System

Abstract

An object of the system according to the embodiment is to analyze reviews in various formats and provide customized information based on the user's preference.SOLUTION: A system includes a review acquisition unit, an analysis unit, a customization unit, and an interaction unit. The review acquisition unit acquires a review. The analysis unit analyzes the review acquired by the review acquisition unit. The customization unit customizes the review on the basis of the result analyzed by the analysis unit. The interaction unit provides the review customized by the customization unit to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of not being able to centrally analyze reviews in a variety of formats and provide information customized based on user preferences.

[0005] The system according to the embodiment aims to analyze reviews in various formats and provide customized information based on the user's preferences. [Means for solving the problem]

[0006] A system according to an embodiment includes a review acquisition unit, an analysis unit, a customization unit, and a dialogue unit. The review acquisition unit acquires reviews. The analysis unit analyzes the reviews acquired by the review acquisition unit. The customization unit customizes the reviews based on the results of the analysis by the analysis unit. The dialogue unit provides the reviews customized by the customization unit to a user. [Effects of the Invention]

[0007] The system according to the embodiment can analyze reviews in various formats and provide customized information based on the user's preferences. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The AI ​​Multimodal Review Summarizer according to an embodiment of the present invention is a system that utilizes Gemini's multimodal AI technology, SB's AI technology, and big data to analyze and summarize product reviews, helping consumers make seamless product selections. As a result, the AI ​​Multimodal Review Summarizer can provide a new experience that enables consumers to make product selections quickly and easily.

[0029] The AI ​​Multimodal Review Summarizer according to the embodiment includes a review acquisition unit, an analysis unit, a customization unit, and a dialogue unit. The review acquisition unit acquires reviews. For example, it can acquire text reviews, audio reviews, and video reviews. The review acquisition unit can also automatically collect reviews posted by users. Furthermore, the review acquisition unit can acquire reviews in real time. For example, the review acquisition unit collects reviews from websites and social media. It uses an API to automatically collect reviews posted by users. To acquire reviews in real time, streaming data processing technology is used. The analysis unit analyzes the reviews acquired by the review acquisition unit. For example, it performs sentiment analysis, content analysis, and statistical analysis. The analysis unit can also execute an algorithm to evaluate the reliability of reviews. Furthermore, the analysis unit can analyze review trends. For example, the sentiment analysis analyzes the text data of reviews and classifies them into positive, negative, and neutral sentiments. The content analysis extracts keywords and phrases from reviews and identifies important information. The statistical analysis aggregates the review evaluation scores and posting frequency to generate statistical data. The customization unit customizes the reviews based on the results of the analysis by the analysis unit. For example, the customization unit filters the reviews based on the user's preferences. The customization unit can also customize the reviews by taking into account past purchase history and reactions to reviews. Furthermore, the customization unit can personalize the reviews based on user behavior data. For example, the customization unit can preferentially display reviews of specific brands or products based on the user's preferences. The customization unit can recommend reviews of related products based on the user's past purchase history. The customization unit can display the most relevant reviews based on the user's behavior data. The dialogue unit provides the user with the reviews customized by the customization unit. For example, the dialogue unit can use a chatbot to interact with the user and provide the reviews. The dialogue unit can also provide a summary of the review in response to a user's question. Furthermore, the dialogue unit can generate a response according to the user's emotions.For example, a chatbot can be used to instantly request the information a user needs. It can automatically generate and provide summaries of related reviews in response to a user's question. It can generate positive or negative responses depending on the user's emotions. This allows the AI ​​Multimodal Review Summarizer according to the embodiment to seamlessly acquire, analyze, customize, and provide reviews.

[0030] The analysis unit can automatically detect usage scenes of a specific product in a video review and link them to text reviews related to those scenes. The analysis unit, for example, develops an algorithm that automatically detects usage scenes of a specific product in a video review. For example, it uses image recognition technology to identify scenes in which the product appears. The analysis unit also builds a system that links text reviews related to the detected usage scenes. For example, it automatically associates text reviews about the same product. The analysis unit also builds a database for linking usage scenes and text reviews. For example, it associates the video timestamp with the text review ID. This makes it possible to associate video reviews with text reviews.

