System

Abstract

An object of a system according to an embodiment is to extract and present reliable information from an enormous amount of word-of-mouth information on the web.SOLUTION: A system according to an embodiment includes a word-of-mouth information collection unit, a learning unit, a filtering unit, and a presentation unit. The word-of-mouth information collection unit collects a plurality of pieces of word-of-mouth information on the web. The learning unit learns the word-of-mouth information collected by the word-of-mouth information collection unit. The filtering unit filters the malicious word-of-mouth information based on the data learned by the learning unit. The presenter presents the reliable word-of-mouth information filtered by the filter.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has faced the challenge of making it difficult to efficiently extract reliable information from the vast amount of word-of-mouth information available on the web.

[0005] The system according to the embodiment aims to extract and present reliable information from the vast amount of word-of-mouth information available on the web. [Means for solving the problem]

[0006] The system according to the embodiment includes a word-of-mouth information collection unit, a learning unit, a filtering unit, and a presentation unit. The word-of-mouth information collection unit collects multiple pieces of word-of-mouth information on the web. The learning unit learns the word-of-mouth information collected by the word-of-mouth information collection unit. The filtering unit filters out malicious word-of-mouth information based on the data learned by the learning unit. The presentation unit presents reliable word-of-mouth information filtered by the filtering unit. [Effects of the Invention]

[0007] The system according to the embodiment can extract and present reliable information from the vast amount of word-of-mouth information available on the web. [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 review filtering system according to an embodiment of the present invention uses a generation AI to learn from a vast amount of review information, filter out malicious reviews, and present only reliable reviews. This allows the review filtering system to provide an environment in which users can select products and services with peace of mind.

[0029] A review filtering system according to an embodiment includes a review information collection unit, a learning unit, a filtering unit, and a presentation unit. The review information collection unit collects multiple pieces of review information from the web. For example, it collects reviews in text format. It can also collect reviews in image and video format. Furthermore, the review information collection unit can automatically translate and collect reviews in different languages. For example, it can translate English reviews into Japanese and collect them. The learning unit learns the collected review information. For example, the generation AI analyzes the content of the review, the poster's history, posting frequency, language patterns, etc. The generation AI can also analyze the poster's past purchasing history and behavioral patterns to evaluate trustworthiness. Furthermore, the generation AI can collect external data, such as the poster's social media activity and number of followers, to increase trustworthiness. The filtering unit filters malicious reviews based on the learned data. For example, it detects and excludes reviews that are defamatory, misrepresentative, or likely to be stealth marketing. The filtering unit can also identify malicious reviews by considering the poster's past posting history and ratings from other users. Furthermore, the filtering unit can analyze not only the content of reviews but also the timing and frequency of posting to detect abnormal patterns. The presentation unit presents filtered, reliable reviews. For example, if the generation AI determines that a review saying "This product is very easy to use" is reliable, it preferentially displays that review. The presentation unit can also add ratings and comments from other users to reviews determined to be reliable, further increasing their reliability. Furthermore, the presentation unit can present reliable reviews not only in text format but also in infographics and video formats, making them easier to understand visually. As a result, the review filtering system according to the embodiment efficiently collects vast amounts of review information and presents only reliable reviews, allowing users to select products and services with confidence.

[0030] The learning unit can analyze the poster's past purchasing history and behavioral patterns to evaluate reliability. For example, the learning unit analyzes the poster's past purchasing history for the review information collected by the generation AI to evaluate reliability. For example, it rates highly reviews by posters who have purchased the same product multiple times in the past. The learning unit also analyzes the poster's behavioral patterns for the review information collected by the generation AI to evaluate reliability. For example, it rates highly reviews by posters who post reviews frequently but whose content is consistent. The learning unit also analyzes the poster's purchasing history and behavioral patterns in combination for the review information collected by the generation AI to evaluate reliability. For example, it rates highly reviews by posters whose past purchasing history and behavioral patterns match. In this way, the reliability of reviews can be increased by analyzing the poster's past purchasing history and behavioral patterns.

[0031] The learning unit can also collect at least one external data item, such as the poster's social media activity and number of followers, to increase reliability. For example, the learning unit analyzes the poster's social media activity and evaluates reliability for the review information collected by the generation AI. For example, it rates reviews by posters who are active on social media highly. The learning unit also analyzes the poster's number of followers for the review information collected by the generation AI and evaluates reliability. For example, it rates reviews by posters who have a large number of followers highly. The learning unit also analyzes the poster's social media activity and number of followers in combination for the review information collected by the generation AI and evaluates reliability. For example, it rates reviews by posters who are active on social media and have a large number of followers highly. In this way, the reliability of reviews can be further increased by taking social media activity and number of followers into consideration.

