system

Abstract

An object of a system according to an embodiment is to efficiently classify word-of-mouth data of an EC site and clarify evaluation before and after use.SOLUTION: A system according to an embodiment includes a word-of-mouth data collection unit, a preprocessing unit, and a classification unit. The word-of-mouth data collection unit collects word-of-mouth data from an EC site. The preprocessor preprocesses the word-of-mouth data collected by the word-of-mouth data collector. The classifier classifies the word-of-mouth data preprocessed by the preprocessor into an evaluation before use and an evaluation after use.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 technology has had the problem of making it difficult to efficiently classify pre- and post-use evaluations from word-of-mouth data on e-commerce sites.

[0005] The system according to the embodiment aims to efficiently classify word-of-mouth data on an EC site and clarify evaluations before and after use. [Means for solving the problem]

[0006] The system according to the embodiment includes a word-of-mouth data collection unit, a preprocessing unit, and a classification unit. The word-of-mouth data collection unit collects word-of-mouth data from an e-commerce site. The preprocessing unit preprocesses the word-of-mouth data collected by the word-of-mouth data collection unit. The classification unit classifies the word-of-mouth data preprocessed by the preprocessing unit into pre-use evaluations and post-use evaluations. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently classify word-of-mouth data from an EC site and clarify evaluations before and after use. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The word-of-mouth analysis system according to the embodiment of the present invention is a system that uses a generation AI to analyze word-of-mouth data on an e-commerce site and efficiently extracts the specific usage experience and evaluations that consumers desire. As a result, the word-of-mouth analysis system can efficiently extract the specific usage experience and evaluations that consumers desire.

[0029] A review analysis system according to an embodiment includes a review data collection unit, a preprocessing unit, and a classification unit. The review data collection unit collects review data from an e-commerce site. For example, the review data collection unit automatically collects review data from the e-commerce site using an API. The review data collection unit can also collect review data using web scraping technology. For example, when using an API, the review data collection unit sends a request to an API endpoint of the e-commerce site and obtains review data returned as a response. When using web scraping technology, the review data collection unit analyzes the HTML structure of the e-commerce site and extracts review data. The preprocessing unit preprocesses the review data collected by the review data collection unit. For example, the preprocessing unit cleans the text and removes unnecessary information. The preprocessing unit can also perform tokenization to convert the text data into a format that is easy to analyze. For example, the preprocessing unit removes HTML tags and special characters to clean the text data. When performing tokenization, the preprocessing unit divides the text data into words and converts it into a format suitable for analysis. The classification unit classifies the review data preprocessed by the preprocessing unit into pre-use ratings and post-use ratings. For example, the classification unit may use a generation AI to analyze the review data and automatically classify the reviews into pre-use and post-use evaluations. The classification unit may also use natural language processing technology to analyze the review data and classify the evaluations. For example, the generation AI may use a text generation AI (e.g., GPT-3) to analyze the review data and classify the reviews into pre-use and post-use evaluations. When natural language processing technology is used, the classification unit analyzes the context of the text data and classifies the evaluations. This allows the review analysis system according to the embodiment to efficiently extract the specific usage experience and evaluations desired by consumers. For example, consumers can easily check specific post-use evaluations and use them as a reference for purchasing. Furthermore, companies can identify areas for product improvement based on consumer evaluations.

[0030] The preprocessing unit can analyze the posting time and posting frequency of the review data collected by the review data collection unit and preferentially preprocess highly reliable reviews. For example, when collecting review data, the preprocessing unit analyzes the user's posting time and filters out reviews posted late at night or early in the morning. This allows for preferential preprocessing of reviews posted during normal activity hours. The preprocessing unit can also analyze the user's posting frequency and preferentially preprocess reviews posted by users who post frequently. For example, the preprocessing unit preferentially preprocesses reviews from highly reliable users based on past posting history. This allows for preferential preprocessing of highly reliable reviews.

[0031] The preprocessing unit can refer to the poster's past rating history and prioritize reviews from users with consistent ratings. The preprocessing unit, for example, analyzes the poster's past rating history and prioritizes preprocessing reviews from users with consistent ratings. For example, it prioritizes reviews from users who have posted many high ratings in the past. The preprocessing unit can also prioritize reviews from users with small fluctuations in ratings based on the past rating history. For example, the preprocessing unit analyzes the past rating history and prioritizes preprocessing reviews from users with high consistency in ratings. This makes it possible to prioritize reviews from users with consistent ratings.

