system

Abstract

The system according to the embodiment aims to analyze posted comments and appropriately classify and display them according to the needs of the viewer. [Solution] A system according to an embodiment includes an analysis unit, a classification unit, and a selection unit. The analysis unit analyzes posted comments. The classification unit classifies the analyzed comments into categories. The selection unit displays the comments classified by the classification unit based on a category specified by a viewer.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to appropriately classify and display posted comments according to the needs of viewers.

[0005] The system according to the embodiment aims to analyze posted comments and appropriately classify and display them according to the needs of the viewer. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a classification unit, and a selection unit. The analysis unit analyzes posted comments. The classification unit classifies the comments analyzed by the analysis unit into categories. The selection unit displays the comments classified by the classification unit based on a category specified by a viewer. [Effects of the Invention]

[0007] The system according to the embodiment can analyze the posted comments and appropriately classify and display them according to the needs of the viewer. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A comment classification system according to an embodiment of the present invention uses a generation AI to classify posted comments into categories such as "opposition" and "approval." Viewers can then select the desired comment by specifying a category. In this comment classification system, the generation AI first analyzes posted comments and classifies them into categories such as "opposition," "approval," "badmouthing," and "rumor." Viewers then select the desired category and the comments belonging to that category are displayed. This allows viewers to efficiently read only the comments they want to read. For example, when the generation AI analyzes posted comments, it analyzes the content of the comment in detail to identify trends in emotions and opinions. For example, a comment such as "I'm disappointed in this actor's behavior" would be classified into the "opposition" category. On the other hand, a comment such as "I support this actor" would be classified into the "approval" category. Next, the generation AI classifies the comments into categories based on the analysis results. For example, the comments could be classified into categories such as "opposition," "approval," "badmouthing," and "rumor." This makes it clear what opinions and emotions are expressed in the comments. Viewers then specify the desired category. For example, by selecting the "approval" category, only comments belonging to that category are displayed. This allows viewers to efficiently read only the comments they want to read. This system allows viewers to select comments that match their interests and concerns. For example, if you want to read supportive comments about an actor's affair, you can select the "positive" category to read only the supportive comments. In addition, since "badmouthing" and "rumors" are also categorized, viewers can select those comments as well. In this way, using generative AI makes it possible to efficiently classify posted comments and realize a system that allows viewers to select comments that match their interests and concerns. This allows the comment classification system to select and read comments that match their interests and concerns efficiently.

[0029] A comment classification system according to an embodiment includes an analysis unit, a classification unit, and a selection unit. The analysis unit analyzes posted comments. For example, the analysis unit analyzes the content of the comments in detail to understand trends in emotions and opinions. The analysis unit analyzes the comments using, for example, natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, morphological analysis divides comments into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the comments to clarify relationships such as subject, predicate, and object. Semantic analysis analyzes the meaning of the comments to understand trends in emotions and opinions. The classification unit classifies the comments analyzed by the analysis unit into categories. For example, the classification unit classifies the comments into categories using machine learning. Machine learning includes supervised learning, unsupervised learning, deep learning, and the like. For example, supervised learning trains a model using pre-labeled data to classify new comments into categories. Unsupervised learning uses unlabeled data to cluster comments and identify categories. Deep learning uses a multi-layer neural network to extract features of comments and classify them into categories. The selection unit displays the comments classified by the classification unit based on categories specified by the viewer. The selection unit, for example, filters and displays comments based on the categories specified by the viewer. For example, if a viewer selects the "positive" category, the selection unit displays only comments belonging to the "positive" category. This allows the viewer to efficiently read only the comments they want to read. Furthermore, the selection unit can refer to the viewer's past browsing history to preferentially display highly relevant comments. For example, the selection unit analyzes the viewer's past browsing history and displays comments related to topics of interest. This allows the viewer to select comments based on their interests and read them efficiently. As a result, the comment classification system according to the embodiment can efficiently analyze, classify, and display posted comments.

[0030] The analysis unit can analyze the content of the comments in detail and grasp trends in emotions and opinions. For example, the analysis unit analyzes the content of the comments in detail and grasps trends in emotions and opinions. For example, the analysis unit analyzes the content of the comments in detail using text analysis techniques. Text analysis techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, morphological analysis divides the comment into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the comment and clarifies relationships such as between subject, predicate, and object. Semantic analysis analyzes the meaning of the comment and grasps trends in emotions and opinions. This enables more accurate analysis by analyzing the content of the comment in detail and grasping trends in emotions and opinions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the content of the comment into a generation AI, which then performs an analysis to grasp trends in emotions and opinions.

[0031] The classification unit can classify comments into categories such as "opposition," "positive," "badmouth," and "gossip" based on the analysis results. For example, the classification unit classifies comments into categories such as "opposition," "positive," "badmouth," and "gossip" based on the analysis results. For example, the classification unit classifies comments into categories using machine learning. Machine learning includes supervised learning, unsupervised learning, and deep learning. For example, supervised learning trains a model using pre-labeled data to classify new comments into categories. Unsupervised learning uses unlabeled data to cluster comments and identify categories. Deep learning uses a multi-layer neural network to extract features of comments and classify them into categories. This allows users to efficiently select comments they want to read by classifying them into categories such as "opposition," "positive," "badmouth," and "gossip." Some or all of the above-mentioned processing in the classification unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the classification unit can input the analysis results to a generation AI, which then performs a process of classifying comments into categories.

[0032] The selection unit can display comments based on categories specified by the viewer. For example, when the viewer selects the "positive" category, the selection unit displays only comments belonging to the "positive" category. This allows the viewer to efficiently read only the comments they want to read. Furthermore, the selection unit can refer to the viewer's past browsing history to preferentially display highly relevant comments. For example, the selection unit analyzes the viewer's past browsing history and displays comments related to topics of interest. This allows the viewer to select and efficiently read comments according to their interests and concerns. This allows the viewer to efficiently read comments they want to read by displaying comments based on the categories specified by the viewer. Some or all of the above-described processing in the selection unit may be performed using, or without, a generation AI. For example, the selection unit can input categories specified by the viewer into the generation AI, and the generation AI can execute a process of displaying comments based on the categories.