[0032] The word-of-mouth information collection unit collects not only text but also video and audio word-of-mouth reviews, allowing it to learn more diverse information. For example, the word-of-mouth information collection unit may include not only text but also video word-of-mouth reviews as the word-of-mouth information collected by the generation AI. For example, it may analyze product review videos and evaluate their reliability. The word-of-mouth information collection unit may also include not only text but also audio word-of-mouth information as the word-of-mouth information collected by the generation AI. For example, it may analyze audio reviews and evaluate their reliability. The word-of-mouth information collection unit may also expand the word-of-mouth information collected by the generation AI to all text, video, and audio, allowing it to learn more diverse information. For example, it may analyze all text, video, and audio and evaluate their reliability. This allows it to learn more diverse information by collecting text, video, and audio word-of-mouth reviews.

[0033] The word-of-mouth information collection unit can automatically translate word-of-mouth information in different languages ​​and evaluate trustworthiness from an international perspective. The word-of-mouth information collection unit, for example, automatically translates word-of-mouth information in different languages ​​collected by the generation AI and evaluates trustworthiness. For example, it translates Japanese reviews into English and evaluates trustworthiness. The word-of-mouth information collection unit also automatically translates word-of-mouth information in different languages ​​collected by the generation AI and evaluates trustworthiness from an international perspective. For example, it translates English reviews into multiple languages ​​and evaluates trustworthiness. The word-of-mouth information collection unit also automatically translates word-of-mouth information in different languages ​​collected by the generation AI and evaluates trustworthiness from an international perspective. For example, it integrates reviews in multiple languages ​​and evaluates trustworthiness. This makes it possible to automatically translate word-of-mouth information in different languages ​​and evaluate trustworthiness from an international perspective.

[0034] The filtering unit can identify malicious reviews based on the poster's past posting history and ratings from other users. For example, when the generation AI filters, the filtering unit analyzes the poster's past posting history to identify malicious reviews. For example, it excludes reviews from users who have posted malicious reviews in the past. Furthermore, when the generation AI filters, the filtering unit considers ratings from other users to identify malicious reviews. For example, it excludes reviews from posters with many low ratings. Furthermore, when the generation AI filters, the filtering unit analyzes a poster's past posting history in combination with ratings from other users to identify malicious reviews. For example, it excludes reviews from posters with a malicious past posting history and low ratings from other users. In this way, malicious reviews can be identified by considering the past posting history and ratings from other users.

[0035] The filtering unit analyzes not only the content of reviews but also the timing and frequency of posting to detect abnormal patterns. For example, when the generation AI filters, the filtering unit analyzes not only the content of reviews but also the timing of posting to detect abnormal patterns. For example, it excludes reviews posted by users who post a large number of reviews in a short period of time. Furthermore, when the generation AI filters, the filtering unit analyzes not only the content of reviews but also the frequency of posting to detect abnormal patterns. For example, it excludes reviews that are posted in concentrations during specific time periods. Furthermore, when the generation AI filters, the filtering unit analyzes a combination of the content, timing, and frequency of posting to detect abnormal patterns. For example, it excludes reviews posted by users who post a large number of reviews in a short period of time, concentrated during specific time periods. In this way, abnormal patterns can be detected by analyzing the timing and frequency of posting.

[0036] The filtering unit can analyze not only text reviews but also the content of images and videos to filter out malicious information. For example, when the generation AI filters, the filtering unit analyzes not only text reviews but also the content of images to filter out malicious information. For example, it filters out images that contain slander. Furthermore, when the generation AI filters, the filtering unit analyzes not only text reviews but also the content of videos to filter out malicious information. For example, it filters out videos that contain slander. Furthermore, when the generation AI filters, the filtering unit analyzes all text, images, and videos to filter out malicious information. For example, it filters out reviews that contain slander in all text, images, and videos. This makes it possible to filter out malicious information by analyzing the content of text, images, and videos.

[0037] The filtering unit can compare reviews from different industries and fields and identify common malicious patterns. For example, the generation AI in the filtering unit compares reviews from different industries and identifies common malicious patterns. For example, it identifies defamatory patterns that are frequently seen in a particular industry. The filtering unit also compares reviews from different fields and identifies common malicious patterns. For example, it identifies stealth marketing patterns that are frequently seen in a particular field. The filtering unit also compares reviews from different industries and fields and identifies common malicious patterns. For example, it identifies defamatory and stealth marketing patterns that are commonly seen in a particular industry or field. This makes it possible to identify common malicious patterns by comparing reviews from different industries and fields.

[0038] The presentation unit can further increase the reliability of reviews that the generation AI has determined to be reliable by additionally displaying ratings and comments from other users. For example, the presentation unit can additionally display ratings from other users for reviews that the generation AI has determined to be reliable. For example, it can display star ratings and the number of "helpful" buttons. The presentation unit can also additionally display comments from other users for reviews that the generation AI has determined to be reliable. For example, it can display specific usage experiences and additional advice. The presentation unit can also further increase the reliability of reviews that the generation AI has determined to be reliable by displaying ratings and comments from other users in combination. For example, by displaying both ratings and comments, the reliability of the reviews can be enhanced. In this way, the reliability of the reviews can be further increased by additionally displaying ratings and comments from other users.