[0032] The word-of-mouth data collection unit simultaneously collects metadata of images and videos, and the preprocessing unit can perform preprocessing based on the metadata of images and videos. The word-of-mouth data collection unit, for example, simultaneously collects metadata of images and videos when collecting word-of-mouth data. For example, it collects metadata such as image resolution and shooting date and time. The word-of-mouth data collection unit can also collect metadata such as video playback time and frame rate. The preprocessing unit, for example, performs preprocessing based on the collected image and video metadata. For example, it preferentially preprocesses highly reliable images based on image resolution and shooting date and time. The preprocessing unit can also preferentially preprocess highly reliable videos based on video playback time and frame rate. This allows preprocessing to be performed based on visual information.

[0033] The review data collection unit can integrate review data from different e-commerce sites, and the preprocessing unit can preprocess the integrated review data. The review data collection unit, for example, builds a system that collects and integrates review data from different e-commerce sites. For example, it collects data from multiple sites such as Amazon and Rakuten. The review data collection unit can also collect and integrate review data in different languages. For example, it collects and integrates review data in English and Chinese. The preprocessing unit, for example, preprocesses the integrated review data. For example, it converts data collected from different sites into a consistent format. The preprocessing unit can also translate data in different languages ​​and convert it into a consistent format. This makes it possible to integrate review data from different e-commerce sites and build a comprehensive dataset.

[0034] The classification unit uses a generation AI to analyze the context of the word-of-mouth data and classify it based not only on the evaluations before and after use, but also on the period of use and frequency of use. The classification unit, for example, uses a generation AI to analyze the context of the word-of-mouth data and classify the evaluations before and after use. For example, it separates expected evaluations before use from actual evaluations after use. The classification unit can also perform classification based on the period of use and frequency of use. For example, it separates evaluations after long-term use from evaluations after short-term use. This makes it possible to perform classification based on the period of use and frequency of use.

[0035] The classification unit takes into consideration attribute information such as the poster's age and gender when classifying the word-of-mouth data, and can extract ratings that are appropriate for the target user. For example, the classification unit takes into consideration attribute information such as the poster's age and gender when classifying the word-of-mouth data. For example, it separates ratings from younger people and older people. The classification unit can also take into consideration differences in ratings based on gender. For example, it separates ratings from males and females. This makes it possible to extract ratings that are appropriate for the target user.

[0036] The classification unit can automatically translate reviews in different languages ​​when classifying the review data and integrate evaluations from an international perspective. For example, the classification unit automatically translates reviews in different languages ​​when classifying the review data and integrates evaluations from an international perspective. For example, reviews in English and Chinese are translated into Japanese. The classification unit can also integrate reviews in different languages ​​and provide evaluations in a consistent format. For example, reviews in different languages ​​are translated and integrated to provide evaluations from an international perspective. This makes it possible to integrate evaluations from an international perspective.

[0037] The classification unit can convert the classification results of the word-of-mouth data into visual notes or mind maps to make them easier to understand visually. For example, the classification unit can convert the classification results of the word-of-mouth data into visual notes and visually display them. For example, important points can be shown using diagrams or icons. The classification unit can also convert the classification results of the word-of-mouth data into mind maps and visually display them. For example, the map can show the structure of central themes and related subthemes. This makes it easier to understand visually.

[0038] The classification unit can use the generation AI to perform a detailed analysis of specific problems contained in the post-use evaluations and identify the root cause of the problem. The classification unit, for example, uses the generation AI to perform a detailed analysis of specific problems contained in the post-use evaluations. For example, it extracts problems such as "I didn't feel any effect" or "It didn't suit my skin." The classification unit can also use the generation AI to perform a detailed analysis to identify the root cause of the problem. For example, the generation AI analyzes word-of-mouth data and identifies the root cause of the problem. This makes it possible to identify the root cause of the problem.

[0039] When extracting post-use evaluations, the classification unit can refer to the technical specifications and usage instructions of the related product to understand the background of the evaluation. For example, when extracting post-use evaluations, the classification unit can refer to the technical specifications of the related product to understand the background of the evaluation. For example, the ingredients and usage instructions of the product can be checked to understand the basis of the evaluation. Furthermore, when extracting post-use evaluations, the classification unit can also refer to the usage instructions of the product to understand the background of the evaluation. For example, the classification unit can refer to the user manual or usage guide to understand the background of the evaluation. This makes it possible to understand the background of the evaluation.

[0040] When extracting post-use reviews, the classification unit can compare reviews of different product categories and identify common problems. For example, when extracting post-use reviews, the classification unit compares reviews of different product categories and identifies common problems. For example, the classification unit compares reviews of skin care products and outdoor products. The classification unit can also use a generation AI to compare reviews of different product categories and identify common problems. For example, the generation AI analyzes word-of-mouth data and identifies common problems. This makes it possible to identify common problems.

