system

Abstract

An object of a system according to an embodiment is to extract useful information from a large amount of review information and provide the information to a consumer.SOLUTION: A system according to an embodiment includes a review collector, an analyzer, a generation summarizer, and a score card generator. The review collecting unit centrally collects a plurality of reviews posted on the major EC site by utilizing the generated AI. The analysis unit analyzes the reviews collected by the review collection unit. The generation summarization unit creates a generation summary based on the content of the review analyzed by the analysis unit. The score card generating unit generates a score card based on the summary generated by the generating / summarizing unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of making it difficult to efficiently extract useful information from a large amount of review information and provide it to consumers.

[0005] The system according to the embodiment aims to extract useful information from a large amount of review information and provide it to consumers. [Means for solving the problem]

[0006] The system according to the embodiment includes a review collection unit, an analysis unit, a summarization unit, and a scorecard generation unit. The review collection unit centrally collects multiple reviews posted on major e-commerce sites using a generation AI. The analysis unit analyzes the reviews collected by the review collection unit. The summarization unit creates a summary based on the content of the review analyzed by the analysis unit. The scorecard generation unit generates a scorecard based on the summary generated by the summarization unit. [Effects of the Invention]

[0007] The system according to the embodiment can extract useful information from a large amount of review information and provide it to consumers. [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 review analysis system according to an embodiment of the present invention utilizes a generation AI to centrally collect and analyze a large number of reviews posted on major e-commerce sites, enabling consumers to quickly obtain useful information. As a result, the review analysis system can significantly reduce the effort and time it takes for consumers to find useful information from reviews.

[0029] A review analysis system according to an embodiment includes a review collection unit, an analysis unit, a generation / summarization unit, and a scorecard generation unit. The review collection unit centrally collects multiple reviews posted on major e-commerce sites using a generation AI. For example, the review collection unit collects reviews from e-commerce sites such as Amazon and Rakuten. The review collection unit can also analyze the review poster's past review history to prioritize collection of highly reliable reviews. For example, the review collection unit can prioritize analysis of reviews posted by posters who have received high ratings in the past. The review collection unit can also analyze the time period and frequency of reviews posted to understand trends in reviews posted during specific time periods. For example, the review collection unit can analyze whether reviews posted at night tend to be more positive. The analysis unit analyzes the reviews collected by the review collection unit. For example, the analysis unit uses an emotion estimation function to analyze the emotional tone of the reviews and classify them into positive and negative reviews. The analysis unit can also analyze image and video reviews and combine them with text reviews to perform a comprehensive evaluation. For example, the analysis unit can analyze images and videos showing the product's user experience. The summarization unit generates summaries based on the review content analyzed by the analysis unit. For example, the AI ​​generation unit understands the context of the review and generates summaries that include comparative information with other related products. The summarization unit can also extract frequently occurring phrases and keywords from reviews and create summaries based on them. For example, keywords such as "screen quality" and "battery life" are extracted. The scorecard generation unit generates a scorecard based on the summaries generated by the summaries. For example, the scorecard generation unit displays average scores for major evaluation items such as product quality, cost performance, and durability. The scorecard generation unit can also analyze detailed evaluation items in reviews and display sub-scores for each item. For example, evaluation items such as "screen quality" and "battery life" are displayed sub-scored. This allows the review analysis system according to the embodiment to quickly obtain useful information. For example, consumers no longer need to read a large number of reviews one by one, and can quickly make purchasing decisions by referring to the summarized information and the scorecard.

[0030] The review collection unit can analyze the poster's past review history and prioritize collecting highly reliable reviews. For example, the review collection unit uses a generation AI to analyze the poster's past review history and prioritize collecting highly reliable reviews. For example, it prioritizes analyzing reviews by posters who have received high ratings in the past. The review collection unit also builds a system that automatically filters out highly reliable reviews based on the poster's past review history. For example, it prioritizes reviews by posters who have received many "helpful" ratings in the past. The review collection unit also uses a generation AI to analyze the poster's past review history and exclude less reliable reviews. For example, it excludes reviews by posters who have a history of posting false information in the past. This allows highly reliable reviews to be collected preferentially.

[0031] The review collection unit analyzes the time and frequency of reviews posted, and can grasp trends in reviews posted during specific time periods. For example, the review collection unit uses a generation AI to analyze the time of review posting and grasp trends in reviews posted during specific time periods. For example, it analyzes whether reviews posted at night tend to be positive. The review collection unit also analyzes posting frequency and builds a system to grasp trends in frequently posted reviews. For example, if there are many reviews posted on weekends, it analyzes this trend. The review collection unit also uses a generation AI to analyze the time and frequency of posting and evaluate the reliability of reviews posted during specific time periods. For example, if reviews posted late at night are considered to be unreliable, it grasps this tendency. This makes it possible to grasp trends in reviews posted during specific time periods.

[0032] The review collection unit can collect reviews from different e-commerce sites and integrate and analyze reviews from multiple platforms. For example, the review collection unit uses a generation AI to collect reviews from different e-commerce sites and integrate and analyze reviews from multiple platforms. For example, it centrally collects reviews from sites such as Amazon and Rakuten. The review collection unit also integrates reviews collected from different e-commerce sites and builds a system for comprehensive evaluation. For example, it integrates reviews from each site to evaluate products. The review collection unit also uses a generation AI to collect reviews from different e-commerce sites and analyze review trends for each platform. For example, it analyzes whether reviews on a particular site tend to be positive. This allows reviews from multiple platforms to be integrated and analyzed.