[0033] The analysis unit can analyze the comments using natural language processing technology. The analysis unit analyzes the comments using, for example, natural language processing technology. Natural language processing technology includes morphological analysis, grammatical analysis, semantic analysis, etc. For example, morphological analysis divides the comment into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the comment and clarifies the relationships between the subject, predicate, object, etc. Semantic analysis analyzes the meaning of the comment and grasps the trends of emotions and opinions. Thus, by using natural language processing technology, the accuracy of comment analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the content of the comment into a generation AI, which then executes a process of analyzing the comment using natural language processing technology.

[0034] The classification unit can classify comments into categories using machine learning. The classification unit classifies comments into categories using, for example, machine learning. Machine learning includes supervised learning, unsupervised learning, deep learning, and the like. For example, supervised learning trains a model using pre-labeled data to classify new comments into categories. Unsupervised learning uses unlabeled data to cluster comments and identify categories. Deep learning uses a multi-layer neural network to extract features of comments and classify them into categories. This improves the accuracy of comment categorization using machine learning. Some or all of the above-described processing in the classification unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the classification unit can input the analysis results to a generation AI, which then performs a process of classifying comments into categories using machine learning.

[0035] The analysis unit can improve the accuracy of the analysis based on the time period in which the comment was posted. The analysis unit improves the accuracy of the analysis, for example, by taking into account the time period in which the comment was posted. For example, the generation AI analyzes comments posted late at night by taking into account emotional fluctuations. Furthermore, the generation AI can analyze comments posted in the morning by taking into account positive emotions. Furthermore, the generation AI can analyze comments posted in the evening by taking into account feelings of fatigue. In this way, by taking into account the time period in which the comment was posted, the accuracy of the analysis is improved. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the time period in which the comment was posted into the generation AI, and the generation AI can execute processing to improve the accuracy of the analysis based on the time period.

[0036] The analysis unit can analyze the context of a comment and extract keywords related to a specific topic. The analysis unit, for example, analyzes the context of a comment and extracts keywords related to a specific topic. For example, the generation AI can analyze the context of a comment and extract keywords related to a specific topic. The generation AI can also analyze the context of a comment and identify related subtopics. Furthermore, the generation AI can analyze the context of a comment and identify related people or places. This enables more accurate analysis by analyzing the context of a comment and extracting keywords related to a specific topic. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the context of a comment to the generation AI, and the generation AI can execute a process of extracting keywords based on the context.

[0037] The analysis unit can improve the accuracy of the analysis based on the past posting history of the comment poster. The analysis unit, for example, improves the accuracy of the analysis by referring to the past posting history of the comment poster. For example, the generation AI can improve the accuracy of the analysis by referring to the past posting history of the comment poster. The generation AI can also analyze the content of the comment poster's past posts and reflect this in the analysis of the current comment. Furthermore, the generation AI can improve the accuracy of the analysis by referring to the comment poster's past emotional tendencies. In this way, the accuracy of the analysis is improved by referring to the comment poster's past posting history. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the comment poster's past posting history into the generation AI, and the generation AI can execute processing to improve the accuracy of the analysis based on the history.

[0038] The analysis unit can adjust the analysis results based on the geographic location information of the comment poster. The analysis unit, for example, adjusts the analysis results by taking into account the geographic location information of the comment poster. For example, the generation AI can take into account the geographic location information of the comment poster and reflect regional expressions in the analysis. The generation AI can also take into account the geographic location information of the comment poster and reflect regional trends in the analysis. Furthermore, the generation AI can take into account the geographic location information of the comment poster and reflect regional cultural background in the analysis. In this way, by taking into account the geographic location information of the comment poster, analysis that reflects regional expressions and trends is possible. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the geographic location information of the comment poster to the generation AI, and the generation AI can execute processing to adjust the analysis results based on the location information.

[0039] The classification unit can simultaneously classify comments into multiple categories based on their content. The classification unit, for example, simultaneously classifies comments into multiple categories based on their content. For example, the generation AI analyzes the content of the comments and classifies them into both "opposition" and "bad words." The generation AI can also analyze the content of the comments and classify them into both "approval" and "rumor." The generation AI can also analyze the content of the comments and classify them into both "opposition" and "rumor." This allows for more flexible categorization by simultaneously classifying comments into multiple categories based on their content. Some or all of the above-described processing in the classification unit may be performed using, or without, the generation AI. For example, the classification unit can input the content of the comments into the generation AI, and the generation AI can execute a process of simultaneously classifying the comments into multiple categories.

[0040] The classification unit can adjust the level of detail of a category based on the length and format of a comment. The classification unit adjusts the level of detail of a category based on, for example, the length and format of a comment. For example, the generation AI takes into account the length of a comment and classifies it into a detailed category. The generation AI can also take into account the format of a comment and classify it into a detailed category. Furthermore, the generation AI can take into account the length and format of a comment and classify it into a detailed category. In this way, adjusting the level of detail of a category based on the length and format of a comment enables more appropriate categorization. Some or all of the above-described processing in the classification unit may be performed using, or without, the generation AI. For example, the classification unit can input the length and format of a comment to the generation AI, and the generation AI can perform processing to adjust the level of detail.