[0031] The customization unit can automatically recommend reviews of related products based on the user's purchasing history. For example, the customization unit analyzes the user's purchasing history and develops an algorithm that automatically recommends reviews of related products. For example, it recommends reviews of products similar to products purchased in the past. The customization unit also builds a system that learns the user's preferences based on the purchasing history. For example, it analyzes the frequency and timing of purchases. The customization unit also builds a database for recommending reviews of related products. For example, it links the purchasing history with the reviews. This makes it possible to recommend reviews based on the user's purchasing history.

[0032] The dialogue unit enables the chatbot to learn the user's past dialogue history and provide more personalized responses. The dialogue unit, for example, develops a system that enables the chatbot to learn the user's past dialogue history. For example, it analyzes the content of past dialogues and learns the user's preferences and interests. The dialogue unit also develops an algorithm that provides more personalized responses based on the learning results. For example, it provides related information based on the user's past questions. The dialogue unit also builds a database for providing personalized responses. For example, it links the dialogue history with response messages. This makes it possible to provide personalized responses based on the user's past dialogue history.

[0033] The dialogue unit can add a voice recognition function to the chatbot to realize product selection support through voice dialogue. The dialogue unit, for example, develops a system that adds a voice recognition function to the chatbot. For example, the dialogue unit converts a user's voice input into text and the chatbot responds. The dialogue unit also develops an algorithm that realizes product selection support through voice dialogue. For example, it provides related product information based on the voice input. The dialogue unit also builds a database for product selection support using the voice recognition function. For example, it links the voice input with corresponding product information. This makes it possible to provide product selection support through voice dialogue.

[0034] The dialogue unit enables the chatbot to automatically generate and provide summaries of reviews related to a user's question. The dialogue unit, for example, develops a system that enables the chatbot to automatically generate summaries of reviews related to a user's question. For example, it analyzes the content of the review using natural language processing technology and generates a summary. The dialogue unit also develops an algorithm that provides the automatically generated summary to the user. For example, it selects the optimal summary based on the content of the user's question. The dialogue unit also builds a database for automatically generating review summaries. For example, it links the review content with the summary. This makes it possible to automatically generate and provide summaries of reviews related to a user's question.

[0035] The customization unit can dynamically change the display order of reviews based on user preferences, displaying the most relevant reviews at the top. The customization unit, for example, learns user preferences and develops an algorithm that dynamically changes the display order of reviews. For example, the display order is determined based on past browsing history and purchase history. The customization unit also builds a system that provides the dynamically changed display order to the user. For example, the display order is updated in real time. The customization unit also builds a database for dynamically changing the display order of reviews. For example, the customization unit links user preference data with reviews. This makes it possible to dynamically change the display order of reviews based on user preferences.

[0036] The customization unit can personalize review summaries based on user preferences and highlight information that interests the user most. For example, the customization unit develops an algorithm that learns user preferences and personalizes review summaries. For example, the customization unit adjusts the summary content based on past browsing history and purchase history. The customization unit also builds a system that provides personalized summaries to users. For example, the customization unit highlights information that interests the user most. The customization unit also builds a database for personalizing review summaries. For example, the customization unit links user preference data with summaries. This makes it possible to personalize review summaries based on user preferences.

[0037] The customization unit customizes the detailed evaluation of a review based on the user's preferences, allowing the user to provide the most relevant information. The customization unit, for example, develops a system that customizes the detailed evaluation of a review based on the user's preferences. For example, the content of the evaluation is adjusted based on the user's past browsing history and purchase history. The customization unit also develops an algorithm that provides the user with customized evaluations. For example, the customization unit displays the optimal evaluation based on the user's preferences. The customization unit also builds a database for customizing the detailed evaluation of a review. For example, the customization unit links the user's preference data with the evaluation content. This makes it possible to customize the detailed evaluation based on the user's preferences.

[0038] The customization department can provide review summaries in different formats (e.g., visual notes or infographics) to make them easier for users to understand visually. For example, the customization department develops a system that provides review summaries in visual note or infographic format. For example, it shows important points with diagrams or icons. The customization department also develops an algorithm that automatically generates visual notes and infographics. For example, it adds visual elements based on the summary text. The customization department also builds a database for providing visual notes and infographics. For example, it links the summary text with corresponding visual elements. This makes it possible to provide review summaries in different formats.