[0039] The presentation unit can also display the poster's profile information and past reliability ratings for reviews that it determines to be reliable. For example, the presentation unit displays the poster's profile information for reviews that the generation AI determines to be reliable. For example, it displays the poster's name, photo, past posting history, etc. The presentation unit also displays the poster's past reliability ratings for reviews that it determines to be reliable. For example, it displays the ratings and reliability scores of reviews posted in the past. The presentation unit also displays the poster's profile information and past reliability ratings in combination for reviews that it determines to be reliable. For example, displaying both the profile information and the reliability score strengthens the reliability of the review. In this way, by displaying the poster's profile information and past reliability ratings, it is possible to further increase the reliability of the review.

[0040] The presentation unit presents trustworthy reviews not only in text but also in infographic and video formats, making them easier to understand visually. For example, the presentation unit presents reviews that the generation AI has determined to be trustworthy not only in text but also in infographic format. For example, the main points of the reviews may be visually displayed in graphs or charts. The presentation unit also presents reviews that the generation AI has determined to be trustworthy not only in text but also in video format. For example, the content of the reviews may be explained in video, making them easier to understand visually. The presentation unit also presents reviews that the generation AI has determined to be trustworthy in all of text, infographics, and video, making them easier to understand visually. For example, text, graphs, and videos may be displayed in combination. In this way, by presenting reviews in text, infographic, and video formats, it is possible to make the reviews easier to understand visually.

[0041] The presentation unit can share reliable reviews across different platforms, allowing users to view the same information on multiple sites. The presentation unit, for example, shares reviews that the generation AI has determined to be reliable across different platforms. For example, the presentation unit displays the same review on multiple review sites. The presentation unit also shares reviews that the generation AI has determined to be reliable across different platforms, allowing users to view the same information on multiple sites. For example, the presentation unit displays the same review on a review site and social media. The presentation unit also shares reviews that the generation AI has determined to be reliable across different platforms, allowing users to view the same information on multiple sites. For example, the presentation unit displays the same review on a review site, social media, and a shopping site. In this way, by sharing reviews across different platforms, users can view the same information on multiple sites.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The review filtering system can further include a recommendation function to increase a user's purchasing motivation. For example, the presentation unit can recommend related products and services based on reliable reviews. The presentation unit can also analyze a user's past purchase history and browsing history to provide individually customized recommendations. Furthermore, the presentation unit can recommend products and services according to the season or trends. This allows a user to select more appropriate products and services while referring to reliable reviews.

[0044] The review filtering system can also collect user feedback to improve the system. For example, the presentation unit can have an interface that provides feedback to users on reviews they have viewed. The feedback collection unit can analyze the user feedback and provide data to improve the accuracy and usability of the system. The feedback collection unit can also suggest new features and improvements based on the user feedback. This allows the system to be continuously improved according to user needs.

[0045] The review filtering system may further include functions for protecting user privacy. For example, the privacy protection unit may anonymize a user's personal information to prevent it from being provided to third parties. The privacy protection unit may also provide an interface that allows users to select how their data is used. Furthermore, the privacy protection unit may strengthen security measures to prevent unauthorized access to user data. This allows users to use the system with peace of mind.

[0046] The review filtering system can further include a product recommendation function that takes into account the user's health condition. For example, the presentation unit can analyze the user's health data and recommend health-conscious products and services. The presentation unit can also select appropriate products based on the user's allergy information and dietary restrictions. Furthermore, the presentation unit can analyze the user's exercise data and sleep data and recommend products and services that support a healthy lifestyle. This allows the user to select products and services that suit their health condition.

[0047] The review filtering system can also provide a reward program that takes into account a user's purchasing history. For example, the reward department can analyze a user's past purchasing history and provide rewards for specific products or services. The reward department can also customize the reward content based on the user's purchasing frequency and amount. Furthermore, the reward department can suggest specific campaigns and promotions based on the user's purchasing history. This allows users to receive rewards through purchasing activities, and companies can also improve customer loyalty.

[0048] The review filtering system can further include an event recommendation function that takes into account the user's hobbies and interests. For example, the event recommendation unit can analyze the user's past event participation history and interests and recommend related events. The event recommendation unit can also suggest nearby events based on the user's current location and schedule. Furthermore, the event recommendation unit can consider the participation status of the user's friends and followers and recommend events that can be attended with people who share common interests. This makes it easier for users to find events that match their hobbies and interests.

[0049] The processing flow of the first embodiment will be briefly explained below.