[0041] The classification unit can subdivide categories based on attribute information of the comment poster. The classification unit, for example, subdivides categories taking into account attribute information of the comment poster. For example, the generation AI can subdivide categories taking into account the age of the comment poster. The generation AI can also subdivide categories taking into account the gender of the comment poster. Furthermore, the generation AI can also subdivide categories taking into account the occupation of the comment poster. This enables more detailed categorization by taking into account the attribute information of the comment poster. Some or all of the above-mentioned processing in the classification unit may be performed using, or without, the generation AI. For example, the classification unit can input attribute information of the comment poster to the generation AI, and the generation AI can execute processing to subdivide categories based on the attribute information.

[0042] The classification unit can clarify the relationship between categories based on the relevance of comments. The classification unit clarifies the relationship between categories based on, for example, the relevance of comments. For example, the generation AI analyzes the relevance of comments and clarifies the relationship between categories. The generation AI can also analyze the relevance of comments and link related categories. Furthermore, the generation AI can analyze the relevance of comments and create a hierarchical structure between categories. This enables more appropriate categorization by clarifying the relationship between categories based on the relevance of comments. Some or all of the above-described processing in the classification unit may be performed using, or without, the generation AI. For example, the classification unit can input the relevance of comments to the generation AI, and the generation AI can execute processing to clarify the relationship between categories based on the relevance.

[0043] The selection unit can display highly relevant comments by referring to the viewer's past browsing history. The selection unit can, for example, display highly relevant comments by referring to the viewer's past browsing history. For example, the generation AI can refer to the viewer's past browsing history and preferentially display relevant comments. The generation AI can also refer to the viewer's past browsing history and display comments related to topics of interest. Furthermore, the generation AI can also refer to the viewer's past browsing history and display comments based on the viewer's preference trends. In this way, more relevant comments can be displayed by referring to the viewer's past browsing history. Some or all of the above-described processing in the selection unit can be performed using, or without, the generation AI. For example, the selection unit can input the viewer's past browsing history into the generation AI, and the generation AI can execute processing to display highly relevant comments based on the history.

[0044] The selection unit can filter comments to be displayed based on the viewer's current topics of interest. The selection unit filters comments to be displayed based on, for example, the viewer's current topics of interest. For example, the generation AI can analyze the viewer's current topics of interest and prioritize displaying related comments. The generation AI can also analyze the viewer's current topics of interest and filter out unnecessary comments. Furthermore, the generation AI can analyze the viewer's current topics of interest and prioritize displaying interesting comments. In this way, by filtering comments based on the viewer's current topics of interest, more relevant comments can be displayed. Some or all of the above-described processing in the selection unit may be performed using, or without, the generation AI. For example, the selection unit can input the viewer's current topics of interest to the generation AI, and the generation AI can execute processing to filter comments based on the topics of interest.

[0045] The selection unit can prioritize displaying highly relevant comments based on the viewer's geographical location information. The selection unit, for example, can prioritize displaying highly relevant comments by taking into account the viewer's geographical location information. For example, the generation AI can prioritize displaying region-specific comments by taking into account the viewer's geographical location information. The generation AI can also prioritize displaying comments related to regional trends by taking into account the viewer's geographical location information. Furthermore, the generation AI can also display comments related to the cultural background of the region by taking into account the viewer's geographical location information. In this way, region-specific comments can be prioritized by taking into account the viewer's geographical location information. Some or all of the above-described processing in the selection unit may be performed using, or without, the generation AI. For example, the selection unit can input the viewer's geographical location information to the generation AI, and the generation AI can execute processing to display highly relevant comments based on the location information.

[0046] The selection unit can analyze the viewer's social media activity and display relevant comments. The selection unit, for example, analyzes the viewer's social media activity and displays relevant comments. For example, the generation AI can analyze the viewer's social media activity and prioritize displaying relevant comments. The generation AI can also analyze the viewer's social media activity and display comments related to topics of interest. Furthermore, the generation AI can analyze the viewer's social media activity and display comments based on the viewer's preferences. In this way, by analyzing the viewer's social media activity, more relevant comments can be displayed. Some or all of the above-described processing in the selection unit may be performed using, or without, the generation AI. For example, the selection unit can input the viewer's social media activity into the generation AI, and the generation AI can execute processing to display relevant comments based on the activity.

[0047] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0048] When analyzing the content of a comment, the analysis unit can improve the accuracy of the analysis by taking into account the context of the comment. For example, the analysis unit can analyze the context before and after the comment to more accurately understand the intent of the comment. The analysis unit can also analyze the context of the comment to extract related topics and keywords. Furthermore, the analysis unit can analyze the context of the comment to more accurately understand the sentiment and opinion trends of the comment. In this way, by taking the context of the comment into account, the analysis accuracy is improved, enabling more accurate analysis.

[0049] The classification unit can simultaneously classify comments into multiple categories based on the content of the comments. For example, the classification unit analyzes the content of the comments and classifies them into both "opposition" and "bad words." The classification unit can also analyze the content of the comments and classify them into both "approval" and "rumor." The classification unit can also analyze the content of the comments and classify them into both "opposition" and "rumor." This allows for more flexible categorization by simultaneously classifying comments into multiple categories based on the content of the comments.

[0050] The selection unit can refer to the viewer's past browsing history and preferentially display highly relevant comments. For example, the selection unit can analyze the viewer's past browsing history and display comments related to topics of interest. The selection unit can also analyze the viewer's past browsing history and display comments based on the viewer's preferences. Furthermore, the selection unit can analyze the viewer's past browsing history and preferentially display highly relevant comments. In this way, more relevant comments can be displayed by referring to the viewer's past browsing history.

[0051] The analysis unit can improve the accuracy of the analysis based on the time period in which the comments were posted. For example, comments posted late at night can be analyzed taking into account emotional fluctuations. Comments posted in the morning can also be analyzed taking into account positive emotions. Furthermore, comments posted in the evening can also be analyzed taking into account feelings of fatigue. In this way, the accuracy of the analysis can be improved by taking into account the time period in which the comments were posted.