[0039] The customization unit can integrate the detailed evaluation of a review with feedback from other users to provide an overall evaluation. The customization unit, for example, develops a system that integrates the detailed evaluation of a review with feedback from other users. For example, it analyzes "likes" and comments on a review to calculate an overall evaluation. The customization unit also develops an algorithm that provides an overall evaluation based on feedback from other users. For example, it gives a high rating to reviews with a lot of positive feedback. The customization unit also builds a database for providing an overall evaluation. For example, it links the review content with the feedback. This makes it possible to provide an overall evaluation that integrates feedback from other users.

[0040] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0041] The review acquisition unit may use an API to automatically collect reviews posted by users. The review acquisition unit may also use streaming data processing technology to acquire reviews in real time. The review acquisition unit may also collect reviews from websites and social media. The analysis unit may analyze the reviews acquired by the review acquisition unit. For example, the analysis unit may perform sentiment analysis, content analysis, and statistical analysis. The analysis unit may also execute an algorithm to evaluate the reliability of the reviews. The analysis unit may also analyze review trends. The customization unit may customize the reviews based on the results of the analysis by the analysis unit. For example, the reviews may be filtered based on user preferences. The customization unit may also customize the reviews by taking into account past purchase history and reactions to reviews. The customization unit may also personalize the reviews based on user behavior data. The dialogue unit may provide the reviews customized by the customization unit to the user. For example, the dialogue unit may use a chatbot to interact with the user and provide the reviews. The dialogue unit may also provide a summary of the reviews in response to a user's question. The dialogue unit may also generate a response according to the user's emotions.

[0042] The analysis unit can automatically detect usage scenes of a specific product in a video review and link those scenes to text reviews related to that scene. For example, image recognition technology can be used to identify scenes in which a product appears. The analysis unit can also build a system that links text reviews related to the detected usage scenes. For example, it can automatically associate text reviews about the same product. Furthermore, the analysis unit can build a database for linking usage scenes and text reviews. For example, it can associate a video timestamp with a text review ID.

[0043] The customization unit can automatically recommend reviews of related products based on the user's purchase history. For example, it can recommend reviews of products similar to products previously purchased. The customization unit can also build a system that learns the user's preferences based on the purchase history. For example, it can analyze purchase frequency and purchase timing. Furthermore, the customization unit can build a database for recommending reviews of related products. For example, it can link purchase history with reviews.

[0044] The dialogue unit enables the chatbot to learn the user's past dialogue history and provide more personalized responses. For example, it can analyze the content of past dialogues and learn the user's preferences and interests. The dialogue unit can also develop an algorithm to provide more personalized responses based on the learning results. For example, it can provide related information based on the user's past questions. Furthermore, the dialogue unit can build a database for providing personalized responses. For example, it can link the dialogue history with response messages.

[0045] The dialogue unit can add a voice recognition function to the chatbot to realize product selection support through voice dialogue. For example, the chatbot can convert a user's voice input into text and respond. The dialogue unit can also develop an algorithm to realize product selection support through voice dialogue. For example, it can provide related product information based on the voice input. Furthermore, the dialogue unit can build a database for product selection support using the voice recognition function. For example, it can link the voice input with corresponding product information.

[0046] The processing flow of the first embodiment will be briefly explained below.

[0047] Step 1: The review acquisition unit acquires reviews. For example, it can acquire text reviews, audio reviews, and video reviews. The review acquisition unit can also automatically collect reviews posted by users. Furthermore, the review acquisition unit can acquire reviews in real time. For example, the review acquisition unit collects reviews from websites and social media. It uses an API to automatically collect reviews posted by users. To acquire reviews in real time, it uses streaming data processing technology. Step 2: The analysis unit analyzes the reviews acquired by the review acquisition unit. For example, it performs sentiment analysis, content analysis, and statistical analysis. The analysis unit can also execute algorithms to evaluate the reliability of reviews. Furthermore, the analysis unit can analyze review trends. For example, sentiment analysis involves analyzing the text data of reviews and classifying them into positive, negative, and neutral sentiments. Content analysis involves extracting keywords and phrases from reviews and identifying important information. Statistical analysis involves aggregating review evaluation scores and posting frequency to generate statistical data. Step 3: The customization unit customizes the reviews based on the results of the analysis by the analysis unit. For example, it filters reviews based on the user's preferences. The customization unit can also customize reviews by taking into account past purchase history and reactions to reviews. Furthermore, the customization unit can personalize the reviews based on user behavior data. For example, it can prioritize and display reviews of specific brands or products based on the user's preferences. It can recommend reviews of related products based on the user's past purchase history. It can display the most relevant reviews based on the user's behavior data. Step 4: The dialogue unit provides the user with the review customized by the customization unit. For example, the dialogue unit uses a chatbot to dialogue with the user and provide the review. The dialogue unit can also provide a summary of the review in response to the user's question. Furthermore, the dialogue unit can generate a response according to the user's emotions. For example, the chatbot can be used to allow the user to instantly request the information they need. In response to the user's question, the dialogue unit automatically generates and provides a summary of related reviews. A positive or negative response is generated according to the user's emotions.

