluation data collection based on the estimated emotions. For example, if the user is showing positive emotions, evaluation data can be collected more frequently to obtain detailed feedback. If the user is showing negative emotions, the collection timing can be delayed to reduce the user's stress. Furthermore, if the user is showing neutral emotions, evaluation data can be collected at the normal collection timing. This allows for more appropriate data collection by adjusting the timing of evaluation data collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI adjust the collection timing based on emotions.

[0117] The analysis unit can estimate the user's emotions and adjust the trend analysis method based on the estimated user emotions. For example, if the user shows positive emotions, a detailed trend analysis can be performed. If the user shows negative emotions, a concise trend analysis can be performed. Furthermore, if the user shows neutral emotions, a normal trend analysis can be performed. In this way, adjusting the trend analysis method according to the user's emotions enables more appropriate trend analysis. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the trend analysis based on emotions.

[0118] The display unit can estimate the user's emotions and adjust the graph display method based on the estimated emotions. For example, if the user is showing positive emotions, a detailed graph can be displayed. If the user is showing negative emotions, a concise graph can be displayed. Furthermore, if the user is showing neutral emotions, a normal graph can be displayed. This allows for a more appropriate display by adjusting the graph display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. Some or all of the above processing in the display unit may be performed using AI or not. For example, the display unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the display method based on the emotions.

[0119] The notification unit can estimate the user's emotions and adjust the alert notification method based on the estimated emotions. For example, if the user is showing positive emotions, a detailed alert notification can be sent. If the user is showing negative emotions, a concise alert notification can be sent. Furthermore, if the user is showing neutral emotions, a normal alert notification can be sent. By adjusting the alert notification method according to the user's emotions, more appropriate notifications can be made. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the notification method based on emotions.

[0120] The dialogue unit can estimate the user's emotions and adjust the way it delivers insights in a dialogue format based on the estimated emotions. For example, if the user is showing positive emotions, it can provide detailed insights. If the user is showing negative emotions, it can provide concise insights. Furthermore, if the user is showing neutral emotions, it can provide standard insights. This allows for more appropriate insight delivery by adjusting the way insights are delivered according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Some or all of the above processing in the dialogue unit may be performed using AI or not. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the insight delivery method based on emotions.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The data collection unit aggregates customer evaluation data for products and services along a timeline. For example, it can collect customer ratings and reviews of products on e-commerce sites and aggregate them on a daily, weekly, or monthly basis. Step 2: The analysis unit performs trend analysis based on the evaluation data collected by the data collection unit. For example, by analyzing the collected evaluation data, it is possible to understand how evaluations of a particular product change over time, the trend of increases or decreases in evaluations, and seasonal fluctuations. Step 3: The display unit displays a graph showing the changes in the evaluation data analyzed by the analysis unit. For example, the evaluation data can be visualized and displayed in formats such as line graphs, bar graphs, and heatmaps. Step 4: The notification unit issues an alert notification when the analysis unit detects an abnormal evaluation. For example, by analyzing evaluation data, if there is a sudden increase in low ratings for a particular product, an alert can be sent in real time via email, SMS, app notification, etc. Step 5: The dialogue unit provides insights in a conversational format based on the results from the analysis unit. For example, it can analyze evaluation data in a conversational format, analyze the reasons why the evaluation of a particular product has declined, and explain those reasons to marketers. It is also possible to provide insights using chatbots or voice assistants.

[0123] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0126] Each of the multiple elements described above, including the data collection unit, analysis unit, display unit, notification unit, and dialogue unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data collection unit collects customer evaluation data using the camera 42 and microphone 38B of the smart device 14 and aggregates it along a time axis by the control unit 46A. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, for example, to analyze the collected evaluation data and grasp trends. The display unit displays a graph of the changes in evaluation data on the display 40A of the smart device 14. The notification unit detects an anomaly in evaluation by the identification processing unit 290 of the data processing unit 12 and issues an alert in real time. The dialogue unit provides insights in an interactive format by the control unit 46A of the smart device 14, for example. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 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.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the data collection unit, analysis unit, display unit, notification unit, and dialogue unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit collects customer evaluation data using the camera 42 and microphone 238 of the smart glasses 214 and aggregates it along the time axis by the control unit 46A. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which analyzes the collected evaluation data and grasps trends. The display unit displays a graph of the changes in evaluation data on the display of the smart glasses 214. The notification unit detects an anomaly evaluation by the identification processing unit 290 of the data processing unit 12 and issues an alert in real time. The dialogue unit provides insights in a dialogue format by the control unit 46A of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the data collection unit, analysis unit, display unit, notification unit, and dialogue unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data collection unit collects customer evaluation data using the camera 42 and microphone 238 of the headset terminal 314 and aggregates it along the time axis by the control unit 46A. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which analyzes the collected evaluation data and grasps trends. The display unit displays a graph of the changes in evaluation data on the display 343 of the headset terminal 314. The notification unit detects abnormal evaluations by the identification processing unit 290 of the data processing unit 12 and issues alerts in real time. The dialogue unit provides insights in a dialogue format by the control unit 46A of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 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.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the data collection unit, analysis unit, display unit, notification unit, and dialogue unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the data collection unit collects customer evaluation data using the camera 42 and microphone 238 of the robot 414 and aggregates it along the time axis by the control unit 46A. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, for example, to analyze the collected evaluation data and grasp trends. The display unit displays a graph of the changes in evaluation data on the display of the robot 414, for example. The notification unit detects an anomaly evaluation by the identification processing unit 290 of the data processing unit 12 and issues an alert in real time, for example. The dialogue unit provides insights in an interactive format by the control unit 46A of the robot 414, for example. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0176] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] 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.