[0052] The classification unit can adjust the level of detail of the category based on the length and format of the comment. For example, the length of the comment is taken into consideration to classify the comment into a detailed category. The classification unit can also take the format of the comment into consideration to classify the comment into a detailed category. The classification unit can also take the length and format of the comment into consideration to classify the comment into a detailed category. In this way, by adjusting the level of detail of the category based on the length and format of the comment, more appropriate categorization is possible.

[0053] The processing flow of the first embodiment will be briefly explained below.

[0054] Step 1: The analysis unit analyzes the posted comments. For example, the analysis unit analyzes the content of the comments in detail to understand the trends in emotions and opinions. The analysis unit analyzes the comments using natural language processing technology. Natural language processing technology includes morphological analysis, grammatical analysis, and semantic analysis. For example, morphological analysis divides the comments into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the comments and clarifies the relationships between subjects, predicates, objects, etc. Semantic analysis analyzes the meaning of the comments and understands the trends in emotions and opinions. Step 2: The classification unit classifies the comments analyzed by the analysis unit into categories. The classification unit classifies comments into categories using machine learning. Machine learning includes supervised learning, unsupervised learning, and deep learning. For example, supervised learning uses pre-labeled data to train a model and classify new comments into categories. Unsupervised learning uses unlabeled data to cluster comments and identify categories. Deep learning uses a multi-layer neural network to extract features of comments and classify them into categories. Step 3: The selection unit displays the comments classified by the classification unit based on the category specified by the viewer. The selection unit filters and displays the comments based on the category specified by the viewer. For example, if the viewer selects the "positive" category, the selection unit displays only comments that belong to the "positive" category. Furthermore, the selection unit can refer to the viewer's past browsing history to prioritize the display of highly relevant comments. For example, the selection unit analyzes the viewer's past browsing history and displays comments related to topics of interest.

[0055] (Example 2) A comment classification system according to an embodiment of the present invention uses a generation AI to classify posted comments into categories such as "opposition" and "approval." Viewers can then select the desired comment by specifying a category. In this comment classification system, the generation AI first analyzes posted comments and classifies them into categories such as "opposition," "approval," "badmouthing," and "rumor." Viewers then select the desired category and the comments belonging to that category are displayed. This allows viewers to efficiently read only the comments they want to read. For example, when the generation AI analyzes posted comments, it analyzes the content of the comment in detail to identify trends in emotions and opinions. For example, a comment such as "I'm disappointed in this actor's behavior" would be classified into the "opposition" category. On the other hand, a comment such as "I support this actor" would be classified into the "approval" category. Next, the generation AI classifies the comments into categories based on the analysis results. For example, the comments could be classified into categories such as "opposition," "approval," "badmouthing," and "rumor." This makes it clear what opinions and emotions are expressed in the comments. Viewers then specify the desired category. For example, by selecting the "approval" category, only comments belonging to that category are displayed. This allows viewers to efficiently read only the comments they want to read. This system allows viewers to select comments that match their interests and concerns. For example, if you want to read supportive comments about an actor's affair, you can select the "positive" category to read only the supportive comments. In addition, since "badmouthing" and "rumors" are also categorized, viewers can select those comments as well. In this way, using generative AI makes it possible to efficiently classify posted comments and realize a system that allows viewers to select comments that match their interests and concerns. This allows the comment classification system to select and read comments that match their interests and concerns efficiently.

[0056] A comment classification system according to an embodiment includes an analysis unit, a classification unit, and a selection unit. The analysis unit analyzes posted comments. For example, the analysis unit analyzes the content of the comments in detail to understand trends in emotions and opinions. The analysis unit analyzes the comments using, for example, natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, morphological analysis divides comments into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the comments to clarify relationships such as subject, predicate, and object. Semantic analysis analyzes the meaning of the comments to understand trends in emotions and opinions. The classification unit classifies the comments analyzed by the analysis unit into categories. For example, the classification unit classifies the comments into categories using machine learning. Machine learning includes supervised learning, unsupervised learning, deep learning, and the like. For example, supervised learning trains a model using pre-labeled data to classify new comments into categories. Unsupervised learning uses unlabeled data to cluster comments and identify categories. Deep learning uses a multi-layer neural network to extract features of comments and classify them into categories. The selection unit displays the comments classified by the classification unit based on categories specified by the viewer. The selection unit, for example, filters and displays comments based on the categories specified by the viewer. For example, if a viewer selects the "positive" category, the selection unit displays only comments belonging to the "positive" category. This allows the viewer to efficiently read only the comments they want to read. Furthermore, the selection unit can refer to the viewer's past browsing history to preferentially display highly relevant comments. For example, the selection unit analyzes the viewer's past browsing history and displays comments related to topics of interest. This allows the viewer to select comments based on their interests and read them efficiently. As a result, the comment classification system according to the embodiment can efficiently analyze, classify, and display posted comments.

[0057] The analysis unit can analyze the content of the comments in detail and grasp trends in emotions and opinions. For example, the analysis unit analyzes the content of the comments in detail and grasps trends in emotions and opinions. For example, the analysis unit analyzes the content of the comments in detail using text analysis techniques. Text analysis techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, morphological analysis divides the comment into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the comment and clarifies relationships such as between subject, predicate, and object. Semantic analysis analyzes the meaning of the comment and grasps trends in emotions and opinions. This enables more accurate analysis by analyzing the content of the comment in detail and grasping trends in emotions and opinions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the content of the comment into a generation AI, which then performs an analysis to grasp trends in emotions and opinions.