[0048] (Example 2) The AI ​​Multimodal Review Summarizer according to an embodiment of the present invention is a system that utilizes Gemini's multimodal AI technology, SB's AI technology, and big data to analyze and summarize product reviews, helping consumers make seamless product selections. As a result, the AI ​​Multimodal Review Summarizer can provide a new experience that enables consumers to make product selections quickly and easily.

[0049] The AI ​​Multimodal Review Summarizer according to the embodiment includes a review acquisition unit, an analysis unit, a customization unit, and a dialogue unit. The review acquisition unit acquires reviews. For example, it can acquire text reviews, audio reviews, and video reviews. The review acquisition unit can also automatically collect reviews posted by users. Furthermore, the review acquisition unit can acquire reviews in real time. For example, the review acquisition unit collects reviews from websites and social media. It uses an API to automatically collect reviews posted by users. To acquire reviews in real time, streaming data processing technology is used. The analysis unit analyzes the reviews acquired by the review acquisition unit. For example, it performs sentiment analysis, content analysis, and statistical analysis. The analysis unit can also execute an algorithm to evaluate the reliability of reviews. Furthermore, the analysis unit can analyze review trends. For example, the sentiment analysis analyzes the text data of reviews and classifies them into positive, negative, and neutral sentiments. The content analysis extracts keywords and phrases from reviews and identifies important information. The statistical analysis aggregates the review evaluation scores and posting frequency to generate statistical data. The customization unit customizes the reviews based on the results of the analysis by the analysis unit. For example, the customization unit filters the reviews based on the user's preferences. The customization unit can also customize the reviews by taking into account past purchase history and reactions to reviews. Furthermore, the customization unit can personalize the reviews based on user behavior data. For example, the customization unit can preferentially display reviews of specific brands or products based on the user's preferences. The customization unit can recommend reviews of related products based on the user's past purchase history. The customization unit can display the most relevant reviews based on the user's behavior data. The dialogue unit provides the user with the reviews customized by the customization unit. For example, the dialogue unit can use a chatbot to interact with the user and provide the reviews. The dialogue unit can also provide a summary of the review in response to a user's question. Furthermore, the dialogue unit can generate a response according to the user's emotions.For example, a chatbot can be used to instantly request the information a user needs. It can automatically generate and provide summaries of related reviews in response to a user's question. It can generate positive or negative responses depending on the user's emotions. This allows the AI ​​Multimodal Review Summarizer according to the embodiment to seamlessly acquire, analyze, customize, and provide reviews.

[0050] The analysis unit can analyze the audio data of reviews and estimate the speaker's emotions. The analysis unit, for example, collects audio data of product reviews and develops an algorithm for estimating the speaker's emotions. For example, it analyzes changes in the tone and pitch of the voice and quantifies the speaker's emotions. The analysis unit also builds a system for evaluating the reliability of reviews based on the speaker's emotional changes. For example, it rates reviews with stable emotions highly and reviews with greatly fluctuating emotions poorly. The analysis unit also builds a database for reflecting the emotion estimation results in the review reliability evaluation. For example, it stores the emotion score as review metadata and uses it in the reliability evaluation. This makes it possible to estimate emotions to evaluate the reliability of reviews.

[0051] The analysis unit can automatically detect usage scenes of a specific product in a video review and link them to text reviews related to those scenes. The analysis unit, for example, develops an algorithm that automatically detects usage scenes of a specific product in a video review. For example, it uses image recognition technology to identify scenes in which the product appears. The analysis unit also builds a system that links text reviews related to the detected usage scenes. For example, it automatically associates text reviews about the same product. The analysis unit also builds a database for linking usage scenes and text reviews. For example, it associates the video timestamp with the text review ID. This makes it possible to associate video reviews with text reviews.