[0041] The classification unit can visualize the post-use evaluations and visually present them in the form of graphs or charts. The classification unit, for example, visualizes the post-use evaluations and visually presents them in the form of graphs or charts. For example, the distribution and trend of the evaluations can be displayed in a bar graph or pie chart. The classification unit can also display fluctuations in the evaluations in a line graph. For example, the fluctuations in the evaluations can be displayed in a time series. This makes it possible to visually present the post-use evaluations.

[0042] The classification unit can use the generation AI to refer to the user's past purchase history and rating history when presenting results and present personalized results. The classification unit, for example, uses the generation AI to refer to the user's past purchase history when presenting results and present personalized results. For example, ratings are displayed based on products purchased in the past. The classification unit can also refer to the user's rating history and present personalized results. For example, ratings that are appropriate for the user are displayed based on the past rating history. This makes it possible to present personalized results.

[0043] When presenting the results, the categorization unit simultaneously displays ratings and reviews of related products, making it possible to provide the user with multifaceted information. For example, when presenting the results, the categorization unit simultaneously displays ratings and reviews of related products. For example, it displays ratings of other products in the same category. The categorization unit can also display reviews of related products. For example, it displays reviews of similar products. This makes it possible to provide multifaceted information.

[0044] The classification unit can provide a display format optimized for different devices (smartphone, tablet, PC) when presenting the results. For example, the classification unit provides a display format optimized for smartphones when presenting the results. For example, the classification unit adopts a layout that matches the screen size. The classification unit can also provide a display format optimized for tablets and PCs. For example, the classification unit adopts a different UI / UX design for each device. This makes it possible to provide a display format optimized for different devices.

[0045] The classification unit can recommend related products that the user is likely to be interested in when presenting the results. For example, the classification unit recommends related products that the user is likely to be interested in when presenting the results. For example, it recommends products in the same category. The classification unit can also recommend related products based on the user's past purchase history. For example, it recommends products related to products that the user has previously purchased. This makes it possible to recommend related products that the user is likely to be interested in.

[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 data collection unit collects user location information, and the preprocessing unit can classify reviews by region based on the location information. For example, the review data collection unit acquires the user's IP address and GPS data to collect location information. The preprocessing unit can also classify reviews by region based on the collected location information. For example, it can separate reviews from urban areas from reviews from rural areas. The preprocessing unit can also prioritize preprocessing of reviews from specific regions based on the location information. This allows for detailed analysis of reviews by region.

[0048] The preprocessing unit can analyze the social media accounts of the posters of the review data and prioritize preprocessing of reviews from highly reliable accounts. For example, the preprocessing unit can analyze the number of followers and posting frequency of the posters to identify highly reliable accounts. The preprocessing unit can also prioritize preprocessing of highly reliable accounts based on engagement rates on social media. For example, the number of likes and shares can be analyzed. This allows highly reliable reviews to be prioritized preprocessing.

[0049] The preprocessing unit can analyze the purchase history of the poster of the review data and prioritize preprocessing of reviews from users who actually purchased the product. For example, the preprocessing unit acquires purchase history data from an e-commerce site and identifies reviews from users who actually purchased the product. The preprocessing unit can also prioritize preprocessing of highly reliable reviews based on the purchase history. For example, it places emphasis on reviews from users who have purchased the same product multiple times in the past. This allows reviews from users who actually purchased the product to be prioritized preprocessing.

[0050] The word-of-mouth data collection unit simultaneously collects voice data, and the preprocessing unit can convert the voice data into text and perform preprocessing. For example, the word-of-mouth data collection unit uses a voice input function to collect users' voice word-of-mouth. The preprocessing unit can also convert the voice data into text and perform preprocessing as text data. For example, the voice data is converted into text using voice recognition technology. This allows preprocessing to be performed based on the voice data.

[0051] The review data collection unit can integrate review data from different social media platforms, and the preprocessing unit can preprocess the integrated review data. For example, the review data collection unit can collect data from multiple social media platforms such as Twitter and Instagram. The review data collection unit can also collect and integrate review data in different languages. For example, it can collect and integrate review data in English and Spanish. The preprocessing unit can preprocess the integrated review data. For example, it can convert data collected from different platforms into a consistent format. The preprocessing unit can also translate data in different languages ​​and convert it into a consistent format. This makes it possible to integrate review data from different social media platforms and build a comprehensive dataset.

[0052] When classifying the review data, the classification unit takes into account attribute information such as the poster's age and gender, and can extract ratings that are appropriate for the target user. For example, when classifying the review data, the classification unit takes into account attribute information such as the poster's age and gender. For example, the classification unit separates ratings from younger people and older people. The classification unit can also take into account differences in ratings based on gender. For example, the classification unit separates ratings from males and females. This makes it possible to extract ratings that are appropriate for the target user.