[0033] The analysis unit can also analyze image or video reviews and combine them with text reviews to form a comprehensive evaluation. For example, the analysis unit uses a generation AI to analyze image or video reviews and combine them with text reviews to form a comprehensive evaluation. For example, it analyzes images and videos that show the product's usability. The analysis unit also uses image recognition technology to build a system that analyzes the content of image reviews and integrates them with text reviews. For example, it analyzes images that show the product's appearance and how to use it. The analysis unit also uses video analysis technology to analyze the content of video reviews and integrate them with text reviews. For example, it analyzes videos that show the product's usage and performance. This allows image and video reviews to be analyzed and a comprehensive evaluation to be formed.

[0034] The summary generating unit can understand the context of the review and generate a summary that includes comparative information with other related products. For example, the summary generating unit uses a generation AI to understand the context of the review and generate a summary that includes comparative information with other related products. For example, it generates a summary that compares with other products in the same category. The summary generating unit also builds a system that analyzes the context of the review and automatically collects information about related products to reflect in the summary. For example, it generates a summary that includes comparative information with competing products. The summary generating unit also uses a generation AI to understand the context of the review and generate a summary that includes comparative information with other related products. For example, it generates a summary that includes comparative information on price and performance. This makes it possible to generate a summary that includes comparative information with other related products.

[0035] The summarization unit can extract phrases and keywords that appear frequently in reviews and create summaries based on them. For example, the summarization unit uses a generation AI to extract phrases and keywords that appear frequently in reviews and create summaries based on them. For example, it extracts keywords such as "screen quality" and "battery life." The summarization unit can also automatically extract phrases and keywords that appear frequently in reviews and build a system that creates summaries based on them. For example, it can extract positive and negative phrases. The summarization unit can also extract phrases and keywords that appear frequently in reviews and create summaries based on them. For example, it can extract keywords such as "usability" and "design." This makes it possible to create summaries based on frequently appearing phrases and keywords.

[0036] The summarization unit can automatically translate reviews in different languages ​​and generate summaries that support multiple languages. For example, the summarization unit uses a generation AI to automatically translate reviews in different languages ​​and generate summaries that support multiple languages. For example, it translates reviews in English, French, Chinese, etc. to create summaries. The summarization unit also uses machine translation technology to build a system that translates reviews in different languages ​​and generates summaries that support multiple languages. For example, it integrates reviews in each language to create summaries. The summarization unit also uses a generation AI to automatically translate reviews in different languages ​​and generate summaries that support multiple languages. For example, it translates reviews in Spanish and German to create summaries. This makes it possible to generate summaries that support multiple languages.

[0037] The generating summary unit can visualize the review summary and display it in a graph or chart. For example, the generating AI can visualize the review summary and display it in a graph or chart. For example, the score for each evaluation item can be displayed in a bar graph or pie chart. The generating summary unit can also visualize the content of the summarized review, building a system that allows users to intuitively understand it. For example, the score for each evaluation item can be displayed in a chart. The generating summary unit can also visualize the review summary and display it in a graph or chart. For example, the ratio of positive reviews to negative reviews can be displayed in a pie chart. This allows the summary to be visualized and displayed in a graph or chart.

[0038] The scorecard generation unit can analyze the detailed evaluation items of a review and display a score for each item in a more detailed manner. For example, the generation AI in the scorecard generation unit analyzes the detailed evaluation items of a review and displays a score for each item in a more detailed manner. For example, evaluation items such as "screen quality" and "battery life" are displayed in a more detailed manner. The scorecard generation unit also builds a system that analyzes the detailed evaluation items and displays a score for each item in a more detailed manner. For example, the score for each evaluation item is displayed in a bar graph or chart. The scorecard generation unit can also analyze the detailed evaluation items of a review and display a score for each item in a more detailed manner. For example, evaluation items such as "operability" and "design" are displayed in a more detailed manner. This allows the generation AI to analyze the detailed evaluation items and display a score for each item in a more detailed manner.

[0039] The scorecard generation unit is able to generate a highly reliable score by taking into account the expertise and experience of the review poster. For example, the generation AI in the scorecard generation unit generates a highly reliable score by taking into account the expertise and experience of the review poster. For example, it prioritizes analysis of reviews by posters with specialized knowledge. The scorecard generation unit also builds a system that generates a highly reliable score based on the poster's expertise and experience. For example, it prioritizes analysis of reviews by experts. The scorecard generation unit also builds a system that generates a highly reliable score by taking into account the expertise and experience of the review poster. For example, it prioritizes analysis of reviews by posters with many years of experience. This makes it possible to generate a highly reliable score.

[0040] The scorecard generation unit can compare scorecards from different product categories and perform a comprehensive evaluation. In the scorecard generation unit, for example, a generation AI compares scorecards from different product categories and performs a comprehensive evaluation. For example, a comprehensive evaluation is performed by comparing scorecards from smartphones and tablets. The scorecard generation unit also builds a system that compares scorecards from different product categories and performs a comprehensive evaluation. For example, a comprehensive evaluation is performed by comparing scorecards from home appliances and gadgets. The scorecard generation unit also builds a system that compares scorecards from different product categories and performs a comprehensive evaluation. For example, a comprehensive evaluation is performed by comparing scorecards from different product categories of the same brand. This makes it possible to compare scorecards from different product categories and perform a comprehensive evaluation.