[0050] Step 1: The word-of-mouth information collection unit collects multiple pieces of word-of-mouth information from the web. For example, it collects text-based word-of-mouth information. It can also collect image and video-based word-of-mouth information. Furthermore, the word-of-mouth information collection unit can automatically translate and collect word-of-mouth information in different languages. For example, it can translate English word-of-mouth information into Japanese and collect it. Step 2: The learning unit learns from the collected review information. For example, the generation AI analyzes the content of the review, the poster's history, posting frequency, language patterns, etc. The generation AI can also analyze the poster's past purchasing history and behavioral patterns to evaluate trustworthiness. Furthermore, the generation AI can collect external data such as the poster's social media activity and number of followers to increase trustworthiness. Step 3: The filtering unit filters out malicious reviews based on the learned data. For example, it detects and eliminates reviews that are defamatory, false, or likely to be stealth marketing. The filtering unit can also identify malicious reviews by taking into account the poster's past posting history and ratings from other users. Furthermore, the filtering unit can analyze not only the content of reviews but also the timing and frequency of posting to detect abnormal patterns. Step 4: The presentation unit presents the filtered, reliable reviews. For example, if the generation AI determines that a review that says "This product is very easy to use" is reliable, it will display that review preferentially. The presentation unit can also add ratings and comments from other users to reviews that it determines to be reliable, further increasing their credibility. Furthermore, the presentation unit can present reliable reviews not only in text format but also in infographics and video formats, making them easier to understand visually.

[0051] (Example 2) The review filtering system according to an embodiment of the present invention uses a generation AI to learn from a vast amount of review information, filter out malicious reviews, and present only reliable reviews. This allows the review filtering system to provide an environment in which users can select products and services with peace of mind.

[0052] A review filtering system according to an embodiment includes a review information collection unit, a learning unit, a filtering unit, and a presentation unit. The review information collection unit collects multiple pieces of review information from the web. For example, it collects reviews in text format. It can also collect reviews in image and video format. Furthermore, the review information collection unit can automatically translate and collect reviews in different languages. For example, it can translate English reviews into Japanese and collect them. The learning unit learns the collected review information. For example, the generation AI analyzes the content of the review, the poster's history, posting frequency, language patterns, etc. The generation AI can also analyze the poster's past purchasing history and behavioral patterns to evaluate trustworthiness. Furthermore, the generation AI can collect external data, such as the poster's social media activity and number of followers, to increase trustworthiness. The filtering unit filters malicious reviews based on the learned data. For example, it detects and excludes reviews that are defamatory, misrepresentative, or likely to be stealth marketing. The filtering unit can also identify malicious reviews by considering the poster's past posting history and ratings from other users. Furthermore, the filtering unit can analyze not only the content of reviews but also the timing and frequency of posting to detect abnormal patterns. The presentation unit presents filtered, reliable reviews. For example, if the generation AI determines that a review saying "This product is very easy to use" is reliable, it preferentially displays that review. The presentation unit can also add ratings and comments from other users to reviews determined to be reliable, further increasing their reliability. Furthermore, the presentation unit can present reliable reviews not only in text format but also in infographics and video formats, making them easier to understand visually. As a result, the review filtering system according to the embodiment efficiently collects vast amounts of review information and presents only reliable reviews, allowing users to select products and services with confidence.

[0053] The learning unit can analyze the poster's past purchasing history and behavioral patterns to evaluate reliability. For example, the learning unit analyzes the poster's past purchasing history for the review information collected by the generation AI to evaluate reliability. For example, it rates highly reviews by posters who have purchased the same product multiple times in the past. The learning unit also analyzes the poster's behavioral patterns for the review information collected by the generation AI to evaluate reliability. For example, it rates highly reviews by posters who post reviews frequently but whose content is consistent. The learning unit also analyzes the poster's purchasing history and behavioral patterns in combination for the review information collected by the generation AI to evaluate reliability. For example, it rates highly reviews by posters whose past purchasing history and behavioral patterns match. In this way, the reliability of reviews can be increased by analyzing the poster's past purchasing history and behavioral patterns.

[0054] The learning unit can also collect at least one external data item, such as the poster's social media activity and number of followers, to increase reliability. For example, the learning unit analyzes the poster's social media activity and evaluates reliability for the review information collected by the generation AI. For example, it rates reviews by posters who are active on social media highly. The learning unit also analyzes the poster's number of followers for the review information collected by the generation AI and evaluates reliability. For example, it rates reviews by posters who have a large number of followers highly. The learning unit also analyzes the poster's social media activity and number of followers in combination for the review information collected by the generation AI and evaluates reliability. For example, it rates reviews by posters who are active on social media and have a large number of followers highly. In this way, the reliability of reviews can be further increased by taking social media activity and number of followers into consideration.