[0053] The classification unit can visualize the post-use evaluations and visually present them in the form of graphs or charts. For example, the classification unit visualizes the post-use evaluations and visually presents them in the form of graphs or charts. For example, the distribution and trend of the evaluations can be displayed in a bar graph or pie chart. The classification unit can also display fluctuations in the evaluations in a line graph. For example, the fluctuations in the evaluations can be displayed in a time series. In this way, the post-use evaluations can be visually presented.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The review data collection unit collects review data from the e-commerce site. For example, review data can be automatically collected from the e-commerce site using an API. Review data can also be collected using web scraping technology. When using an API, the review data collection unit sends a request to the API endpoint of the e-commerce site and obtains the review data returned as a response. When using web scraping technology, the review data collection unit analyzes the HTML structure of the e-commerce site and extracts the review data. Step 2: The preprocessing unit preprocesses the word-of-mouth data collected by the word-of-mouth data collection unit. For example, the preprocessing unit cleans the text and removes unnecessary information. The preprocessing unit also performs tokenization to convert the text data into a format that is easy to analyze. It removes HTML tags and special characters to make the text data clean. When tokenizing, the preprocessing unit divides the text data into words and converts it into a format suitable for analysis. Step 3: The classification unit classifies the review data preprocessed by the preprocessing unit into pre-use evaluations and post-use evaluations. For example, the generation AI is used to analyze the review data and automatically classify it into pre-use evaluations and post-use evaluations. Natural language processing technology is also used to analyze the review data and classify the evaluations. The generation AI uses text generation AI (e.g., GPT-3) to analyze the review data and classify it into pre-use evaluations and post-use evaluations. When natural language processing technology is used, the classification unit analyzes the context of the text data and classifies the evaluations.

[0056] (Example 2) The word-of-mouth analysis system according to the embodiment of the present invention is a system that uses a generation AI to analyze word-of-mouth data on an e-commerce site and efficiently extracts the specific usage experience and evaluations that consumers desire. As a result, the word-of-mouth analysis system can efficiently extract the specific usage experience and evaluations that consumers desire.

[0057] A review analysis system according to an embodiment includes a review data collection unit, a preprocessing unit, and a classification unit. The review data collection unit collects review data from an e-commerce site. For example, the review data collection unit automatically collects review data from the e-commerce site using an API. The review data collection unit can also collect review data using web scraping technology. For example, when using an API, the review data collection unit sends a request to an API endpoint of the e-commerce site and obtains review data returned as a response. When using web scraping technology, the review data collection unit analyzes the HTML structure of the e-commerce site and extracts review data. The preprocessing unit preprocesses the review data collected by the review data collection unit. For example, the preprocessing unit cleans the text and removes unnecessary information. The preprocessing unit can also perform tokenization to convert the text data into a format that is easy to analyze. For example, the preprocessing unit removes HTML tags and special characters to clean the text data. When performing tokenization, the preprocessing unit divides the text data into words and converts it into a format suitable for analysis. The classification unit classifies the review data preprocessed by the preprocessing unit into pre-use ratings and post-use ratings. For example, the classification unit may use a generation AI to analyze the review data and automatically classify the reviews into pre-use and post-use evaluations. The classification unit may also use natural language processing technology to analyze the review data and classify the evaluations. For example, the generation AI may use a text generation AI (e.g., GPT-3) to analyze the review data and classify the reviews into pre-use and post-use evaluations. When natural language processing technology is used, the classification unit analyzes the context of the text data and classifies the evaluations. This allows the review analysis system according to the embodiment to efficiently extract the specific usage experience and evaluations desired by consumers. For example, consumers can easily check specific post-use evaluations and use them as a reference for purchasing. Furthermore, companies can identify areas for product improvement based on consumer evaluations.

[0058] The preprocessing unit can analyze the posting time and posting frequency of the review data collected by the review data collection unit and preferentially preprocess highly reliable reviews. For example, when collecting review data, the preprocessing unit analyzes the user's posting time and filters out reviews posted late at night or early in the morning. This allows for preferential preprocessing of reviews posted during normal activity hours. The preprocessing unit can also analyze the user's posting frequency and preferentially preprocess reviews posted by users who post frequently. For example, the preprocessing unit preferentially preprocesses reviews from highly reliable users based on past posting history. This allows for preferential preprocessing of highly reliable reviews.

[0059] The preprocessing unit can refer to the poster's past rating history and prioritize reviews from users with consistent ratings. The preprocessing unit, for example, analyzes the poster's past rating history and prioritizes preprocessing reviews from users with consistent ratings. For example, it prioritizes reviews from users who have posted many high ratings in the past. The preprocessing unit can also prioritize reviews from users with small fluctuations in ratings based on the past rating history. For example, the preprocessing unit analyzes the past rating history and prioritizes preprocessing reviews from users with high consistency in ratings. This makes it possible to prioritize reviews from users with consistent ratings.