[0041] The scorecard generation unit can make the scorecard customizable, allowing the user to select the evaluation items that they value. For example, the scorecard generation unit allows the generation AI to customize the scorecard, allowing the user to select the evaluation items that they value. For example, the user can select evaluation items such as "battery life" or "screen quality." The scorecard generation unit also builds a system that makes the scorecard customizable, allowing the user to select the evaluation items that they value. For example, the user can customize the evaluation items to suit their needs. The scorecard generation unit also makes the generation AI customizable, allowing the user to select the evaluation items that they value. For example, the user can select evaluation items such as "operability" or "design." This makes the scorecard customizable so that the user can select the evaluation items that they value.

[0042] The analysis unit understands the context of the review and can automatically correct inappropriate language or misleading information. For example, the generation AI in the analysis unit understands the context of the review and automatically corrects inappropriate language or misleading information. For example, it replaces discriminatory language with appropriate language. The analysis unit also builds a system that analyzes the context of the review and automatically corrects inappropriate language or misleading information. For example, it corrects incorrect information with accurate information. The analysis unit also builds a system that analyzes the context of the review and automatically corrects inappropriate language or misleading information. For example, it replaces offensive language with neutral language. This makes it possible to automatically correct inappropriate language or misleading information.

[0043] The analysis unit can analyze the past posting history of the review poster and filter out posts with low reliability. For example, the analysis unit uses a generation AI to analyze the past posting history of the review poster and filter out posts with low reliability. For example, it excludes reviews from posters who have a history of posting false information in the past. The analysis unit also builds a system that automatically filters out posts with low reliability based on the poster's past posting history. For example, it excludes reviews from posters who have received many low ratings in the past. The analysis unit also uses a generation AI to analyze the past posting history of the review poster and filter out posts with low reliability. For example, it excludes reviews from posters who have used inappropriate language in the past. This makes it possible to filter out posts with low reliability.

[0044] The analysis unit can analyze reviews in different languages ​​and perform multilingual filtering. For example, the generation AI in the analysis unit analyzes reviews in different languages ​​and performs multilingual filtering. For example, it analyzes and filters reviews in English, French, Chinese, etc. The analysis unit also uses machine translation technology to translate reviews in different languages ​​and build a system for multilingual filtering. For example, it integrates and filters reviews in each language. The analysis unit also analyzes reviews in different languages ​​and performs multilingual filtering. For example, it analyzes and filters reviews in Spanish and German. This enables multilingual filtering.

[0045] The analysis unit can also analyze image and video reviews and filter out inappropriate content. For example, the analysis unit uses a generative AI to analyze images and video reviews and filter out inappropriate content. For example, it can automatically filter out discriminatory images and offensive videos. The analysis unit also uses image recognition technology to analyze the content of image reviews and build a system to filter out inappropriate content. For example, it can automatically filter out inappropriate images. The analysis unit also uses video analysis technology to analyze the content of video reviews and filter out inappropriate content. For example, it can automatically filter out offensive videos and misleading videos. This makes it possible to filter out inappropriate content in image and video reviews.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The review analysis system can also analyze a user's purchasing history and prioritize the display of reviews that are most suitable for each individual user. For example, reviews of products similar to products purchased in the past can be prioritized. It can also prioritize the display of reviews of specific brands or categories based on the user's purchasing history. For example, if a user has purchased many products from a specific brand, reviews of that brand can be prioritized. It can also analyze a user's purchasing history and, if a product purchased in the past received high ratings, prioritize the display of reviews of related products based on those ratings. This allows users to quickly find reviews that are useful to them.

[0048] The review analysis system can also analyze a user's search history and prioritize the display of related reviews. For example, reviews related to keywords previously searched can be prioritized. It can also prioritize the display of reviews about specific categories or brands based on the user's search history. For example, if a user frequently searches for products in a specific category, reviews of that category can be prioritized. It can also analyze a user's search history and, if a product previously searched for has a high rating, prioritize the display of reviews of related products based on that rating. This allows users to quickly find reviews that are useful to them.

[0049] The review analysis system can further analyze a user's social media activity and prioritize the display of relevant reviews. For example, it can prioritize the display of reviews about products that the user has mentioned on social media. It can also prioritize the display of reviews about specific brands or categories based on the user's social media activity. For example, if a user frequently mentions a specific brand, it can prioritize the display of reviews about that brand. It can also analyze a user's social media activity and, if a product that the user has mentioned in the past has received high ratings, it can prioritize the display of reviews of related products based on those ratings. This allows users to quickly find reviews that are useful to them.

[0050] The review analysis system can further analyze the user's geographic location information and prioritize the display of reviews that are specific to the region. For example, based on the user's current location, reviews of nearby stores and services can be prioritized and displayed. The review analysis system can also prioritize the display of reviews of products that are popular in a specific region based on the user's geographic location information. For example, reviews of products that are highly rated in a specific region can be prioritized and displayed. The review analysis system can also analyze the user's geographic location information and prioritize the display of reviews of products related to places that the user has visited in the past. This allows users to quickly find useful reviews that are specific to their region.

[0051] The review analysis system can also analyze a user's purchasing history and prioritize the display of reviews that are most suitable for each individual user. For example, reviews of products similar to products purchased in the past can be prioritized. It can also prioritize the display of reviews of specific brands or categories based on the user's purchasing history. For example, if a user has purchased many products from a specific brand, reviews of that brand can be prioritized. It can also analyze a user's purchasing history and, if a product purchased in the past received high ratings, prioritize the display of reviews of related products based on those ratings. This allows users to quickly find reviews that are useful to them.

