system

Abstract

The system according to the embodiment aims to enable users to obtain appropriate information through the avatars of trusted reviewers. [Solution] A system according to an embodiment includes a collection unit, an identification unit, a generation unit, a reception unit, and an answering unit. The collection unit collects product reviews. The identification unit analyzes the reviews collected by the collection unit and identifies reliable reviewers. The generation unit generates an avatar of the reviewer identified by the identification unit. The reception unit allows a user to input a question to the avatar generated by the generation unit. The answering unit generates an answer to the question input by the reception unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem that it is difficult to determine the reliability of product reviews and to obtain appropriate information.

[0005] The system according to the embodiment aims to enable users to obtain appropriate information through the avatars of trusted reviewers. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an identification unit, a generation unit, a reception unit, and an answering unit. The collection unit collects product reviews. The identification unit analyzes the reviews collected by the collection unit and identifies reliable reviewers. The generation unit generates an avatar of the reviewer identified by the identification unit. The reception unit allows a user to input a question to the avatar generated by the generation unit. The answering unit generates an answer to the question input by the reception unit. [Effects of the Invention]

[0007] The system according to the embodiment allows users to obtain appropriate information through the avatars of trusted reviewers. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A review support system according to an embodiment of the present invention generates avatars of reliable reviewers and allows users to directly ask questions. This review support system collects product reviews and analyzes them using a large-scale language model (LLM). Based on the analysis results, a reliable reviewer is identified, and the LLM generates an avatar for the reviewer. This avatar is based on the reviewer's past reviews and ratings, allowing users to directly ask questions. For example, when a user asks, "How durable is this product?", the LLM responds as the reviewer's avatar. This mechanism allows users to obtain additional information while referring to reliable reviews, thereby making purchasing decisions more reliable. For example, the review support system collects product reviews and analyzes them using an LLM. The system analyzes the content and ratings of reviewers' past reviews in detail to identify reliable reviewers. For example, the system evaluates the reviewer's trustworthiness based on the ratings of the reviewer's past reviews and feedback from other users. The system then identifies a reliable reviewer and generates an avatar for the reviewer. This avatar is based on the reviewer's past reviews and ratings, allowing users to directly ask questions. For example, if a user asks, "How durable is this product?", the LLM will respond as the reviewer's avatar. In addition, an interface is provided for users to ask questions. A UI / UX is designed to make it easy for users to ask questions, and a feedback function is also introduced to ensure the quality of the answers generated by the LLM. For example, when a user asks a question, the quality of the answer generated by the LLM can be evaluated and feedback provided to improve the quality of the answer. This mechanism allows users to obtain additional information while referring to reliable reviews, making purchasing decisions more reliable. As a result, the review support system allows users to ask questions directly through the avatar of a reliable reviewer and obtain reliable information.

[0029] A review support system according to an embodiment includes a collection unit, an identification unit, a generation unit, a reception unit, and an answering unit. The collection unit collects product reviews. The collection unit can automatically collect product reviews from, for example, an online platform. The collection unit can also collect reviews manually entered by a user. The identification unit analyzes the reviews collected by the collection unit to identify reliable reviewers. The identification unit evaluates the reviewer's reliability based on, for example, ratings of past reviews and feedback from other users. The generation unit generates an avatar for the reviewer identified by the identification unit. The generation unit generates the avatar based on, for example, the reviewer's past reviews and ratings. The reception unit provides an interface through which a user inputs a question to the avatar generated by the generation unit. The reception unit provides an interface through which a user can input a question by, for example, text input or voice input. The answering unit generates an answer to the question input by the reception unit. The answering unit generates an answer to the user's question using, for example, an LLM. As a result, the review support system according to the embodiment allows the user to ask questions directly through the avatar of a reliable reviewer and obtain highly reliable information.

[0030] The collection unit can analyze the content and ratings of the reviewer's past reviews. For example, the collection unit analyzes the content of the reviewer's past reviews using text analysis technology. For example, the collection unit analyzes the text content of the reviewer's past reviews and extracts the reviewer's ratings. The collection unit can also analyze the star ratings of the reviewer's past reviews. For example, the collection unit aggregates the star ratings of the reviewer's past reviews and evaluates the reviewer's reliability. The collection unit can also analyze feedback from other users. For example, the collection unit analyzes comments and ratings from other users and evaluates the reviewer's reliability. In this way, the collection unit can identify highly reliable reviewers by analyzing the content and ratings of the reviewer's past reviews in detail.