[0058] The classification unit can classify comments into categories such as "opposition," "positive," "badmouth," and "gossip" based on the analysis results. For example, the classification unit classifies comments into categories such as "opposition," "positive," "badmouth," and "gossip" based on the analysis results. For example, the classification unit classifies comments into categories using machine learning. Machine learning includes supervised learning, unsupervised learning, and deep learning. For example, supervised learning trains a model using pre-labeled data to classify new comments into categories. Unsupervised learning uses unlabeled data to cluster comments and identify categories. Deep learning uses a multi-layer neural network to extract features of comments and classify them into categories. This allows users to efficiently select comments they want to read by classifying them into categories such as "opposition," "positive," "badmouth," and "gossip." Some or all of the above-mentioned processing in the classification unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the classification unit can input the analysis results to a generation AI, which then performs a process of classifying comments into categories.

[0059] The selection unit can display comments based on categories specified by the viewer. For example, when the viewer selects the "positive" category, the selection unit displays only comments belonging to the "positive" category. This allows the viewer to efficiently read only the comments they want to read. Furthermore, the selection unit can refer to the viewer's past browsing history to preferentially display highly relevant comments. For example, the selection unit analyzes the viewer's past browsing history and displays comments related to topics of interest. This allows the viewer to select and efficiently read comments according to their interests and concerns. This allows the viewer to efficiently read comments they want to read by displaying comments based on the categories specified by the viewer. Some or all of the above-described processing in the selection unit may be performed using, or without, a generation AI. For example, the selection unit can input categories specified by the viewer into the generation AI, and the generation AI can execute a process of displaying comments based on the categories.

[0060] The analysis unit can analyze the comments using natural language processing technology. The analysis unit analyzes the comments using, for example, natural language processing technology. Natural language processing technology includes morphological analysis, grammatical analysis, semantic analysis, etc. For example, morphological analysis divides the comment into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the comment and clarifies the relationships between the subject, predicate, object, etc. Semantic analysis analyzes the meaning of the comment and grasps the trends of emotions and opinions. Thus, by using natural language processing technology, the accuracy of comment analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the content of the comment into a generation AI, which then executes a process of analyzing the comment using natural language processing technology.

[0061] The classification unit can classify comments into categories using machine learning. The classification unit classifies comments into categories using, for example, machine learning. Machine learning includes supervised learning, unsupervised learning, deep learning, and the like. For example, supervised learning trains a model using pre-labeled data to classify new comments into categories. Unsupervised learning uses unlabeled data to cluster comments and identify categories. Deep learning uses a multi-layer neural network to extract features of comments and classify them into categories. This improves the accuracy of comment categorization using machine learning. Some or all of the above-described processing in the classification unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the classification unit can input the analysis results to a generation AI, which then performs a process of classifying comments into categories using machine learning.

[0062] The analysis unit can estimate the emotion of the comment poster and adjust the comment analysis method based on the estimated emotion. For example, the analysis unit can estimate the emotion of the comment poster and adjust the comment analysis method based on the estimated emotion. For example, if the comment poster is angry, the generation AI can take the emotion into consideration and apply an analysis method that emphasizes expressions of anger. Also, if the comment poster is sad, the generation AI can take the emotion into consideration and apply an analysis method that emphasizes expressions of sadness. Furthermore, if the comment poster is happy, the generation AI can take the emotion into consideration and apply an analysis method that emphasizes expressions of joy. This allows for more appropriate analysis by adjusting the analysis method based on the emotion of the comment poster. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, the generation AI, or without the generation AI. For example, the analysis unit can input the emotion of the comment poster into the generation AI, and the generation AI can adjust the analysis method based on the emotion.

[0063] The analysis unit can improve the accuracy of the analysis based on the time period in which the comment was posted. The analysis unit improves the accuracy of the analysis, for example, by taking into account the time period in which the comment was posted. For example, the generation AI analyzes comments posted late at night by taking into account emotional fluctuations. Furthermore, the generation AI can analyze comments posted in the morning by taking into account positive emotions. Furthermore, the generation AI can analyze comments posted in the evening by taking into account feelings of fatigue. In this way, by taking into account the time period in which the comment was posted, the accuracy of the analysis is improved. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the time period in which the comment was posted into the generation AI, and the generation AI can execute processing to improve the accuracy of the analysis based on the time period.

[0064] The analysis unit can analyze the context of a comment and extract keywords related to a specific topic. The analysis unit, for example, analyzes the context of a comment and extracts keywords related to a specific topic. For example, the generation AI can analyze the context of a comment and extract keywords related to a specific topic. The generation AI can also analyze the context of a comment and identify related subtopics. Furthermore, the generation AI can analyze the context of a comment and identify related people or places. This enables more accurate analysis by analyzing the context of a comment and extracting keywords related to a specific topic. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the context of a comment to the generation AI, and the generation AI can execute a process of extracting keywords based on the context.

[0065] The analysis unit can estimate the emotion of a comment poster and prioritize the analysis results based on the estimated emotion. For example, the analysis unit can estimate the emotion of a comment poster and prioritize the analysis results based on the estimated emotion. For example, if a comment poster has strong emotion, the analysis unit prioritizes that comment. Also, if a comment poster has neutral emotion, the analysis unit can postpone that comment. Furthermore, if a comment poster has positive emotion, the analysis unit can prioritize that comment. Thus, by prioritizing the analysis results based on the emotion of the comment poster, more important comments can be prioritized for analysis. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, the generation AI. For example, the analysis unit can input the emotion of a comment poster into the generation AI, and the generation AI can prioritize the analysis results based on the emotion.

[0066] The analysis unit can improve the accuracy of the analysis based on the past posting history of the comment poster. The analysis unit, for example, improves the accuracy of the analysis by referring to the past posting history of the comment poster. For example, the generation AI can improve the accuracy of the analysis by referring to the past posting history of the comment poster. The generation AI can also analyze the content of the comment poster's past posts and reflect this in the analysis of the current comment. Furthermore, the generation AI can improve the accuracy of the analysis by referring to the comment poster's past emotional tendencies. In this way, the accuracy of the analysis is improved by referring to the comment poster's past posting history. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the comment poster's past posting history into the generation AI, and the generation AI can execute processing to improve the accuracy of the analysis based on the history.