[0060] The preprocessing unit can use the emotion estimation function to analyze the user's emotion when posting the review data and prioritize preprocessing of reviews with positive emotions. The preprocessing unit, for example, can use the emotion estimation function to analyze the user's emotion when posting the review and prioritize preprocessing of reviews with positive emotions. For example, it can place emphasis on reviews with strong feelings of joy or satisfaction. The preprocessing unit can also use the emotion estimation function to filter reviews with negative emotions. For example, it can exclude reviews with strong feelings of anger or dissatisfaction. This allows reviews with positive emotions to be prioritized preprocessing.

[0061] The word-of-mouth data collection unit simultaneously collects metadata of images and videos, and the preprocessing unit can perform preprocessing based on the metadata of images and videos. The word-of-mouth data collection unit, for example, simultaneously collects metadata of images and videos when collecting word-of-mouth data. For example, it collects metadata such as image resolution and shooting date and time. The word-of-mouth data collection unit can also collect metadata such as video playback time and frame rate. The preprocessing unit, for example, performs preprocessing based on the collected image and video metadata. For example, it preferentially preprocesses highly reliable images based on image resolution and shooting date and time. The preprocessing unit can also preferentially preprocess highly reliable videos based on video playback time and frame rate. This allows preprocessing to be performed based on visual information.

[0062] The review data collection unit can integrate review data from different e-commerce sites, and the preprocessing unit can preprocess the integrated review data. The review data collection unit, for example, builds a system that collects and integrates review data from different e-commerce sites. For example, it collects data from multiple sites such as Amazon and Rakuten. The review data collection unit can also collect and integrate review data in different languages. For example, it collects and integrates review data in English and Chinese. The preprocessing unit, for example, preprocesses the integrated review data. For example, it converts data collected from different sites into a consistent format. The preprocessing unit can also translate data in different languages ​​and convert it into a consistent format. This makes it possible to integrate review data from different e-commerce sites and build a comprehensive dataset.

[0063] The preprocessing unit can use the emotion estimation function to analyze the user's emotion at the time of posting the review data in real time and filter out reviews with negative emotions. The preprocessing unit, for example, uses the emotion estimation function to analyze the user's emotion at the time of posting the review in real time and filter out reviews with negative emotions. For example, reviews with strong anger or dissatisfaction are excluded. The preprocessing unit can also use the emotion estimation function to preferentially preprocess reviews with positive emotions. For example, reviews with strong joy or satisfaction are given more importance. This makes it possible to filter out reviews with negative emotions.

[0064] The classification unit uses a generation AI to analyze the context of the word-of-mouth data and classify it based not only on the evaluations before and after use, but also on the period of use and frequency of use. The classification unit, for example, uses a generation AI to analyze the context of the word-of-mouth data and classify the evaluations before and after use. For example, it separates expected evaluations before use from actual evaluations after use. The classification unit can also perform classification based on the period of use and frequency of use. For example, it separates evaluations after long-term use from evaluations after short-term use. This makes it possible to perform classification based on the period of use and frequency of use.

[0065] The classification unit takes into consideration attribute information such as the poster's age and gender when classifying the word-of-mouth data, and can extract ratings that are appropriate for the target user. For example, the classification unit takes into consideration attribute information such as the poster's age and gender when classifying the word-of-mouth data. For example, it separates ratings from younger people and older people. The classification unit can also take into consideration differences in ratings based on gender. For example, it separates ratings from males and females. This makes it possible to extract ratings that are appropriate for the target user.

[0066] The classification unit can use the emotion estimation function to analyze the emotional nuances of the word-of-mouth data and perform emotion-based evaluation classification. The classification unit, for example, uses the emotion estimation function to analyze the emotional nuances of the word-of-mouth data and perform emotion-based evaluation classification. For example, it separates word-of-mouth reviews with positive emotions from word-of-mouth reviews with negative emotions. The classification unit can also perform classification based on the intensity of emotions. For example, it separates word-of-mouth reviews with strong positive emotions from word-of-mouth reviews with weak positive emotions. This allows emotion-based evaluation classification.

[0067] The classification unit can automatically translate reviews in different languages ​​when classifying the review data and integrate evaluations from an international perspective. For example, the classification unit automatically translates reviews in different languages ​​when classifying the review data and integrates evaluations from an international perspective. For example, reviews in English and Chinese are translated into Japanese. The classification unit can also integrate reviews in different languages ​​and provide evaluations in a consistent format. For example, reviews in different languages ​​are translated and integrated to provide evaluations from an international perspective. This makes it possible to integrate evaluations from an international perspective.