[0052] The analysis unit can use the emotion estimation function to highlight the parts of a video review that interest the user most and reflect them in the summary. The analysis unit, for example, develops an emotion estimation algorithm to highlight the parts of a video review that interest the user most. For example, it identifies scenes of high interest using eye tracking and facial expression analysis. The analysis unit also builds a system to reflect the highlighted parts in the summary. For example, it automatically incorporates scenes of high interest into the summary. The analysis unit also builds a database to reflect the emotion estimation results in the summary. For example, it uses the emotion score to generate the summary. This makes it possible to create summaries that reflect the user's interests.

[0053] The customization unit can analyze users' responses to past reviews and use an emotion estimation function to preferentially display reviews that showed positive responses. The customization unit, for example, develops a system that analyzes users' responses to past reviews. For example, it analyzes "likes" and comments on reviews. The customization unit also uses the emotion estimation function to develop an algorithm that preferentially displays reviews that showed positive responses. For example, it determines the display order of reviews based on emotion scores. The customization unit also builds a database for preferentially displaying reviews that showed positive responses. For example, it stores the emotion scores as review metadata. This makes it possible to display reviews based on user preferences.

[0054] The customization unit can automatically recommend reviews of related products based on the user's purchasing history. For example, the customization unit analyzes the user's purchasing history and develops an algorithm that automatically recommends reviews of related products. For example, it recommends reviews of products similar to products purchased in the past. The customization unit also builds a system that learns the user's preferences based on the purchasing history. For example, it analyzes the frequency and timing of purchases. The customization unit also builds a database for recommending reviews of related products. For example, it links the purchasing history with the reviews. This makes it possible to recommend reviews based on the user's purchasing history.

[0055] The dialogue unit equips the chatbot with an emotion estimation function, enabling it to generate responses according to the user's emotions. The dialogue unit, for example, develops a system that equips the chatbot with the emotion estimation function. For example, it analyzes the user's input text and voice and calculates an emotion score. The dialogue unit also develops an algorithm that generates responses according to the user's emotions based on the emotion estimation results. For example, it generates an encouraging message for positive emotions and a comforting message for negative emotions. The dialogue unit also builds a database for generating responses according to emotions. For example, it links the emotion score with the corresponding response message. This makes it possible to provide responses according to the user's emotions.

[0056] The dialogue unit enables the chatbot to learn the user's past dialogue history and provide more personalized responses. The dialogue unit, for example, develops a system that enables the chatbot to learn the user's past dialogue history. For example, it analyzes the content of past dialogues and learns the user's preferences and interests. The dialogue unit also develops an algorithm that provides more personalized responses based on the learning results. For example, it provides related information based on the user's past questions. The dialogue unit also builds a database for providing personalized responses. For example, it links the dialogue history with response messages. This makes it possible to provide personalized responses based on the user's past dialogue history.

[0057] The dialogue unit uses the emotion estimation function to analyze the emotions felt by the user during a dialogue in real time and make appropriate product suggestions. The dialogue unit, for example, uses the emotion estimation function to develop a system that analyzes the emotions felt by the user during a dialogue in real time. For example, the dialogue unit analyzes the user's input text and voice and calculates an emotion score. The dialogue unit also develops an algorithm that makes appropriate product suggestions based on the emotion analysis results. For example, it suggests related products to users who show positive emotions and provides alternative options to users who show negative emotions. The dialogue unit also builds a database for making product suggestions based on emotions. For example, it links the emotion score with corresponding product information. This makes it possible to make product suggestions based on the user's emotions.

[0058] The dialogue unit can add a voice recognition function to the chatbot to realize product selection support through voice dialogue. The dialogue unit, for example, develops a system that adds a voice recognition function to the chatbot. For example, the dialogue unit converts a user's voice input into text and the chatbot responds. The dialogue unit also develops an algorithm that realizes product selection support through voice dialogue. For example, it provides related product information based on the voice input. The dialogue unit also builds a database for product selection support using the voice recognition function. For example, it links the voice input with corresponding product information. This makes it possible to provide product selection support through voice dialogue.

[0059] The dialogue unit enables the chatbot to automatically generate and provide summaries of reviews related to a user's question. The dialogue unit, for example, develops a system that enables the chatbot to automatically generate summaries of reviews related to a user's question. For example, it analyzes the content of the review using natural language processing technology and generates a summary. The dialogue unit also develops an algorithm that provides the automatically generated summary to the user. For example, it selects the optimal summary based on the content of the user's question. The dialogue unit also builds a database for automatically generating review summaries. For example, it links the review content with the summary. This makes it possible to automatically generate and provide summaries of reviews related to a user's question.