[0067] The analysis unit can adjust the analysis results based on the geographic location information of the comment poster. The analysis unit, for example, adjusts the analysis results by taking into account the geographic location information of the comment poster. For example, the generation AI can take into account the geographic location information of the comment poster and reflect regional expressions in the analysis. The generation AI can also take into account the geographic location information of the comment poster and reflect regional trends in the analysis. Furthermore, the generation AI can take into account the geographic location information of the comment poster and reflect regional cultural background in the analysis. In this way, by taking into account the geographic location information of the comment poster, analysis that reflects regional expressions and trends is possible. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the geographic location information of the comment poster to the generation AI, and the generation AI can execute processing to adjust the analysis results based on the location information.

[0068] The classification unit can estimate the emotion of a comment poster and adjust the category of a comment based on the estimated emotion. For example, the classification unit can estimate the emotion of a comment poster and adjust the category of a comment based on the estimated emotion. For example, if a comment poster is angry, the classification unit can categorize the comment into an "opposition" category. Also, if a comment poster is happy, the classification unit can categorize the comment into a "positive" category. Furthermore, if a comment poster is sad, the classification unit can categorize the comment into a "bad" category. This allows for more appropriate categorization by adjusting the category based on the emotion of the comment poster. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the classification unit can be performed using, for example, the generation AI. For example, the classification unit can input the emotion of a comment poster into the generation AI, and the generation AI can adjust the category based on the emotion.

[0069] The classification unit can simultaneously classify comments into multiple categories based on their content. The classification unit, for example, simultaneously classifies comments into multiple categories based on their content. For example, the generation AI analyzes the content of the comments and classifies them into both "opposition" and "bad words." The generation AI can also analyze the content of the comments and classify them into both "approval" and "rumor." The generation AI can also analyze the content of the comments and classify them into both "opposition" and "rumor." This allows for more flexible categorization by simultaneously classifying comments into multiple categories based on their content. Some or all of the above-described processing in the classification unit may be performed using, or without, the generation AI. For example, the classification unit can input the content of the comments into the generation AI, and the generation AI can execute a process of simultaneously classifying the comments into multiple categories.

[0070] The classification unit can adjust the level of detail of a category based on the length and format of a comment. The classification unit adjusts the level of detail of a category based on, for example, the length and format of a comment. For example, the generation AI takes into account the length of a comment and classifies it into a detailed category. The generation AI can also take into account the format of a comment and classify it into a detailed category. Furthermore, the generation AI can take into account the length and format of a comment and classify it into a detailed category. In this way, adjusting the level of detail of a category based on the length and format of a comment enables more appropriate categorization. Some or all of the above-described processing in the classification unit may be performed using, or without, the generation AI. For example, the classification unit can input the length and format of a comment to the generation AI, and the generation AI can perform processing to adjust the level of detail.

[0071] The classification unit can estimate the emotion of a comment poster and adjust the display order of categories based on the estimated emotion. The classification unit, for example, estimates the emotion of a comment poster and adjusts the display order of categories based on the estimated emotion. For example, if a comment poster has strong emotion, the classification unit can prioritize displaying that category. Also, if a comment poster has neutral emotion, the classification unit can prioritize displaying that category. Furthermore, if a comment poster has positive emotion, the classification unit can prioritize displaying that category. In this way, by adjusting the display order of categories based on the emotion of the comment poster, the categories can be displayed in a more appropriate order. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the classification unit can be performed using, for example, the generation AI. For example, the classification unit can input the emotion of a comment poster into the generation AI, and the generation AI can adjust the display order of categories based on the emotion.

[0072] The classification unit can subdivide categories based on attribute information of the comment poster. The classification unit, for example, subdivides categories taking into account attribute information of the comment poster. For example, the generation AI can subdivide categories taking into account the age of the comment poster. The generation AI can also subdivide categories taking into account the gender of the comment poster. Furthermore, the generation AI can also subdivide categories taking into account the occupation of the comment poster. This enables more detailed categorization by taking into account the attribute information of the comment poster. Some or all of the above-mentioned processing in the classification unit may be performed using, or without, the generation AI. For example, the classification unit can input attribute information of the comment poster to the generation AI, and the generation AI can execute processing to subdivide categories based on the attribute information.

[0073] The classification unit can clarify the relationship between categories based on the relevance of comments. The classification unit clarifies the relationship between categories based on, for example, the relevance of comments. For example, the generation AI analyzes the relevance of comments and clarifies the relationship between categories. The generation AI can also analyze the relevance of comments and link related categories. Furthermore, the generation AI can analyze the relevance of comments and create a hierarchical structure between categories. This enables more appropriate categorization by clarifying the relationship between categories based on the relevance of comments. Some or all of the above-described processing in the classification unit may be performed using, or without, the generation AI. For example, the classification unit can input the relevance of comments to the generation AI, and the generation AI can execute processing to clarify the relationship between categories based on the relevance.

[0074] The selection unit can estimate the viewer's emotions and adjust the order of comments to be displayed based on the estimated emotions. The selection unit, for example, estimates the viewer's emotions and adjusts the order of comments to be displayed based on the estimated emotions. For example, if the viewer is angry, the generation AI can take the viewer's emotions into consideration and prioritize displaying comments that will alleviate the anger. Also, if the viewer is sad, the generation AI can take the viewer's emotions into consideration and prioritize displaying comforting comments. Furthermore, if the viewer is happy, the generation AI can take the viewer's emotions into consideration and prioritize displaying sympathetic comments. This allows the comments to be displayed in a more appropriate order by adjusting the order of comments to be displayed based on the viewer's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the selection unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the selection unit can input the viewer's emotions into the generation AI and execute a process in which the generation AI adjusts the order of comments to be displayed based on the emotions.