[0068] The classification unit can convert the classification results of the word-of-mouth data into visual notes or mind maps to make them easier to understand visually. For example, the classification unit can convert the classification results of the word-of-mouth data into visual notes and visually display them. For example, important points can be shown using diagrams or icons. The classification unit can also convert the classification results of the word-of-mouth data into mind maps and visually display them. For example, the map can show the structure of central themes and related subthemes. This makes it easier to understand visually.

[0069] The classification unit can use the emotion estimation function to analyze the emotional responses of the word-of-mouth data in real time and prioritize classification of reviews with positive emotions. The classification unit, for example, uses the emotion estimation function to analyze the emotional responses of the word-of-mouth data in real time and prioritize classification of reviews with positive emotions. For example, it places emphasis on reviews that express a strong sense of joy or satisfaction. The classification unit can also use the emotion estimation function to filter out reviews with negative emotions. For example, it excludes reviews that express a strong sense of anger or dissatisfaction. This allows classification of reviews with positive emotions to be prioritized.

[0070] The classification unit can use the generation AI to perform a detailed analysis of specific problems contained in the post-use evaluations and identify the root cause of the problem. The classification unit, for example, uses the generation AI to perform a detailed analysis of specific problems contained in the post-use evaluations. For example, it extracts problems such as "I didn't feel any effect" or "It didn't suit my skin." The classification unit can also use the generation AI to perform a detailed analysis to identify the root cause of the problem. For example, the generation AI analyzes word-of-mouth data and identifies the root cause of the problem. This makes it possible to identify the root cause of the problem.

[0071] When extracting post-use evaluations, the classification unit can refer to the technical specifications and usage instructions of the related product to understand the background of the evaluation. For example, when extracting post-use evaluations, the classification unit can refer to the technical specifications of the related product to understand the background of the evaluation. For example, the ingredients and usage instructions of the product can be checked to understand the basis of the evaluation. Furthermore, when extracting post-use evaluations, the classification unit can also refer to the usage instructions of the product to understand the background of the evaluation. For example, the classification unit can refer to the user manual or usage guide to understand the background of the evaluation. This makes it possible to understand the background of the evaluation.

[0072] The classification unit can use the emotion estimation function to analyze emotional elements included in the post-use evaluations and perform summarization based on emotions. The classification unit, for example, uses the emotion estimation function to analyze emotional elements included in the post-use evaluations and perform summarization based on emotions. For example, it separates evaluations with positive emotions from evaluations with negative emotions. The classification unit can also perform summarization based on the intensity of emotions. For example, it separates evaluations with strong positive emotions from evaluations with weak positive emotions. This allows summarization based on emotions.

[0073] When extracting post-use reviews, the classification unit can compare reviews of different product categories and identify common problems. For example, when extracting post-use reviews, the classification unit compares reviews of different product categories and identifies common problems. For example, the classification unit compares reviews of skin care products and outdoor products. The classification unit can also use a generation AI to compare reviews of different product categories and identify common problems. For example, the generation AI analyzes word-of-mouth data and identifies common problems. This makes it possible to identify common problems.

[0074] The classification unit can visualize the post-use evaluations and visually present them in the form of graphs or charts. The classification unit, for example, visualizes the post-use evaluations and visually presents them in the form of graphs or charts. For example, the distribution and trend of the evaluations can be displayed in a bar graph or pie chart. The classification unit can also display fluctuations in the evaluations in a line graph. For example, the fluctuations in the evaluations can be displayed in a time series. This makes it possible to visually present the post-use evaluations.

[0075] The classification unit can use the emotion estimation function to analyze the user's emotional response to the post-use evaluation in real time and perform summarization based on the emotion. The classification unit can, for example, use the emotion estimation function to analyze the user's emotional response to the post-use evaluation in real time and perform summarization based on the emotion. For example, the classification unit can prioritize summarization of evaluations with positive emotions. The classification unit can also filter out evaluations with negative emotions. For example, it can exclude evaluations with strong anger or dissatisfaction. This makes it possible to perform summarization based on the emotion.

[0076] The classification unit can use the generation AI to refer to the user's past purchase history and rating history when presenting results and present personalized results. The classification unit, for example, uses the generation AI to refer to the user's past purchase history when presenting results and present personalized results. For example, ratings are displayed based on products purchased in the past. The classification unit can also refer to the user's rating history and present personalized results. For example, ratings that are appropriate for the user are displayed based on the past rating history. This makes it possible to present personalized results.