[0060] The dialogue unit can use the emotion estimation function to preferentially suggest products that indicate the most positive emotion for the user during a dialogue. The dialogue unit, for example, uses the emotion estimation function to develop a system that preferentially suggests products that indicate the most positive emotion for the user during a dialogue. For example, the dialogue unit analyzes the user's input text or voice and calculates an emotion score. The dialogue unit also develops an algorithm that preferentially suggests products that indicate positive emotion based on the emotion analysis results. For example, products with high emotion scores are preferentially displayed. The dialogue unit also builds a database for suggesting products that indicate positive emotion. For example, the emotion score is linked to corresponding product information. This makes it possible to suggest products based on the user's positive emotion.

[0061] The customization unit can dynamically change the display order of reviews based on user preferences, displaying the most relevant reviews at the top. The customization unit, for example, learns user preferences and develops an algorithm that dynamically changes the display order of reviews. For example, the display order is determined based on past browsing history and purchase history. The customization unit also builds a system that provides the dynamically changed display order to the user. For example, the display order is updated in real time. The customization unit also builds a database for dynamically changing the display order of reviews. For example, the customization unit links user preference data with reviews. This makes it possible to dynamically change the display order of reviews based on user preferences.

[0062] The customization unit can personalize review summaries based on user preferences and highlight information that interests the user most. For example, the customization unit develops an algorithm that learns user preferences and personalizes review summaries. For example, the customization unit adjusts the summary content based on past browsing history and purchase history. The customization unit also builds a system that provides personalized summaries to users. For example, the customization unit highlights information that interests the user most. The customization unit also builds a database for personalizing review summaries. For example, the customization unit links user preference data with summaries. This makes it possible to personalize review summaries based on user preferences.

[0063] The customization unit can use the emotion estimation function to automatically select and notify the user of the reviews that interest them most. The customization unit, for example, uses the emotion estimation function to develop an algorithm that automatically selects the reviews that interest the user most. For example, it analyzes facial expressions and voice when reading reviews. The customization unit also builds a system that notifies the user of the selected reviews. For example, it uses push notifications or email notifications. The customization unit also builds a database for selecting the reviews that interest the user most. For example, it stores emotion scores in a user profile. This makes it possible to select and notify reviews based on the user's interests.

[0064] The customization unit customizes the detailed evaluation of a review based on the user's preferences, allowing the user to provide the most relevant information. The customization unit, for example, develops a system that customizes the detailed evaluation of a review based on the user's preferences. For example, the content of the evaluation is adjusted based on the user's past browsing history and purchase history. The customization unit also develops an algorithm that provides the user with customized evaluations. For example, the customization unit displays the optimal evaluation based on the user's preferences. The customization unit also builds a database for customizing the detailed evaluation of a review. For example, the customization unit links the user's preference data with the evaluation content. This makes it possible to customize the detailed evaluation based on the user's preferences.

[0065] The customization unit can use the emotion estimation function to extract parts of a review that evoke the most positive emotions in the user and reflect them in a summary. The customization unit, for example, develops a system that uses the emotion estimation function to extract parts of a review that evoke the most positive emotions in the user. For example, it analyzes emotion scores of speech or text. The customization unit also develops an algorithm that reflects the extracted positive emotion parts in a summary. For example, it incorporates parts with high emotion scores into a summary. The customization unit also builds a database for reflecting the positive emotion parts in a summary. For example, it uses the emotion scores to generate a summary. This makes it possible to summarize reviews based on the user's positive emotions.

[0066] The customization department can provide review summaries in different formats (e.g., visual notes or infographics) to make them easier for users to understand visually. For example, the customization department develops a system that provides review summaries in visual note or infographic format. For example, it shows important points with diagrams or icons. The customization department also develops an algorithm that automatically generates visual notes and infographics. For example, it adds visual elements based on the summary text. The customization department also builds a database for providing visual notes and infographics. For example, it links the summary text with corresponding visual elements. This makes it possible to provide review summaries in different formats.

[0067] The customization unit can integrate the detailed evaluation of a review with feedback from other users to provide an overall evaluation. The customization unit, for example, develops a system that integrates the detailed evaluation of a review with feedback from other users. For example, it analyzes "likes" and comments on a review to calculate an overall evaluation. The customization unit also develops an algorithm that provides an overall evaluation based on feedback from other users. For example, it gives a high rating to reviews with a lot of positive feedback. The customization unit also builds a database for providing an overall evaluation. For example, it links the review content with the feedback. This makes it possible to provide an overall evaluation that integrates feedback from other users.