[0052] The processing flow of the first embodiment will be briefly explained below.

[0053] Step 1: The review collection unit uses generation AI to centrally collect multiple reviews posted on major e-commerce sites. For example, reviews can be collected from e-commerce sites such as Amazon and Rakuten. The review collection unit can also analyze the review poster's past review history to prioritize the collection of highly reliable reviews. It can also analyze the time and frequency of reviews posted to understand trends in reviews posted during specific time periods. Step 2: The analysis unit analyzes the reviews collected by the review collection unit. For example, it uses an emotion estimation function to analyze the emotional tone of the reviews and classify them into positive and negative reviews. It can also analyze image and video reviews and combine them with text reviews to create an overall evaluation. Step 3: The generator / summarizer creates a summary based on the review content analyzed by the analyzer. For example, the generator / summarizer can understand the context of the review and generate a summary that includes comparative information with other related products. It can also extract frequently occurring phrases and keywords from the review and create a summary based on them. Step 4: The scorecard generator generates a scorecard based on the summary generated by the summary generator. For example, it displays the average scores for major evaluation items such as product quality, cost performance, and durability. It can also analyze the detailed evaluation items in the reviews and display the scores for each item in more detail.

[0054] (Example 2) A review analysis system according to an embodiment of the present invention utilizes a generation AI to centrally collect and analyze a large number of reviews posted on major e-commerce sites, enabling consumers to quickly obtain useful information. As a result, the review analysis system can significantly reduce the effort and time it takes for consumers to find useful information from reviews.

[0055] A review analysis system according to an embodiment includes a review collection unit, an analysis unit, a generation / summarization unit, and a scorecard generation unit. The review collection unit centrally collects multiple reviews posted on major e-commerce sites using a generation AI. For example, the review collection unit collects reviews from e-commerce sites such as Amazon and Rakuten. The review collection unit can also analyze the review poster's past review history to prioritize collection of highly reliable reviews. For example, the review collection unit can prioritize analysis of reviews posted by posters who have received high ratings in the past. The review collection unit can also analyze the time period and frequency of reviews posted to understand trends in reviews posted during specific time periods. For example, the review collection unit can analyze whether reviews posted at night tend to be more positive. The analysis unit analyzes the reviews collected by the review collection unit. For example, the analysis unit uses an emotion estimation function to analyze the emotional tone of the reviews and classify them into positive and negative reviews. The analysis unit can also analyze image and video reviews and combine them with text reviews to perform a comprehensive evaluation. For example, the analysis unit can analyze images and videos showing the product's user experience. The summarization unit generates summaries based on the review content analyzed by the analysis unit. For example, the AI ​​generation unit understands the context of the review and generates summaries that include comparative information with other related products. The summarization unit can also extract frequently occurring phrases and keywords from reviews and create summaries based on them. For example, keywords such as "screen quality" and "battery life" are extracted. The scorecard generation unit generates a scorecard based on the summaries generated by the summaries. For example, the scorecard generation unit displays average scores for major evaluation items such as product quality, cost performance, and durability. The scorecard generation unit can also analyze detailed evaluation items in reviews and display sub-scores for each item. For example, evaluation items such as "screen quality" and "battery life" are displayed sub-scored. This allows the review analysis system according to the embodiment to quickly obtain useful information. For example, consumers no longer need to read a large number of reviews one by one, and can quickly make purchasing decisions by referring to the summarized information and the scorecard.

[0056] The review collection unit can analyze the poster's past review history and prioritize collecting highly reliable reviews. For example, the review collection unit uses a generation AI to analyze the poster's past review history and prioritize collecting highly reliable reviews. For example, it prioritizes analyzing reviews by posters who have received high ratings in the past. The review collection unit also builds a system that automatically filters out highly reliable reviews based on the poster's past review history. For example, it prioritizes reviews by posters who have received many "helpful" ratings in the past. The review collection unit also uses a generation AI to analyze the poster's past review history and exclude less reliable reviews. For example, it excludes reviews by posters who have a history of posting false information in the past. This allows highly reliable reviews to be collected preferentially.

[0057] The review collection unit analyzes the time and frequency of reviews posted, and can grasp trends in reviews posted during specific time periods. For example, the review collection unit uses a generation AI to analyze the time of review posting and grasp trends in reviews posted during specific time periods. For example, it analyzes whether reviews posted at night tend to be positive. The review collection unit also analyzes posting frequency and builds a system to grasp trends in frequently posted reviews. For example, if there are many reviews posted on weekends, it analyzes this trend. The review collection unit also uses a generation AI to analyze the time and frequency of posting and evaluate the reliability of reviews posted during specific time periods. For example, if reviews posted late at night are considered to be unreliable, it grasps this tendency. This makes it possible to grasp trends in reviews posted during specific time periods.

[0058] The analysis unit can use the emotion estimation function to analyze the emotional tone of the review and classify it into positive and negative reviews. For example, the analysis unit uses the emotion estimation function to analyze the emotional tone of the review and classify it into positive and negative reviews. For example, it classifies reviews that show joy or satisfaction as positive. The analysis unit also builds a system in which the generation AI analyzes the emotional tone of the review and automatically filters out negative reviews. For example, it classifies reviews that show dissatisfaction or anger as negative. The analysis unit also uses the emotion estimation function to analyze the emotional tone of the review and classify the review based on the emotion score. For example, it classifies reviews with a high emotion score as positive. This makes it possible to classify positive and negative reviews.