[0186] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) A data collection unit that aggregates customer evaluation data for products and services along a timeline, An analysis unit performs trend analysis based on the evaluation data collected by the aforementioned collection unit, A display unit that displays a graph showing the changes in evaluation data analyzed by the aforementioned analysis unit, A notification unit that issues an alert notification when an abnormal evaluation is detected by the analysis unit, The system includes a dialogue unit that provides insights in an interactive format based on the results of the analysis unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is We collect data on customer ratings and reviews of products on e-commerce sites. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Analyze the collected evaluation data to understand evaluation trends. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned display unit is Visualize evaluation data and display changes in evaluation as graphs. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned notification unit, An alert will be sent in real time if an abnormal evaluation is detected. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned dialogue unit, It analyzes evaluation data in an interactive format and provides marketers with insights. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of evaluation data collection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Analyze the customer's past evaluation history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting evaluation data, filtering is performed based on the customer's current purchasing behavior and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates user sentiment and determines the priority of evaluation data to collect based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting evaluation data, the system prioritizes collecting highly relevant data based on the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting evaluation data, we analyze customers' social media activity and collect relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, We estimate user sentiment and adjust the trend analysis method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, the priority of analyses is determined based on when the evaluation data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned display unit is It estimates the user's emotions and adjusts how the graph is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned display unit is When displaying graphs, adjust the level of detail based on the importance of the evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned display unit is When displaying graphs, different display formats are applied depending on the category of the evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned display unit is It estimates the user's emotions and adjusts the display order of the graphs based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned display unit is When displaying graphs, the display priority is determined based on when the evaluation data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned display unit is When displaying graphs, the display order is adjusted based on the relevance of the evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned notification unit, It estimates the user's emotions and adjusts the alert notification method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned notification unit, When an alert is sent, adjust the level of detail in the notification based on the importance of the evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned notification unit, When an alert is sent, different notification algorithms are applied depending on the category of evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned notification unit, It estimates the user's emotions and prioritizes alert notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned notification unit, When an alert is sent, the notification priority is determined based on when the evaluation data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned notification unit, When alerts are sent, the order of notifications will be adjusted based on the relevance of the evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned dialogue unit, It estimates the user's emotions and adjusts the way it delivers conversational insights based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned dialogue unit, When providing insights in an interactive format, adjust the level of detail of the insights based on the importance of the evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned dialogue unit, When providing interactive insights, different insight-providing algorithms are applied depending on the category of evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned dialogue unit, It estimates the user's emotions and prioritizes the delivery of conversational insights based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned dialogue unit, When providing insights in an interactive format, the priority of insight delivery is determined based on the timing of evaluation data submission. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned dialogue unit, When providing insights in an interactive format, adjust the order of insight delivery based on the relevance of the evaluation data. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A data collection unit that aggregates customer evaluation data for products and services along a timeline, An analysis unit performs trend analysis based on the evaluation data collected by the aforementioned collection unit, A display unit that displays a graph showing the changes in evaluation data analyzed by the aforementioned analysis unit, A notification unit that issues an alert notification when an abnormal evaluation is detected by the analysis unit, The system includes a dialogue unit that provides insights in an interactive format based on the results of the analysis unit. A system characterized by the following features.

2. The aforementioned collection unit is We collect data on customer ratings and reviews of products on e-commerce sites. The system according to feature 1.

3. The aforementioned analysis unit, Analyze the collected evaluation data to understand evaluation trends. The system according to feature 1.

4. The aforementioned display unit is Visualize evaluation data and display changes in evaluation as graphs. The system according to feature 1.

5. The aforementioned notification unit, An alert will be sent in real time if an abnormal evaluation is detected. The system according to feature 1.

6. The aforementioned dialogue unit, It analyzes evaluation data in an interactive format and provides marketers with insights. The system according to feature 1.

7. The aforementioned collection unit is We estimate the user's emotions and adjust the timing of evaluation data collection based on the estimated user emotions. The system according to feature 1.

8. The aforementioned collection unit is Analyze the customer's past evaluation history and select the optimal data collection method. The system according to feature 1.

Images