[0068] The customization unit can use the emotion estimation function to automatically select and notify the user of the reviews that interest them most. The customization unit, for example, uses the emotion estimation function to develop an algorithm that automatically selects the reviews that interest the user most. For example, it analyzes facial expressions and voice when reading reviews. The customization unit also builds a system that notifies the user of the selected reviews. For example, it uses push notifications or email notifications. The customization unit also builds a database for selecting the reviews that interest the user most. For example, it stores emotion scores in a user profile. This makes it possible to select and notify reviews based on the user's interests.

[0069] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0070] The review acquisition unit may use an API to automatically collect reviews posted by users. The review acquisition unit may also use streaming data processing technology to acquire reviews in real time. The review acquisition unit may also collect reviews from websites and social media. The analysis unit may analyze the reviews acquired by the review acquisition unit. For example, the analysis unit may perform sentiment analysis, content analysis, and statistical analysis. The analysis unit may also execute an algorithm to evaluate the reliability of the reviews. The analysis unit may also analyze review trends. The customization unit may customize the reviews based on the results of the analysis by the analysis unit. For example, the reviews may be filtered based on user preferences. The customization unit may also customize the reviews by taking into account past purchase history and reactions to reviews. The customization unit may also personalize the reviews based on user behavior data. The dialogue unit may provide the reviews customized by the customization unit to the user. For example, the dialogue unit may use a chatbot to interact with the user and provide the reviews. The dialogue unit may also provide a summary of the reviews in response to a user's question. The dialogue unit may also generate a response according to the user's emotions.

[0071] The analysis unit can analyze the audio data of the review and estimate the speaker's emotions. For example, it can analyze changes in the tone and pitch of the voice and quantify the speaker's emotions. The analysis unit can also build a system that evaluates the reliability of reviews based on the speaker's emotional changes. For example, it can rate reviews with stable emotions highly and rate reviews with greatly fluctuating emotions poorly. Furthermore, the analysis unit can build a database to reflect the emotion estimation results in the review reliability evaluation. For example, it can save the emotion score as review metadata and use it in the reliability evaluation.

[0072] The analysis unit can automatically detect usage scenes of a specific product in a video review and link those scenes to text reviews related to that scene. For example, image recognition technology can be used to identify scenes in which a product appears. The analysis unit can also build a system that links text reviews related to the detected usage scenes. For example, it can automatically associate text reviews about the same product. Furthermore, the analysis unit can build a database for linking usage scenes and text reviews. For example, it can associate a video timestamp with a text review ID.

[0073] The analysis unit can use the emotion estimation function to highlight the parts of a video review that users find most interesting and reflect them in the summary. For example, eye tracking and facial expression analysis can be used to identify scenes of high interest. The analysis unit can also build a system that reflects the highlighted parts in the summary. For example, scenes of high interest can be automatically incorporated into the summary. Furthermore, the analysis unit can build a database to reflect the emotion estimation results in the summary. For example, the emotion score can be used to generate the summary.

[0074] The customization unit can analyze users' responses to past reviews and prioritize displaying reviews with positive responses using an emotion estimation function. For example, the customization unit can analyze "likes" and comments on reviews. The customization unit can also use the emotion estimation function to develop an algorithm that prioritizes displaying reviews with positive responses. For example, the customization unit can determine the display order of reviews based on the emotion score. Furthermore, the customization unit can build a database for prioritize displaying reviews with positive responses. For example, the emotion score can be stored as metadata for the review.

[0075] The customization unit can automatically recommend reviews of related products based on the user's purchase history. For example, it can recommend reviews of products similar to products previously purchased. The customization unit can also build a system that learns the user's preferences based on the purchase history. For example, it can analyze purchase frequency and purchase timing. Furthermore, the customization unit can build a database for recommending reviews of related products. For example, it can link purchase history with reviews.

[0076] The dialogue unit can equip the chatbot with an emotion estimation function and generate responses according to the user's emotions. For example, it can analyze the user's input text or voice and calculate an emotion score. The dialogue unit can also develop an algorithm that generates responses according to the user's emotions based on the emotion estimation results. For example, it can generate an encouraging message for positive emotions and a comforting message for negative emotions. Furthermore, the dialogue unit can build a database for generating responses according to emotions. For example, it can link the emotion score with the corresponding response message.