[0059] The review collection unit can collect reviews from different e-commerce sites and integrate and analyze reviews from multiple platforms. For example, the review collection unit uses a generation AI to collect reviews from different e-commerce sites and integrate and analyze reviews from multiple platforms. For example, it centrally collects reviews from sites such as Amazon and Rakuten. The review collection unit also integrates reviews collected from different e-commerce sites and builds a system for comprehensive evaluation. For example, it integrates reviews from each site to evaluate products. The review collection unit also uses a generation AI to collect reviews from different e-commerce sites and analyze review trends for each platform. For example, it analyzes whether reviews on a particular site tend to be positive. This allows reviews from multiple platforms to be integrated and analyzed.

[0060] The analysis unit can also analyze image or video reviews and combine them with text reviews to form a comprehensive evaluation. For example, the analysis unit uses a generation AI to analyze image or video reviews and combine them with text reviews to form a comprehensive evaluation. For example, it analyzes images and videos that show the product's usability. The analysis unit also uses image recognition technology to build a system that analyzes the content of image reviews and integrates them with text reviews. For example, it analyzes images that show the product's appearance and how to use it. The analysis unit also uses video analysis technology to analyze the content of video reviews and integrate them with text reviews. For example, it analyzes videos that show the product's usage and performance. This allows image and video reviews to be analyzed and a comprehensive evaluation to be formed.

[0061] The analysis unit can use the emotion estimation function to analyze the emotions of the review poster in real time and track changes in their emotions. For example, the analysis unit uses the emotion estimation function to analyze the emotions of the review poster in real time and track changes in their emotions. For example, it analyzes the emotions at the time of posting the review and changes in their emotions afterwards. The analysis unit also builds a system in which the generation AI analyzes the emotions of the poster in real time and tracks changes in their emotions. For example, it analyzes changes in emotions before and after posting the review. The analysis unit also uses the emotion estimation function to analyze the emotions of the review poster in real time and visualize changes in their emotions. For example, it displays changes in emotions in a graph or chart. This makes it possible to analyze the emotions of the review poster in real time and track changes in their emotions.

[0062] The summary generating unit can understand the context of the review and generate a summary that includes comparative information with other related products. For example, the summary generating unit uses a generation AI to understand the context of the review and generate a summary that includes comparative information with other related products. For example, it generates a summary that compares with other products in the same category. The summary generating unit also builds a system that analyzes the context of the review and automatically collects information about related products to reflect in the summary. For example, it generates a summary that includes comparative information with competing products. The summary generating unit also uses a generation AI to understand the context of the review and generate a summary that includes comparative information with other related products. For example, it generates a summary that includes comparative information on price and performance. This makes it possible to generate a summary that includes comparative information with other related products.

[0063] The summarization unit can extract phrases and keywords that appear frequently in reviews and create summaries based on them. For example, the summarization unit uses a generation AI to extract phrases and keywords that appear frequently in reviews and create summaries based on them. For example, it extracts keywords such as "screen quality" and "battery life." The summarization unit can also automatically extract phrases and keywords that appear frequently in reviews and build a system that creates summaries based on them. For example, it can extract positive and negative phrases. The summarization unit can also extract phrases and keywords that appear frequently in reviews and create summaries based on them. For example, it can extract keywords such as "usability" and "design." This makes it possible to create summaries based on frequently appearing phrases and keywords.

[0064] The summarization unit can use the emotion estimation function to generate summaries that reflect the emotional elements of reviews. The summarization unit, for example, uses the emotion estimation function to generate summaries that reflect the emotional elements of reviews. For example, summaries are created based on reviews with strong positive emotions. The summarization unit also builds a system in which a generative AI analyzes the emotional elements of reviews and generates summaries that reflect the results. For example, summaries are created based on emotion scores. The summarization unit also uses the emotion estimation function to generate summaries that reflect the emotional elements of reviews. For example, summaries are created based on reviews with strong negative emotions. This makes it possible to generate summaries that reflect emotional elements.

[0065] The summarization unit can automatically translate reviews in different languages ​​and generate summaries that support multiple languages. For example, the summarization unit uses a generation AI to automatically translate reviews in different languages ​​and generate summaries that support multiple languages. For example, it translates reviews in English, French, Chinese, etc. to create summaries. The summarization unit also uses machine translation technology to build a system that translates reviews in different languages ​​and generates summaries that support multiple languages. For example, it integrates reviews in each language to create summaries. The summarization unit also uses a generation AI to automatically translate reviews in different languages ​​and generate summaries that support multiple languages. For example, it translates reviews in Spanish and German to create summaries. This makes it possible to generate summaries that support multiple languages.

[0066] The generating summary unit can visualize the review summary and display it in a graph or chart. For example, the generating AI can visualize the review summary and display it in a graph or chart. For example, the score for each evaluation item can be displayed in a bar graph or pie chart. The generating summary unit can also visualize the content of the summarized review, building a system that allows users to intuitively understand it. For example, the score for each evaluation item can be displayed in a chart. The generating summary unit can also visualize the review summary and display it in a graph or chart. For example, the ratio of positive reviews to negative reviews can be displayed in a pie chart. This allows the summary to be visualized and displayed in a graph or chart.