[0031] The identification unit can determine the trustworthiness based on the ratings of the reviewer's past reviews and feedback from other users. The identification unit, for example, analyzes the ratings of the reviewer's past reviews to determine trustworthiness. For example, the identification unit aggregates the star ratings of the reviewer's past reviews and evaluates trustworthiness. The identification unit can also analyze feedback from other users to determine trustworthiness. For example, the identification unit analyzes comments and ratings from other users to evaluate the reviewer's trustworthiness. In this way, the identification unit can identify a reliable reviewer by evaluating the reviewer's trustworthiness highly.

[0032] The generation unit can create an avatar based on the reviewer's past reviews and ratings. The generation unit generates an avatar based on, for example, the content of the reviewer's past reviews. For example, the generation unit analyzes the text content of the reviewer's past reviews to generate an avatar. The generation unit can also generate an avatar based on the ratings of the reviewer's past reviews. For example, the generation unit analyzes the star ratings of the reviewer's past reviews to generate an avatar. The generation unit can also generate an avatar based on feedback from other users. For example, the generation unit analyzes comments and ratings from other users to generate an avatar. In this way, the generation unit can provide a highly reliable avatar by generating an avatar based on the reviewer's past reviews and ratings.

[0033] The reception unit can provide an interface through which the user inputs a question. For example, the reception unit provides an interface through which the user can input a question by text input. For example, the reception unit provides an interface through which the user can input a question into a text box. The reception unit can also provide an interface through which the user can input a question by voice input. For example, the reception unit provides an interface through which the user can input a question by voice using a microphone. In this way, the reception unit provides an interface through which the user can easily input a question, thereby improving convenience.

[0034] The answering unit can determine the quality of the answer generated by the LLM when a user asks a question and provide feedback. For example, the answering unit evaluates the quality of the answer generated by the LLM when a user asks a question. For example, the answering unit evaluates the accuracy and relevance of the answer generated by the LLM. The answering unit can also evaluate the quality of the answer based on feedback from the user. For example, the answering unit evaluates the quality of the answer based on ratings and comments from the user. Furthermore, the answering unit can improve the quality of the answer by providing feedback. For example, the answering unit improves the answer generation algorithm of the LLM based on feedback from the user. As a result, the answering unit evaluates the quality of the answer and provides feedback, thereby improving the quality of the answer.

[0035] When collecting reviews, the collection unit can select reviews to collect based on the reviewer's past posting frequency and consistency of content. The collection unit, for example, analyzes the reviewer's past posting frequency to select reviews. For example, if a reviewer posts frequently, the collection unit prioritizes collecting those reviews. The collection unit can also analyze the consistency of the reviewer's past posting content to select reviews. For example, if a reviewer's past posting content is consistent, the collection unit prioritizes collecting those reviews. The collection unit can also collect reviews even if the reviewer posts infrequently, as long as the content is consistent. In this way, the collection unit can collect highly reliable reviews by taking into account the reviewer's past posting frequency and consistency of content.

[0036] When collecting reviews, the collection unit can prioritize collecting reviews that include specific keywords or phrases. For example, the collection unit prioritizes collecting reviews that include specific keywords. For example, the collection unit prioritizes collecting reviews that include keywords such as "reliability" and "durability." The collection unit can also prioritize collecting reviews that include specific phrases. For example, the collection unit prioritizes collecting reviews that include phrases such as "recommended" and "repurchase." The collection unit can also collect reviews that include negative keywords. For example, the collection unit also collects reviews that include negative keywords such as "dissatisfaction" and "problem." In this way, the collection unit can collect highly relevant reviews by prioritized collection of reviews that include specific keywords or phrases.

[0037] When collecting reviews, the collection unit can prioritize collecting reliable reviews based on the reviewer's evaluation history. For example, the collection unit analyzes the reviewer's evaluation history and prioritizes collecting reliable reviews. The collection unit preferentially collects reviews from highly rated reviewers. The collection unit can also preferentially collect reviews from reviewers who have received a lot of feedback from other users. For example, the collection unit preferentially collects reviews from reviewers who have received a lot of feedback from other users. The collection unit can also preferentially collect reviews from reviewers who have been evaluated as highly reliable in the past. For example, the collection unit preferentially collects reviews from reviewers who have been evaluated as highly reliable in the past. In this way, the collection unit can obtain highly reliable information by preferentially collecting highly reliable reviews based on the reviewer's evaluation history.