[0075] The selection unit can display highly relevant comments by referring to the viewer's past browsing history. The selection unit can, for example, display highly relevant comments by referring to the viewer's past browsing history. For example, the generation AI can refer to the viewer's past browsing history and preferentially display relevant comments. The generation AI can also refer to the viewer's past browsing history and display comments related to topics of interest. Furthermore, the generation AI can also refer to the viewer's past browsing history and display comments based on the viewer's preference trends. In this way, more relevant comments can be displayed by referring to the viewer's past browsing history. Some or all of the above-described processing in the selection unit can be performed using, or without, the generation AI. For example, the selection unit can input the viewer's past browsing history into the generation AI, and the generation AI can execute processing to display highly relevant comments based on the history.

[0076] The selection unit can filter comments to be displayed based on the viewer's current topics of interest. The selection unit filters comments to be displayed based on, for example, the viewer's current topics of interest. For example, the generation AI can analyze the viewer's current topics of interest and prioritize displaying related comments. The generation AI can also analyze the viewer's current topics of interest and filter out unnecessary comments. Furthermore, the generation AI can analyze the viewer's current topics of interest and prioritize displaying interesting comments. In this way, by filtering comments based on the viewer's current topics of interest, more relevant comments can be displayed. Some or all of the above-described processing in the selection unit may be performed using, or without, the generation AI. For example, the selection unit can input the viewer's current topics of interest to the generation AI, and the generation AI can execute processing to filter comments based on the topics of interest.

[0077] The selection unit can estimate the viewer's emotions and determine the priority of comments to be displayed based on the estimated emotions. The selection unit, for example, estimates the viewer's emotions and determines the priority of comments to be displayed based on the estimated emotions. For example, if the viewer is angry, the generation AI can take the viewer's emotions into consideration and prioritize comments that will alleviate the anger. Also, if the viewer is sad, the generation AI can take the viewer's emotions into consideration and prioritize comments that will comfort the viewer. Furthermore, if the viewer is happy, the generation AI can take the viewer's emotions into consideration and prioritize comments that empathize with the viewer. This allows the comments to be displayed in a more appropriate order by determining the priority of comments to be displayed based on the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the selection unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the selection unit can input the viewer's emotions into the generation AI and execute a process in which the generation AI determines the priority of comments to be displayed based on the emotions.

[0078] The selection unit can prioritize displaying highly relevant comments based on the viewer's geographical location information. The selection unit, for example, can prioritize displaying highly relevant comments by taking into account the viewer's geographical location information. For example, the generation AI can prioritize displaying region-specific comments by taking into account the viewer's geographical location information. The generation AI can also prioritize displaying comments related to regional trends by taking into account the viewer's geographical location information. Furthermore, the generation AI can also display comments related to the cultural background of the region by taking into account the viewer's geographical location information. In this way, region-specific comments can be prioritized by taking into account the viewer's geographical location information. Some or all of the above-described processing in the selection unit may be performed using, or without, the generation AI. For example, the selection unit can input the viewer's geographical location information to the generation AI, and the generation AI can execute processing to display highly relevant comments based on the location information.

[0079] The selection unit can analyze the viewer's social media activity and display relevant comments. The selection unit, for example, analyzes the viewer's social media activity and displays relevant comments. For example, the generation AI can analyze the viewer's social media activity and prioritize displaying relevant comments. The generation AI can also analyze the viewer's social media activity and display comments related to topics of interest. Furthermore, the generation AI can analyze the viewer's social media activity and display comments based on the viewer's preferences. In this way, by analyzing the viewer's social media activity, more relevant comments can be displayed. Some or all of the above-described processing in the selection unit may be performed using, or without, the generation AI. For example, the selection unit can input the viewer's social media activity into the generation AI, and the generation AI can execute processing to display relevant comments based on the activity. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, classification unit, and selection unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The classification unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The selection unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, classification unit, and selection unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The classification unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The selection unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, classification unit, and selection unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The classification unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The selection unit is realized, for example, by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, classification unit, and selection unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The classification unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The selection unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12.

[0080] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0081] When analyzing the content of a comment, the analysis unit can improve the accuracy of the analysis by taking into account the context of the comment. For example, the analysis unit can analyze the context before and after the comment to more accurately understand the intent of the comment. The analysis unit can also analyze the context of the comment to extract related topics and keywords. Furthermore, the analysis unit can analyze the context of the comment to more accurately understand the sentiment and opinion trends of the comment. In this way, by taking the context of the comment into account, the analysis accuracy is improved, enabling more accurate analysis.

[0082] The classification unit can simultaneously classify comments into multiple categories based on the content of the comments. For example, the classification unit analyzes the content of the comments and classifies them into both "opposition" and "bad words." The classification unit can also analyze the content of the comments and classify them into both "approval" and "rumor." The classification unit can also analyze the content of the comments and classify them into both "opposition" and "rumor." This allows for more flexible categorization by simultaneously classifying comments into multiple categories based on the content of the comments.

[0083] The selection unit can refer to the viewer's past browsing history and preferentially display highly relevant comments. For example, the selection unit can analyze the viewer's past browsing history and display comments related to topics of interest. The selection unit can also analyze the viewer's past browsing history and display comments based on the viewer's preferences. Furthermore, the selection unit can analyze the viewer's past browsing history and preferentially display highly relevant comments. In this way, more relevant comments can be displayed by referring to the viewer's past browsing history.

[0084] The analysis unit can improve the accuracy of the analysis based on the time period in which the comments were posted. For example, comments posted late at night can be analyzed taking into account emotional fluctuations. Comments posted in the morning can also be analyzed taking into account positive emotions. Furthermore, comments posted in the evening can also be analyzed taking into account feelings of fatigue. In this way, the accuracy of the analysis can be improved by taking into account the time period in which the comments were posted.