[0067] The summarization unit can use the emotion estimation function to collect users' emotional reactions to the summarized reviews and improve the accuracy of the summaries. For example, the summarization unit can use the emotion estimation function to collect users' emotional reactions to the summarized reviews and improve the accuracy of the summaries based on that data. For example, it can prioritize summaries with a large number of positive reactions. The summarization unit can also use the generation AI to analyze users' emotional reactions to the summarized reviews and build a system that improves the accuracy of the summaries based on the results. For example, it can regenerate summaries based on emotion scores. The summarization unit can also use the emotion estimation function to collect users' emotional reactions to the summarized reviews and improve the accuracy of the summaries based on that data. For example, it can revise summaries with a large number of negative reactions. This allows the summarization unit to collect users' emotional reactions to improve the accuracy of the summaries.

[0068] The scorecard generation unit can analyze the detailed evaluation items of a review and display a score for each item in a more detailed manner. For example, the generation AI in the scorecard generation unit analyzes the detailed evaluation items of a review and displays a score for each item in a more detailed manner. For example, evaluation items such as "screen quality" and "battery life" are displayed in a more detailed manner. The scorecard generation unit also builds a system that analyzes the detailed evaluation items and displays a score for each item in a more detailed manner. For example, the score for each evaluation item is displayed in a bar graph or chart. The scorecard generation unit can also analyze the detailed evaluation items of a review and display a score for each item in a more detailed manner. For example, evaluation items such as "operability" and "design" are displayed in a more detailed manner. This allows the generation AI to analyze the detailed evaluation items and display a score for each item in a more detailed manner.

[0069] The scorecard generation unit is able to generate a highly reliable score by taking into account the expertise and experience of the review poster. For example, the generation AI in the scorecard generation unit generates a highly reliable score by taking into account the expertise and experience of the review poster. For example, it prioritizes analysis of reviews by posters with specialized knowledge. The scorecard generation unit also builds a system that generates a highly reliable score based on the poster's expertise and experience. For example, it prioritizes analysis of reviews by experts. The scorecard generation unit also builds a system that generates a highly reliable score by taking into account the expertise and experience of the review poster. For example, it prioritizes analysis of reviews by posters with many years of experience. This makes it possible to generate a highly reliable score.

[0070] The scorecard generation unit can use the emotion estimation function to generate a scorecard that reflects the emotional tone of the review. The scorecard generation unit, for example, uses the emotion estimation function to generate a scorecard that reflects the emotional tone of the review. For example, a review with a strong positive emotion is reflected in the scorecard as a high rating. The scorecard generation unit also builds a system in which a generation AI analyzes the emotional tone of the review and generates a scorecard that reflects the results. For example, the scorecard is generated based on the emotion score. The scorecard generation unit also uses the emotion estimation function to generate a scorecard that reflects the emotional tone of the review. For example, a review with a strong negative emotion is reflected in the scorecard as a low rating. This makes it possible to generate a scorecard that reflects the emotional tone.

[0071] The scorecard generation unit can compare scorecards from different product categories and perform a comprehensive evaluation. In the scorecard generation unit, for example, a generation AI compares scorecards from different product categories and performs a comprehensive evaluation. For example, a comprehensive evaluation is performed by comparing scorecards from smartphones and tablets. The scorecard generation unit also builds a system that compares scorecards from different product categories and performs a comprehensive evaluation. For example, a comprehensive evaluation is performed by comparing scorecards from home appliances and gadgets. The scorecard generation unit also builds a system that compares scorecards from different product categories and performs a comprehensive evaluation. For example, a comprehensive evaluation is performed by comparing scorecards from different product categories of the same brand. This makes it possible to compare scorecards from different product categories and perform a comprehensive evaluation.

[0072] The scorecard generation unit can make the scorecard customizable, allowing the user to select the evaluation items that they value. For example, the scorecard generation unit allows the generation AI to customize the scorecard, allowing the user to select the evaluation items that they value. For example, the user can select evaluation items such as "battery life" or "screen quality." The scorecard generation unit also builds a system that makes the scorecard customizable, allowing the user to select the evaluation items that they value. For example, the user can customize the evaluation items to suit their needs. The scorecard generation unit also makes the generation AI customizable, allowing the user to select the evaluation items that they value. For example, the user can select evaluation items such as "operability" or "design." This makes the scorecard customizable so that the user can select the evaluation items that they value.

[0073] The scorecard generation unit can use the emotion estimation function to collect users' emotional reactions to the scorecard and improve the reliability of the score. The scorecard generation unit, for example, uses the emotion estimation function to collect users' emotional reactions to the scorecard and improve the reliability of the score based on that data. For example, scores with a large number of positive reactions are preferentially displayed. The scorecard generation unit also builds a system in which the generation AI analyzes users' emotional reactions to the scorecard and improves the reliability of the score based on the results. For example, the score is reevaluated based on the emotional score. The scorecard generation unit also uses the emotion estimation function to collect users' emotional reactions to the scorecard and improves the reliability of the score based on that data. For example, scores with a large number of negative reactions are corrected. In this way, the score generation unit can collect users' emotional reactions to the scorecard and improve the reliability of the score.

[0074] The analysis unit understands the context of the review and can automatically correct inappropriate language or misleading information. For example, the generation AI in the analysis unit understands the context of the review and automatically corrects inappropriate language or misleading information. For example, it replaces discriminatory language with appropriate language. The analysis unit also builds a system that analyzes the context of the review and automatically corrects inappropriate language or misleading information. For example, it corrects incorrect information with accurate information. The analysis unit also builds a system that analyzes the context of the review and automatically corrects inappropriate language or misleading information. For example, it replaces offensive language with neutral language. This makes it possible to automatically correct inappropriate language or misleading information.