[0077] When presenting the results, the categorization unit simultaneously displays ratings and reviews of related products, making it possible to provide the user with multifaceted information. For example, when presenting the results, the categorization unit simultaneously displays ratings and reviews of related products. For example, it displays ratings of other products in the same category. The categorization unit can also display reviews of related products. For example, it displays reviews of similar products. This makes it possible to provide multifaceted information.

[0078] The classification unit can use the emotion estimation function to analyze the user's emotional response when presenting the results and adopt a presentation method that elicits positive emotions. The classification unit, for example, uses the emotion estimation function to analyze the user's emotional response when presenting the results and adopts a presentation method that elicits positive emotions. For example, the classification unit can emphasize positive reviews. The classification unit can also filter reviews that have negative emotions. For example, reviews that express strong anger or dissatisfaction can be excluded. This makes it possible to adopt a presentation method that elicits positive emotions.

[0079] The classification unit can provide a display format optimized for different devices (smartphone, tablet, PC) when presenting the results. For example, the classification unit provides a display format optimized for smartphones when presenting the results. For example, the classification unit adopts a layout that matches the screen size. The classification unit can also provide a display format optimized for tablets and PCs. For example, the classification unit adopts a different UI / UX design for each device. This makes it possible to provide a display format optimized for different devices.

[0080] The classification unit can recommend related products that the user is likely to be interested in when presenting the results. For example, the classification unit recommends related products that the user is likely to be interested in when presenting the results. For example, it recommends products in the same category. The classification unit can also recommend related products based on the user's past purchase history. For example, it recommends products related to products that the user has previously purchased. This makes it possible to recommend related products that the user is likely to be interested in.

[0081] The classification unit uses the emotion estimation function to analyze the user's emotional response in real time when the results are presented, and can provide improvement suggestions and support information to users who have negative emotions. The classification unit, for example, uses the emotion estimation function to analyze the user's emotional response in real time when the results are presented, and can provide improvement suggestions and support information to users who have negative emotions. For example, it displays usage advice. The classification unit can also provide customer support contact information to users who have negative emotions. For example, it displays contact information for the support desk. This makes it possible to provide improvement suggestions and support information to users who have negative emotions.

[0082] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0083] The review data collection unit collects user location information, and the preprocessing unit can classify reviews by region based on the location information. For example, the review data collection unit acquires the user's IP address and GPS data to collect location information. The preprocessing unit can also classify reviews by region based on the collected location information. For example, it can separate reviews from urban areas from reviews from rural areas. The preprocessing unit can also prioritize preprocessing of reviews from specific regions based on the location information. This allows for detailed analysis of reviews by region.

[0084] The preprocessing unit can analyze the social media accounts of the posters of the review data and prioritize preprocessing of reviews from highly reliable accounts. For example, the preprocessing unit can analyze the number of followers and posting frequency of the posters to identify highly reliable accounts. The preprocessing unit can also prioritize preprocessing of highly reliable accounts based on engagement rates on social media. For example, the number of likes and shares can be analyzed. This allows highly reliable reviews to be prioritized preprocessing.

[0085] The preprocessing unit can use the emotion estimation function to analyze the user's emotion at the time of posting the review data and filter out reviews with negative emotions. For example, the preprocessing unit can use the emotion estimation function to analyze the user's emotion at the time of posting the review in real time and filter out reviews with negative emotions. The preprocessing unit can also use the emotion estimation function to preferentially preprocess reviews with positive emotions. For example, it can place emphasis on reviews with a strong sense of joy or satisfaction. This makes it possible to filter out reviews with negative emotions.

[0086] The preprocessing unit can analyze the purchase history of the poster of the review data and prioritize preprocessing of reviews from users who actually purchased the product. For example, the preprocessing unit acquires purchase history data from an e-commerce site and identifies reviews from users who actually purchased the product. The preprocessing unit can also prioritize preprocessing of highly reliable reviews based on the purchase history. For example, it places emphasis on reviews from users who have purchased the same product multiple times in the past. This allows reviews from users who actually purchased the product to be prioritized preprocessing.

[0087] The word-of-mouth data collection unit simultaneously collects voice data, and the preprocessing unit can convert the voice data into text and perform preprocessing. For example, the word-of-mouth data collection unit uses a voice input function to collect users' voice word-of-mouth. The preprocessing unit can also convert the voice data into text and perform preprocessing as text data. For example, the voice data is converted into text using voice recognition technology. This allows preprocessing to be performed based on the voice data.

[0088] The review data collection unit can integrate review data from different social media platforms, and the preprocessing unit can preprocess the integrated review data. For example, the review data collection unit can collect data from multiple social media platforms such as Twitter and Instagram. The review data collection unit can also collect and integrate review data in different languages. For example, it can collect and integrate review data in English and Spanish. The preprocessing unit can preprocess the integrated review data. For example, it can convert data collected from different platforms into a consistent format. The preprocessing unit can also translate data in different languages ​​and convert it into a consistent format. This makes it possible to integrate review data from different social media platforms and build a comprehensive dataset.