[0077] The dialogue unit enables the chatbot to learn the user's past dialogue history and provide more personalized responses. For example, it can analyze the content of past dialogues and learn the user's preferences and interests. The dialogue unit can also develop an algorithm to provide more personalized responses based on the learning results. For example, it can provide related information based on the user's past questions. Furthermore, the dialogue unit can build a database for providing personalized responses. For example, it can link the dialogue history with response messages.

[0078] The dialogue unit can use the emotion estimation function to analyze the emotions felt by the user during the dialogue in real time and make appropriate product suggestions. For example, it can analyze the user's input text and voice and calculate an emotion score. The dialogue unit can also develop an algorithm to make appropriate product suggestions based on the emotion analysis results. For example, it can suggest related products to users who show positive emotions and provide alternative options to users who show negative emotions. Furthermore, the dialogue unit can build a database for making product suggestions based on emotions. For example, it can link the emotion score with corresponding product information.

[0079] The dialogue unit can add a voice recognition function to the chatbot to realize product selection support through voice dialogue. For example, the chatbot can convert a user's voice input into text and respond. The dialogue unit can also develop an algorithm to realize product selection support through voice dialogue. For example, it can provide related product information based on the voice input. Furthermore, the dialogue unit can build a database for product selection support using the voice recognition function. For example, it can link the voice input with corresponding product information.

[0080] The processing flow of the second embodiment will be briefly explained below.

[0081] Step 1: The review acquisition unit acquires reviews. For example, it can acquire text reviews, audio reviews, and video reviews. The review acquisition unit can also automatically collect reviews posted by users. Furthermore, the review acquisition unit can acquire reviews in real time. For example, the review acquisition unit collects reviews from websites and social media. It uses an API to automatically collect reviews posted by users. To acquire reviews in real time, it uses streaming data processing technology. Step 2: The analysis unit analyzes the reviews acquired by the review acquisition unit. For example, it performs sentiment analysis, content analysis, and statistical analysis. The analysis unit can also execute algorithms to evaluate the reliability of reviews. Furthermore, the analysis unit can analyze review trends. For example, sentiment analysis involves analyzing the text data of reviews and classifying them into positive, negative, and neutral sentiments. Content analysis involves extracting keywords and phrases from reviews and identifying important information. Statistical analysis involves aggregating review evaluation scores and posting frequency to generate statistical data. Step 3: The customization unit customizes the reviews based on the results of the analysis by the analysis unit. For example, it filters reviews based on the user's preferences. The customization unit can also customize reviews by taking into account past purchase history and reactions to reviews. Furthermore, the customization unit can personalize the reviews based on user behavior data. For example, it can prioritize and display reviews of specific brands or products based on the user's preferences. It can recommend reviews of related products based on the user's past purchase history. It can display the most relevant reviews based on the user's behavior data. Step 4: The dialogue unit provides the user with the review customized by the customization unit. For example, the dialogue unit uses a chatbot to dialogue with the user and provide the review. The dialogue unit can also provide a summary of the review in response to the user's question. Furthermore, the dialogue unit can generate a response according to the user's emotions. For example, the chatbot can be used to allow the user to instantly request the information they need. In response to the user's question, the dialogue unit automatically generates and provides a summary of related reviews. A positive or negative response is generated according to the user's emotions.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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).

[0091] 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.

[0092] 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.

[0093] 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.

[0094] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0095] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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).

[0106] 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.

[0107] 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.

[0108] 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.

[0109] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0110] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0126] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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."

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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]

[0149] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a review acquisition unit that acquires reviews; an analysis unit that analyzes the reviews acquired by the review acquisition unit; a customization unit that customizes the reviews based on the results of the analysis by the analysis unit; a dialogue unit that provides the review customized by the customization unit to the user. A system characterized by:

2. The analysis unit Analyze the audio data of the review and estimate the speaker's emotions 2. The system of claim 1.

3. The analysis unit Automatically detect scenes in video reviews where a specific product is used and link them to related text reviews 2. The system of claim 1.

4. The analysis unit Highlight the parts of the video review that interest the user most and reflect them in the summary 2. The system of claim 1.

5. The customization unit Analyze the user's responses to past reviews and prioritize reviews that have positive responses.

2. The system of claim 1.

Images