[0055] The learning unit can use the emotion estimation function to analyze the emotions of the poster and evaluate the reliability based on the intensity and type of emotion. For example, the learning unit uses the emotion estimation function to analyze the emotions of the poster for review information collected by the generation AI and evaluates the reliability. For example, reviews with strong positive emotions are rated highly. The learning unit also uses the emotion estimation function to analyze the intensity of the emotions of the poster for review information collected by the generation AI and evaluates the reliability. For example, reviews with strong emotional intensity are rated highly. The learning unit also uses the emotion estimation function to analyze the type of emotions of the poster for review information collected by the generation AI and evaluates the reliability. For example, reviews with a large number of positive emotional types are rated highly. In this way, the reliability of reviews can be increased by analyzing the intensity and type of emotion.

[0056] The word-of-mouth information collection unit collects not only text but also video and audio word-of-mouth reviews, allowing it to learn more diverse information. For example, the word-of-mouth information collection unit may include not only text but also video word-of-mouth reviews as the word-of-mouth information collected by the generation AI. For example, it may analyze product review videos and evaluate their reliability. The word-of-mouth information collection unit may also include not only text but also audio word-of-mouth information as the word-of-mouth information collected by the generation AI. For example, it may analyze audio reviews and evaluate their reliability. The word-of-mouth information collection unit may also expand the word-of-mouth information collected by the generation AI to all text, video, and audio, allowing it to learn more diverse information. For example, it may analyze all text, video, and audio and evaluate their reliability. This allows it to learn more diverse information by collecting text, video, and audio word-of-mouth reviews.

[0057] The word-of-mouth information collection unit can automatically translate word-of-mouth information in different languages ​​and evaluate trustworthiness from an international perspective. The word-of-mouth information collection unit, for example, automatically translates word-of-mouth information in different languages ​​collected by the generation AI and evaluates trustworthiness. For example, it translates Japanese reviews into English and evaluates trustworthiness. The word-of-mouth information collection unit also automatically translates word-of-mouth information in different languages ​​collected by the generation AI and evaluates trustworthiness from an international perspective. For example, it translates English reviews into multiple languages ​​and evaluates trustworthiness. The word-of-mouth information collection unit also automatically translates word-of-mouth information in different languages ​​collected by the generation AI and evaluates trustworthiness from an international perspective. For example, it integrates reviews in multiple languages ​​and evaluates trustworthiness. This makes it possible to automatically translate word-of-mouth information in different languages ​​and evaluate trustworthiness from an international perspective.

[0058] The learning unit can use the emotion estimation function to collect emotional responses of users viewing reviews in real time and reflect them in the reliability evaluation. For example, the learning unit can use the emotion estimation function to collect users' emotional responses in real time to the review information collected by the generation AI and reflect them in the reliability evaluation. For example, it can highly evaluate reviews with a high number of positive emotional responses. The learning unit can also use the emotion estimation function to collect users' emotional responses in real time to the review information collected by the generation AI and reflect them in the reliability evaluation. For example, it can highly evaluate reviews with a high intensity of emotional responses. The learning unit can also use the emotion estimation function to collect users' emotional responses in real time to the review information collected by the generation AI and reflect them in the reliability evaluation. For example, it can highly evaluate reviews with a high number of positive emotions. In this way, the reliability of reviews can be increased by collecting users' emotional responses in real time and reflecting them in the reliability evaluation.

[0059] The filtering unit can identify malicious reviews based on the poster's past posting history and ratings from other users. For example, when the generation AI filters, the filtering unit analyzes the poster's past posting history to identify malicious reviews. For example, it excludes reviews from users who have posted malicious reviews in the past. Furthermore, when the generation AI filters, the filtering unit considers ratings from other users to identify malicious reviews. For example, it excludes reviews from posters with many low ratings. Furthermore, when the generation AI filters, the filtering unit analyzes a poster's past posting history in combination with ratings from other users to identify malicious reviews. For example, it excludes reviews from posters with a malicious past posting history and low ratings from other users. In this way, malicious reviews can be identified by considering the past posting history and ratings from other users.

[0060] The filtering unit analyzes not only the content of reviews but also the timing and frequency of posting to detect abnormal patterns. For example, when the generation AI filters, the filtering unit analyzes not only the content of reviews but also the timing of posting to detect abnormal patterns. For example, it excludes reviews posted by users who post a large number of reviews in a short period of time. Furthermore, when the generation AI filters, the filtering unit analyzes not only the content of reviews but also the frequency of posting to detect abnormal patterns. For example, it excludes reviews that are posted in concentrations during specific time periods. Furthermore, when the generation AI filters, the filtering unit analyzes a combination of the content, timing, and frequency of posting to detect abnormal patterns. For example, it excludes reviews posted by users who post a large number of reviews in a short period of time, concentrated during specific time periods. In this way, abnormal patterns can be detected by analyzing the timing and frequency of posting.