[0075] The analysis unit can analyze the past posting history of the review poster and filter out posts with low reliability. For example, the analysis unit uses a generation AI to analyze the past posting history of the review poster and filter out posts with low reliability. For example, it excludes reviews from posters who have a history of posting false information in the past. The analysis unit also builds a system that automatically filters out posts with low reliability based on the poster's past posting history. For example, it excludes reviews from posters who have received many low ratings in the past. The analysis unit also uses a generation AI to analyze the past posting history of the review poster and filter out posts with low reliability. For example, it excludes reviews from posters who have used inappropriate language in the past. This makes it possible to filter out posts with low reliability.

[0076] The analysis unit can use the emotion estimation function to detect and filter emotionally extreme expressions. The analysis unit, for example, uses the emotion estimation function to detect and filter emotionally extreme expressions. For example, expressions showing anger or hatred are automatically excluded. The analysis unit also constructs a system in which the generation AI analyzes emotionally extreme expressions and filters them based on the results. For example, expressions with a high emotion score are excluded. The analysis unit also uses the emotion estimation function to detect and filter emotionally extreme expressions. For example, aggressive expressions and insulting expressions are automatically excluded. This makes it possible to filter emotionally extreme expressions.

[0077] The analysis unit can analyze reviews in different languages ​​and perform multilingual filtering. For example, the generation AI in the analysis unit analyzes reviews in different languages ​​and performs multilingual filtering. For example, it analyzes and filters reviews in English, French, Chinese, etc. The analysis unit also uses machine translation technology to translate reviews in different languages ​​and build a system for multilingual filtering. For example, it integrates and filters reviews in each language. The analysis unit also analyzes reviews in different languages ​​and performs multilingual filtering. For example, it analyzes and filters reviews in Spanish and German. This enables multilingual filtering.

[0078] The analysis unit can also analyze image and video reviews and filter out inappropriate content. For example, the analysis unit uses a generative AI to analyze images and video reviews and filter out inappropriate content. For example, it can automatically filter out discriminatory images and offensive videos. The analysis unit also uses image recognition technology to analyze the content of image reviews and build a system to filter out inappropriate content. For example, it can automatically filter out inappropriate images. The analysis unit also uses video analysis technology to analyze the content of video reviews and filter out inappropriate content. For example, it can automatically filter out offensive videos and misleading videos. This makes it possible to filter out inappropriate content in image and video reviews.

[0079] The analysis unit can use the emotion estimation function to collect users' emotional reactions to filtered reviews and improve the accuracy of filtering. For example, the analysis unit can use the emotion estimation function to collect users' emotional reactions to filtered reviews and improve the accuracy of filtering based on that data. For example, the analysis unit can prioritize the adoption of filtering results with a high number of positive reactions. The analysis unit also uses the generation AI to analyze users' emotional reactions to filtered reviews and build a system that improves the accuracy of filtering based on the results. For example, the analysis unit can reevaluate filtering based on the emotion score. The analysis unit also uses the emotion estimation function to collect users' emotional reactions to filtered reviews and improve the accuracy of filtering based on that data. For example, the analysis unit can correct filtering results with a high number of negative reactions. In this way, users' emotional reactions can be collected to improve the accuracy of filtering.

[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] The review analysis system can also analyze a user's purchasing history and prioritize the display of reviews that are most suitable for each individual user. For example, reviews of products similar to products purchased in the past can be prioritized. It can also prioritize the display of reviews of specific brands or categories based on the user's purchasing history. For example, if a user has purchased many products from a specific brand, reviews of that brand can be prioritized. It can also analyze a user's purchasing history and, if a product purchased in the past received high ratings, prioritize the display of reviews of related products based on those ratings. This allows users to quickly find reviews that are useful to them.

[0082] The review analysis system can also analyze a user's search history and prioritize the display of related reviews. For example, reviews related to keywords previously searched can be prioritized. It can also prioritize the display of reviews about specific categories or brands based on the user's search history. For example, if a user frequently searches for products in a specific category, reviews of that category can be prioritized. It can also analyze a user's search history and, if a product previously searched for has a high rating, prioritize the display of reviews of related products based on that rating. This allows users to quickly find reviews that are useful to them.

[0083] The review analysis system can further analyze a user's social media activity and prioritize the display of relevant reviews. For example, it can prioritize the display of reviews about products that the user has mentioned on social media. It can also prioritize the display of reviews about specific brands or categories based on the user's social media activity. For example, if a user frequently mentions a specific brand, it can prioritize the display of reviews about that brand. It can also analyze a user's social media activity and, if a product that the user has mentioned in the past has received high ratings, it can prioritize the display of reviews of related products based on those ratings. This allows users to quickly find reviews that are useful to them.

[0084] The review analysis system can further analyze the user's geographic location information and prioritize the display of reviews that are specific to the region. For example, based on the user's current location, reviews of nearby stores and services can be prioritized and displayed. The review analysis system can also prioritize the display of reviews of products that are popular in a specific region based on the user's geographic location information. For example, reviews of products that are highly rated in a specific region can be prioritized and displayed. The review analysis system can also analyze the user's geographic location information and prioritize the display of reviews of products related to places that the user has visited in the past. This allows users to quickly find useful reviews that are specific to their region.