[0089] The classification unit can use the emotion estimation function to analyze the emotional nuances of the review data and perform rating classification based on emotions. For example, the classification unit can use the emotion estimation function to analyze the emotional nuances of the review data and separate reviews with positive emotions from reviews with negative emotions. The classification unit can also perform classification based on the intensity of emotions. For example, it can separate reviews with strong positive emotions from reviews with weak positive emotions. This allows rating classification based on emotions.

[0090] When classifying the review data, the classification unit takes into account attribute information such as the poster's age and gender, and can extract ratings that are appropriate for the target user. For example, when classifying the review data, the classification unit takes into account attribute information such as the poster's age and gender. For example, the classification unit separates ratings from younger people and older people. The classification unit can also take into account differences in ratings based on gender. For example, the classification unit separates ratings from males and females. This makes it possible to extract ratings that are appropriate for the target user.

[0091] The classification unit can use the emotion estimation function to analyze emotional elements included in the post-use evaluations and perform summarization based on emotions. For example, the classification unit can use the emotion estimation function to analyze emotional elements included in the post-use evaluations and separate evaluations with positive emotions from evaluations with negative emotions. The classification unit can also perform summarization based on the intensity of emotions. For example, the classification unit can separate evaluations with strong positive emotions from evaluations with weak positive emotions. This allows for summarization based on emotions.

[0092] The classification unit can visualize the post-use evaluations and visually present them in the form of graphs or charts. For example, the classification unit visualizes the post-use evaluations and visually presents them in the form of graphs or charts. For example, the distribution and trend of the evaluations can be displayed in a bar graph or pie chart. The classification unit can also display fluctuations in the evaluations in a line graph. For example, the fluctuations in the evaluations can be displayed in a time series. In this way, the post-use evaluations can be visually presented.

[0093] The processing flow of the second embodiment will be briefly explained below.

[0094] Step 1: The review data collection unit collects review data from the e-commerce site. For example, review data can be automatically collected from the e-commerce site using an API. Review data can also be collected using web scraping technology. When using an API, the review data collection unit sends a request to the API endpoint of the e-commerce site and obtains the review data returned as a response. When using web scraping technology, the review data collection unit analyzes the HTML structure of the e-commerce site and extracts the review data. Step 2: The preprocessing unit preprocesses the word-of-mouth data collected by the word-of-mouth data collection unit. For example, the preprocessing unit cleans the text and removes unnecessary information. The preprocessing unit also performs tokenization to convert the text data into a format that is easy to analyze. It removes HTML tags and special characters to make the text data clean. When tokenizing, the preprocessing unit divides the text data into words and converts it into a format suitable for analysis. Step 3: The classification unit classifies the review data preprocessed by the preprocessing unit into pre-use evaluations and post-use evaluations. For example, the generation AI is used to analyze the review data and automatically classify it into pre-use evaluations and post-use evaluations. Natural language processing technology is also used to analyze the review data and classify the evaluations. The generation AI uses text generation AI (e.g., GPT-3) to analyze the review data and classify it into pre-use evaluations and post-use evaluations. When natural language processing technology is used, the classification unit analyzes the context of the text data and classifies the evaluations.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0099] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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).

[0104] 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.

[0105] 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.

[0106] 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.

[0107] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0108] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

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

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

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

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

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

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

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

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

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

[0122] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

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

[0126] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt 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.

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

[0128] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0139] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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."

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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]

[0162] 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 word-of-mouth data collection department that collects word-of-mouth data from e-commerce sites; a preprocessing unit that preprocesses the word-of-mouth data collected by the word-of-mouth data collection unit; a classification unit that classifies the word-of-mouth data preprocessed by the preprocessing unit into pre-use evaluations and post-use evaluations. A system characterized by:

2. The word-of-mouth data collection unit It also collects metadata for images and videos. The pre-treatment unit Preprocessing is performed based on the metadata of the images and videos.

2. The system of claim 1.

3. The classification unit Generative AI is used to analyze the context of the review data and classify it based on not only pre- and post-use evaluations but also the duration and frequency of use.

2. The system of claim 1.

4. The classification unit Using generative AI to perform detailed analysis of specific issues within post-use evaluations and identify the root cause of the issues 2. The system of claim 1.

5. The classification unit Analyze the user's emotional response when presenting the results and adopt a presentation method that elicits positive emotions.

2. The system of claim 1.

6. The pre-treatment unit Analyze the user's emotions when posting the review data, and prioritize preprocess reviews with positive emotions.

2. The system of claim 1.

Images