[0061] The filtering unit can use the emotion estimation function to preferentially filter reviews that strongly express negative emotions. For example, when the generation AI filters, the filtering unit uses the emotion estimation function to preferentially filter reviews that strongly express negative emotions. For example, it excludes reviews that strongly express anger or sadness. Furthermore, when the generation AI filters, the filtering unit uses the emotion estimation function to analyze the intensity of negative emotions and preferentially filter reviews that are highly intense. For example, it excludes negative reviews that are highly intense. Furthermore, when the generation AI filters, the filtering unit uses the emotion estimation function to analyze the type of negative emotion and preferentially filter reviews that strongly express a specific negative emotion. For example, it excludes reviews that strongly express anger. In this way, by preferentially filtering reviews that strongly express negative emotions, it is possible to exclude malicious reviews.

[0062] The filtering unit can analyze not only text reviews but also the content of images and videos to filter out malicious information. For example, when the generation AI filters, the filtering unit analyzes not only text reviews but also the content of images to filter out malicious information. For example, it filters out images that contain slander. Furthermore, when the generation AI filters, the filtering unit analyzes not only text reviews but also the content of videos to filter out malicious information. For example, it filters out videos that contain slander. Furthermore, when the generation AI filters, the filtering unit analyzes all text, images, and videos to filter out malicious information. For example, it filters out reviews that contain slander in all text, images, and videos. This makes it possible to filter out malicious information by analyzing the content of text, images, and videos.

[0063] The filtering unit can compare reviews from different industries and fields and identify common malicious patterns. For example, the generation AI in the filtering unit compares reviews from different industries and identifies common malicious patterns. For example, it identifies defamatory patterns that are frequently seen in a particular industry. The filtering unit also compares reviews from different fields and identifies common malicious patterns. For example, it identifies stealth marketing patterns that are frequently seen in a particular field. The filtering unit also compares reviews from different industries and fields and identifies common malicious patterns. For example, it identifies defamatory and stealth marketing patterns that are commonly seen in a particular industry or field. This makes it possible to identify common malicious patterns by comparing reviews from different industries and fields.

[0064] The filtering unit can use the emotion estimation function to collect users' emotional responses to the filtered reviews, thereby improving filtering accuracy. For example, the filtering unit can use the emotion estimation function to collect users' emotional responses to reviews filtered by the generation AI, thereby improving filtering accuracy. For example, reviews with many negative emotional responses are re-evaluated. The filtering unit can also use the emotion estimation function to collect users' emotional responses to reviews filtered by the generation AI, thereby improving filtering accuracy. For example, reviews with strong emotional responses are re-evaluated. The filtering unit can also use the emotion estimation function to collect users' emotional responses to reviews filtered by the generation AI, thereby improving filtering accuracy. For example, reviews with many positive emotional responses are preferentially displayed. In this way, filtering accuracy can be improved by collecting users' emotional responses.

[0065] The presentation unit can further increase the reliability of reviews that the generation AI has determined to be reliable by additionally displaying ratings and comments from other users. For example, the presentation unit can additionally display ratings from other users for reviews that the generation AI has determined to be reliable. For example, it can display star ratings and the number of "helpful" buttons. The presentation unit can also additionally display comments from other users for reviews that the generation AI has determined to be reliable. For example, it can display specific usage experiences and additional advice. The presentation unit can also further increase the reliability of reviews that the generation AI has determined to be reliable by displaying ratings and comments from other users in combination. For example, by displaying both ratings and comments, the reliability of the reviews can be enhanced. In this way, the reliability of the reviews can be further increased by additionally displaying ratings and comments from other users.

[0066] The presentation unit can also display the poster's profile information and past reliability ratings for reviews that it determines to be reliable. For example, the presentation unit displays the poster's profile information for reviews that the generation AI determines to be reliable. For example, it displays the poster's name, photo, past posting history, etc. The presentation unit also displays the poster's past reliability ratings for reviews that it determines to be reliable. For example, it displays the ratings and reliability scores of reviews posted in the past. The presentation unit also displays the poster's profile information and past reliability ratings in combination for reviews that it determines to be reliable. For example, displaying both the profile information and the reliability score strengthens the reliability of the review. In this way, by displaying the poster's profile information and past reliability ratings, it is possible to further increase the reliability of the review.

[0067] The presentation unit can use the emotion estimation function to analyze the emotional reactions of users viewing reliable reviews and propose a display method that elicits positive emotions. For example, the presentation unit uses the emotion estimation function to analyze the emotional reactions of users viewing reviews that the generation AI has determined to be reliable and proposes a display method that elicits positive emotions. For example, it uses colors and fonts that elicit positive emotions. The presentation unit also uses the emotion estimation function to analyze the emotional reactions of users viewing reviews that the generation AI has determined to be reliable and proposes a display method that elicits positive emotions. For example, it uses layouts and designs that elicit positive emotions. The presentation unit also uses the emotion estimation function to analyze the emotional reactions of users viewing reviews that the generation AI has determined to be reliable and proposes a display method that elicits positive emotions. For example, it uses animations and effects that elicit positive emotions. In this way, the reliability of reviews can be increased by analyzing the emotional reactions of users and proposing a display method that elicits positive emotions.