[0085] The classification unit can adjust the level of detail of the category based on the length and format of the comment. For example, the length of the comment is taken into consideration to classify the comment into a detailed category. The classification unit can also take the format of the comment into consideration to classify the comment into a detailed category. The classification unit can also take the length and format of the comment into consideration to classify the comment into a detailed category. In this way, by adjusting the level of detail of the category based on the length and format of the comment, more appropriate categorization is possible.

[0086] The analysis unit can estimate the emotion of the comment poster and adjust the comment analysis method based on the estimated emotion. For example, if the comment poster is angry, an analysis method that emphasizes expressions of anger can be applied. If the comment poster is sad, an analysis method that emphasizes expressions of sadness can be applied. Furthermore, if the comment poster is happy, an analysis method that emphasizes expressions of joy can be applied. In this way, by adjusting the analysis method based on the emotion of the comment poster, more appropriate analysis is possible.

[0087] The classification unit can estimate the emotion of the comment poster and adjust the category of the comment based on the estimated emotion. For example, if the comment poster is angry, the comment can be classified into the "opposition" category. If the comment poster is happy, the comment can be classified into the "positive" category. Furthermore, if the comment poster is sad, the comment can be classified into the "bad" category. In this way, adjusting the category based on the emotion of the comment poster allows for more appropriate categorization.

[0088] The selection unit can estimate the viewer's emotions and adjust the order of comments to be displayed based on the estimated emotions. For example, if the viewer is angry, comments that alleviate the anger can be displayed preferentially. Also, if the viewer is sad, comments that comfort the viewer can be displayed preferentially. Furthermore, if the viewer is happy, comments that express sympathy can be displayed preferentially. In this way, by adjusting the order of comments to be displayed based on the viewer's emotions, comments can be displayed in a more appropriate order.

[0089] The selection unit can estimate the viewer's emotions and determine the priority of comments to be displayed based on the estimated emotions. For example, if the viewer is angry, comments that alleviate the anger can be displayed preferentially. Also, if the viewer is sad, comments that comfort the viewer can be displayed preferentially. Furthermore, if the viewer is happy, comments that express sympathy can be displayed preferentially. In this way, by determining the priority of comments to be displayed based on the viewer's emotions, comments can be displayed in a more appropriate order.

[0090] The analysis unit can estimate the emotions of the comment poster and prioritize the analysis results based on the estimated emotions. For example, if the comment poster has strong emotions, the analysis of that comment can be prioritized. Also, if the comment poster has neutral emotions, the analysis of that comment can be postponed. Furthermore, if the comment poster has positive emotions, the analysis of that comment can be prioritized. In this way, by prioritizing the analysis results based on the emotions of the comment poster, more important comments can be analyzed preferentially.

[0091] The processing flow of the second embodiment will be briefly explained below.

[0092] Step 1: The analysis unit analyzes the posted comments. For example, the analysis unit analyzes the content of the comments in detail to understand the trends in emotions and opinions. The analysis unit analyzes the comments using natural language processing technology. Natural language processing technology includes morphological analysis, grammatical analysis, and semantic analysis. For example, morphological analysis divides the comments into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the comments and clarifies the relationships between subjects, predicates, objects, etc. Semantic analysis analyzes the meaning of the comments and understands the trends in emotions and opinions. Step 2: The classification unit classifies the comments analyzed by the analysis unit into categories. The classification unit classifies comments into categories using machine learning. Machine learning includes supervised learning, unsupervised learning, and deep learning. For example, supervised learning uses pre-labeled data to train a model and classify new comments into categories. Unsupervised learning uses unlabeled data to cluster comments and identify categories. Deep learning uses a multi-layer neural network to extract features of comments and classify them into categories. Step 3: The selection unit displays the comments classified by the classification unit based on the category specified by the viewer. The selection unit filters and displays the comments based on the category specified by the viewer. For example, if the viewer selects the "positive" category, the selection unit displays only comments that belong to the "positive" category. Furthermore, the selection unit can refer to the viewer's past browsing history to prioritize the display of highly relevant comments. For example, the selection unit analyzes the viewer's past browsing history and displays comments related to topics of interest.

[0093] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0094] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0095] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0096] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0097] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0098] 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.

[0099] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0100] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0101] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0102] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0103] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0104] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0105] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0106] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0107] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0108] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0109] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0110] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0111] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0112] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0113] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0114] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0115] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0116] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0117] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0119] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0120] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0121] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0122] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0123] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0124] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0125] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0127] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0128] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0129] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0130] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0131] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0132] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0133] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0135] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0136] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0137] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0138] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0140] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0141] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0142] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0143] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0144] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0145] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0146] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0147] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0148] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0149] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0150] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0151] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0152] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0153] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0154] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0155] 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.

[0156] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0157] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0158] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0159] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0160] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0161] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0162] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0163] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0164] [Explanation of symbols]

[0165] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes the posted comments; a classification unit that classifies the comments analyzed by the analysis unit into categories; a selection unit that displays the comments classified by the classification unit based on a category designated by a viewer; Equipped with A system characterized by:

2. The analysis unit Analyze comments in detail to understand trends in sentiment and opinions 2. The system of claim 1.

3. The system of claim 1 , wherein the classifier classifies comments into categories of negative, positive, negative, and gossip based on the analysis results.

4. The selection unit Display comments based on the category you specify 2. The system of claim 1.

5. The analysis unit Analyzing comments using natural language processing technology 2. The system of claim 1.

6. The classification unit Classifying comments into categories using machine learning 2. The system of claim 1.

7. The analysis unit Estimate the sentiment of the commenter and adjust how the comment is parsed based on that sentiment 2. The system of claim 1.

8. The system according to claim 1 , wherein the analysis unit improves the accuracy of the analysis based on the time period in which the comment was posted.

Images