[0085] The review analysis system can further estimate a user's purchasing intent and prioritize the display of reviews based on that intent. For example, if a user frequently views a particular product, reviews of that product will be prioritized. The review analysis system can also estimate a user's purchasing intent and prioritize the display of reviews related to a particular category or brand. For example, if a user frequently views products in a particular category, reviews of that category will be prioritized. The review analysis system can also estimate a user's purchasing intent and prioritize the display of reviews of products that have received high ratings in the past. This allows users to quickly find useful reviews that match their purchasing intent.

[0086] The review analysis system can further estimate the user's emotions and prioritize the display of reviews based on those emotions. For example, if a user expresses positive emotions, positive reviews will be displayed preferentially. The system can also estimate the user's emotions and prioritize the display of reviews related to specific categories or brands. For example, if a user expresses positive emotions about products in a specific category, positive reviews of that category will be displayed preferentially. The system can also estimate the user's emotions and prioritize the display of reviews of products that have received high ratings in the past. This allows users to quickly find useful reviews that match their emotions.

[0087] The review analysis system can also track changes in a user's emotions and prioritize the display of reviews based on those changes. For example, if a user's emotions change from negative to positive, positive reviews will be prioritized. The review analysis system can also track changes in a user's emotions and prioritize the display of reviews related to specific categories or brands. For example, if a user's emotions change regarding products in a specific category, reviews of that category will be prioritized. The review analysis system can also track changes in a user's emotions and prioritize the display of reviews of products that have received high ratings in the past. This allows users to quickly find useful reviews that match their changing emotions.

[0088] The review analysis system can further estimate a user's emotions and generate review summaries based on those emotions. For example, if a user expresses positive emotions, a summary is generated based on positive reviews. It can also estimate a user's emotions and generate summaries of reviews related to a specific category or brand. For example, if a user expresses positive emotions toward products in a specific category, a summary is generated based on positive reviews in that category. It can also estimate a user's emotions and generate summaries based on reviews of products that have received high ratings in the past. This allows users to quickly find useful review summaries that match their emotions.

[0089] The review analysis system can further infer a user's emotions and generate a scorecard based on those emotions. For example, if a user expresses positive emotions, a scorecard is generated based on positive reviews. The review analysis system can also infer a user's emotions and generate a scorecard for a specific category or brand. For example, if a user expresses positive emotions toward products in a specific category, a scorecard is generated based on positive reviews in that category. The review analysis system can also infer a user's emotions and generate a scorecard based on reviews of products that have received high ratings in the past. This allows users to quickly find useful scorecards that match their emotions.

[0090] The review analysis system can also analyze a user's purchasing history and prioritize the display of reviews that are most suitable for each individual user. For example, reviews of products similar to products purchased in the past can be prioritized. It can also prioritize the display of reviews of specific brands or categories based on the user's purchasing history. For example, if a user has purchased many products from a specific brand, reviews of that brand can be prioritized. It can also analyze a user's purchasing history and, if a product purchased in the past received high ratings, prioritize the display of reviews of related products based on those ratings. This allows users to quickly find reviews that are useful to them.

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

[0092] Step 1: The review collection unit uses generation AI to centrally collect multiple reviews posted on major e-commerce sites. For example, reviews can be collected from e-commerce sites such as Amazon and Rakuten. The review collection unit can also analyze the review poster's past review history to prioritize the collection of highly reliable reviews. It can also analyze the time and frequency of reviews posted to understand trends in reviews posted during specific time periods. Step 2: The analysis unit analyzes the reviews collected by the review collection unit. For example, it uses an emotion estimation function to analyze the emotional tone of the reviews and classify them into positive and negative reviews. It can also analyze image and video reviews and combine them with text reviews to create an overall evaluation. Step 3: The generator / summarizer creates a summary based on the review content analyzed by the analyzer. For example, the generator / summarizer can understand the context of the review and generate a summary that includes comparative information with other related products. It can also extract frequently occurring phrases and keywords from the review and create a summary based on them. Step 4: The scorecard generator generates a scorecard based on the summary generated by the summary generator. For example, it displays the average scores for major evaluation items such as product quality, cost performance, and durability. It can also analyze the detailed evaluation items in the reviews and display the scores for each item in more detail.

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

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

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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).

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0110] 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.

[0111] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0122] 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.

[0123] 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.

[0124] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0125] 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.

[0126] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0127] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] 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.

[0139] 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.

[0140] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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."

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0160] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A review collection department that uses AI generation to centrally collect multiple reviews posted on major e-commerce sites, and an analysis unit that analyzes the reviews collected by the review collection unit; a summarizing unit that generates a summary based on the review content analyzed by the analyzing unit; a scorecard generation unit that generates a scorecard based on the summary generated by the summary generation unit; A system characterized by:

2. The review collection unit Analyze the reviewer's past review history and prioritize the collection of highly reliable reviews 2. The system of claim 1.

3. The review collection unit Analyzing the time period and frequency of reviews posted and understanding trends in reviews posted during specific time periods 2. The system of claim 1.

4. The analysis unit Analyzing the emotional tone of the reviews and classifying them as positive or negative 2. The system of claim 1.

5. The review collection unit The reviews are collected from different e-commerce sites, and the reviews from the multiple platforms are integrated and analyzed.

2. The system of claim 1.

6. The analysis unit Image or video reviews are also analyzed and combined with text reviews to provide a comprehensive evaluation.

2. The system of claim 1.

Images