[0068] The presentation unit presents trustworthy reviews not only in text but also in infographic and video formats, making them easier to understand visually. For example, the presentation unit presents reviews that the generation AI has determined to be trustworthy not only in text but also in infographic format. For example, the main points of the reviews may be visually displayed in graphs or charts. The presentation unit also presents reviews that the generation AI has determined to be trustworthy not only in text but also in video format. For example, the content of the reviews may be explained in video, making them easier to understand visually. The presentation unit also presents reviews that the generation AI has determined to be trustworthy in all of text, infographics, and video, making them easier to understand visually. For example, text, graphs, and videos may be displayed in combination. In this way, by presenting reviews in text, infographic, and video formats, it is possible to make the reviews easier to understand visually.

[0069] The presentation unit can share reliable reviews across different platforms, allowing users to view the same information on multiple sites. The presentation unit, for example, shares reviews that the generation AI has determined to be reliable across different platforms. For example, the presentation unit displays the same review on multiple review sites. The presentation unit also shares reviews that the generation AI has determined to be reliable across different platforms, allowing users to view the same information on multiple sites. For example, the presentation unit displays the same review on a review site and social media. The presentation unit also shares reviews that the generation AI has determined to be reliable across different platforms, allowing users to view the same information on multiple sites. For example, the presentation unit displays the same review on a review site, social media, and a shopping site. In this way, by sharing reviews across different platforms, users can view the same information on multiple sites.

[0070] The presentation unit can use the emotion estimation function to monitor users' emotional reactions to trustworthy reviews in real time and continuously search for the optimal display method. For example, the presentation unit uses the emotion estimation function to monitor users' emotional reactions in real time for reviews that the generation AI has determined to be trustworthy and search for the optimal display method. For example, the presentation unit adjusts the display method according to the user's emotional reaction. The presentation unit also uses the emotion estimation function to monitor users' emotional reactions in real time for reviews that the generation AI has determined to be trustworthy and search for the optimal display method. For example, the presentation unit prioritizes the adoption of display methods with a high number of positive emotional reactions. The presentation unit also uses the emotion estimation function to monitor users' emotional reactions in real time for reviews that the generation AI has determined to be trustworthy and search for the optimal display method. For example, the presentation unit continuously improves the display method based on user emotional reaction data. In this way, the reliability of reviews can be increased by monitoring users' emotional reactions in real time and continuously searching for the optimal display method.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The review filtering system can further include a recommendation function to increase a user's purchasing motivation. For example, the presentation unit can recommend related products and services based on reliable reviews. The presentation unit can also analyze a user's past purchase history and browsing history to provide individually customized recommendations. Furthermore, the presentation unit can recommend products and services according to the season or trends. This allows a user to select more appropriate products and services while referring to reliable reviews.

[0073] The review filtering system can also collect user feedback to improve the system. For example, the presentation unit can have an interface that provides feedback to users on reviews they have viewed. The feedback collection unit can analyze the user feedback and provide data to improve the accuracy and usability of the system. The feedback collection unit can also suggest new features and improvements based on the user feedback. This allows the system to be continuously improved according to user needs.

[0074] The review filtering system may further include functions for protecting user privacy. For example, the privacy protection unit may anonymize a user's personal information to prevent it from being provided to third parties. The privacy protection unit may also provide an interface that allows users to select how their data is used. Furthermore, the privacy protection unit may strengthen security measures to prevent unauthorized access to user data. This allows users to use the system with peace of mind.

[0075] The word-of-mouth filtering system can further include an advertisement display function that takes user emotions into consideration. For example, the presentation unit can estimate the user's emotions and display advertisements that elicit positive emotions. The presentation unit can also adjust the content and timing of advertisements according to the user's emotions. Furthermore, the presentation unit can analyze user emotion data and optimize the effectiveness of advertisements. This allows users to receive more effective advertisements and allows advertisers to conduct more effective marketing.

[0076] The review filtering system can further include a product recommendation function that takes into account the user's health condition. For example, the presentation unit can analyze the user's health data and recommend health-conscious products and services. The presentation unit can also select appropriate products based on the user's allergy information and dietary restrictions. Furthermore, the presentation unit can analyze the user's exercise data and sleep data and recommend products and services that support a healthy lifestyle. This allows the user to select products and services that suit their health condition.

[0077] The review filtering system can also be equipped with a customer support function that takes user emotions into consideration. For example, the support department can estimate the user's emotions and provide appropriate support. The support department can also adjust the content and method of support according to the user's emotions. Furthermore, the support department can analyze the user's emotional data and optimize the effectiveness of support. This allows users to receive more satisfying support and allows companies to improve customer satisfaction.

[0078] The review filtering system can also provide a reward program that takes into account a user's purchasing history. For example, the reward department can analyze a user's past purchasing history and provide rewards for specific products or services. The reward department can also customize the reward content based on the user's purchasing frequency and amount. Furthermore, the reward department can suggest specific campaigns and promotions based on the user's purchasing history. This allows users to receive rewards through purchasing activities, and companies can also improve customer loyalty.

[0079] The word-of-mouth filtering system can further include a personalized news feed function that takes into account the user's emotions. For example, the news feed unit can estimate the user's emotions and prioritize displaying news articles that evoke positive emotions. The news feed unit can also adjust the content and display order of news articles according to the user's emotions. Furthermore, the news feed unit can analyze the user's emotional data and optimize the effectiveness of the news feed. This allows the user to receive more positive news and improves the news consumption experience.

[0080] The review filtering system can further include an event recommendation function that takes into account the user's hobbies and interests. For example, the event recommendation unit can analyze the user's past event participation history and interests and recommend related events. The event recommendation unit can also suggest nearby events based on the user's current location and schedule. Furthermore, the event recommendation unit can consider the participation status of the user's friends and followers and recommend events that can be attended with people who share common interests. This makes it easier for users to find events that match their hobbies and interests.

[0081] The review filtering system can further include an entertainment content recommendation function that takes into account the user's emotions. For example, the entertainment recommendation unit can estimate the user's emotions and recommend movies or music that evoke positive emotions. The entertainment recommendation unit can also adjust the type and genre of content according to the user's emotions. Furthermore, the entertainment recommendation unit can analyze the user's emotional data and optimize the effectiveness of the content. This allows the user to enjoy entertainment content that matches their emotions.

[0082] The processing flow of the second embodiment will be briefly explained below.

[0083] Step 1: The word-of-mouth information collection unit collects multiple pieces of word-of-mouth information from the web. For example, it collects text-based word-of-mouth information. It can also collect image and video-based word-of-mouth information. Furthermore, the word-of-mouth information collection unit can automatically translate and collect word-of-mouth information in different languages. For example, it can translate English word-of-mouth information into Japanese and collect it. Step 2: The learning unit learns from the collected review information. For example, the generation AI analyzes the content of the review, the poster's history, posting frequency, language patterns, etc. The generation AI can also analyze the poster's past purchasing history and behavioral patterns to evaluate trustworthiness. Furthermore, the generation AI can collect external data such as the poster's social media activity and number of followers to increase trustworthiness. Step 3: The filtering unit filters out malicious reviews based on the learned data. For example, it detects and eliminates reviews that are defamatory, false, or likely to be stealth marketing. The filtering unit can also identify malicious reviews by taking into account the poster's past posting history and ratings from other users. Furthermore, the filtering unit can analyze not only the content of reviews but also the timing and frequency of posting to detect abnormal patterns. Step 4: The presentation unit presents the filtered, reliable reviews. For example, if the generation AI determines that a review that says "This product is very easy to use" is reliable, it will display that review preferentially. The presentation unit can also add ratings and comments from other users to reviews that it determines to be reliable, further increasing their credibility. Furthermore, the presentation unit can present reliable reviews not only in text format but also in infographics and video formats, making them easier to understand visually.

[0084] 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.

[0085] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of 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.

[0086] 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.

[0087] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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).

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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 AI 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.

[0101] 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.

[0102] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0103] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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).

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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 AI 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.

[0116] 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.

[0117] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0118] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0129] 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.

[0130] 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.

[0131] 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 AI 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0138] 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."

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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]

[0151] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A word-of-mouth information collection department that collects multiple word-of-mouth information from the web, a learning unit that learns the word-of-mouth information collected by the word-of-mouth information collecting unit; a filtering unit that filters out malicious reviews based on the data learned by the learning unit; a presentation unit that presents reliable word-of-mouth reviews filtered by the filtering unit. A system characterized by:

2. The learning unit Analyze the poster's past purchasing history and behavioral patterns to evaluate their reliability 2. The system of claim 1.

3. The learning unit We also collect external data on at least one of the poster's social media activity and number of followers to enhance reliability.

2. The system of claim 1.

4. The learning unit Analyze the poster's emotions and evaluate their credibility based on the intensity and type of those emotions 2. The system of claim 1.

5. The word-of-mouth information collection unit Collect not only text but also video and audio reviews to learn more diverse information 2. The system of claim 1.

6. The word-of-mouth information collection unit Automatically translate reviews in different languages ​​and evaluate their credibility from an international perspective 2. The system of claim 1.

7. The learning unit The emotional responses of users viewing the reviews are collected in real time and reflected in the reliability assessment.

2. The system of claim 1.

8. The filtering unit Identifying malicious reviews based on the poster's past posting history and ratings from other users 2. The system of claim 1.

Images