[0038] When collecting reviews, the collection unit can prioritize collecting relevant reviews based on the reviewer's geographical location information. The collection unit, for example, analyzes the reviewer's geographical location information and prioritizes collecting highly relevant reviews. For example, the collection unit prioritizes collecting reviews by reviewers who are close to the user's region. The collection unit can also prioritize collecting reviews by reviewers in the same country or region. For example, the collection unit prioritizes collecting reviews by reviewers in the same country or region. The collection unit can also prioritize collecting reviews that are highly geographically relevant. For example, the collection unit prioritizes collecting reviews that are highly geographically relevant. In this way, the collection unit can collect highly relevant reviews by taking the reviewer's geographical location information into consideration.

[0039] The collection unit can analyze the reviewer's social media activity and collect related reviews when collecting reviews. The collection unit, for example, analyzes the reviewer's social media activity and collects related reviews. For example, the collection unit analyzes the reviewer's social media activity and collects related reviews. The collection unit can also collect reviews taking into account the reviewer's number of followers on social media. For example, the collection unit collects reviews taking into account the reviewer's number of followers on social media. The collection unit can also collect related reviews based on the reviewer's social media posts. For example, the collection unit collects related reviews based on the reviewer's social media posts. In this way, the collection unit can collect highly relevant reviews by analyzing the reviewer's social media activity.

[0040] When collecting reviews, the collection unit can adjust the collection method based on the reviewer's past feedback. The collection unit, for example, determines the priority of reviews to be collected based on the reviewer's past feedback. For example, the collection unit determines the priority of reviews to be collected based on the reviewer's past feedback. The collection unit can also customize the content of reviews to be collected based on the reviewer's past feedback. For example, the collection unit customizes the content of reviews to be collected based on the reviewer's past feedback. The collection unit can also adjust the timing of reviews to be collected based on the reviewer's past feedback. For example, the collection unit adjusts the timing of reviews to be collected based on the reviewer's past feedback. In this way, the collection unit can customize the collection method by reflecting the reviewer's past feedback and collect more appropriate reviews.

[0041] When identifying a reviewer, the identification unit can determine the reliability based on the quality and quantity of the reviewer's past reviews. The identification unit, for example, analyzes the quality of the reviewer's past reviews to determine reliability. For example, the identification unit analyzes the text content of the reviewer's past reviews to evaluate reliability. The identification unit can also analyze the quantity of the reviewer's past reviews to determine reliability. For example, the identification unit analyzes the frequency with which the reviewer has posted past reviews to evaluate reliability. The identification unit can also evaluate reliability by taking into account the balance between the quality and quantity of the reviewer's past reviews. For example, the identification unit evaluates reliability by taking into account the balance between the quality and quantity of the reviewer's past reviews. In this way, the identification unit can identify highly reliable reviewers by taking into account the quality and quantity of the reviewer's past reviews.

[0042] When identifying a reviewer, the identification unit can determine reliability based on the reviewer's expertise or experience. The identification unit, for example, analyzes the reviewer's expertise to determine reliability. For example, the identification unit analyzes the reviewer's qualifications and work history that indicate the reviewer's expertise to evaluate reliability. The identification unit can also analyze the reviewer's experience to determine reliability. For example, the identification unit analyzes the content of the reviewer's past reviews to evaluate reliability. The identification unit can also evaluate reliability by comprehensively considering the reviewer's expertise and experience. For example, the identification unit evaluates reliability by comprehensively considering the reviewer's expertise and experience. In this way, the identification unit can identify highly reliable reviewers by considering the reviewer's expertise and experience.

[0043] When identifying a reviewer, the identification unit can determine reliability based on the consistency of feedback from other users. The identification unit, for example, analyzes the consistency of feedback from other users and determines reliability. For example, the identification unit may evaluate the reliability as high if the feedback from other users is consistently high. Furthermore, the identification unit may evaluate the reliability as low if the feedback from other users is consistently low. For example, the identification unit may evaluate the reliability as low if the feedback from other users is consistently low. Furthermore, the identification unit may evaluate the reliability by comprehensively considering the consistency of feedback from other users. For example, the identification unit evaluates the reliability by comprehensively considering the consistency of feedback from other users. In this way, the identification unit can identify a highly reliable reviewer by considering the consistency of feedback from other users.

[0044] When identifying a reviewer, the identification unit can determine the reliability based on the geographical background of the reviewer. The identification unit, for example, analyzes the geographical background of the reviewer and determines the reliability. For example, the identification unit may evaluate the reliability as high if the reviewer's geographical background is close to that of the user. The identification unit can also evaluate the reliability as low if the reviewer's geographical background is different. For example, the identification unit may evaluate the reliability as low if the reviewer's geographical background is different. The identification unit can also evaluate the reliability by comprehensively considering the geographical background of the reviewer. For example, the identification unit evaluates the reliability by comprehensively considering the geographical background of the reviewer. In this way, the identification unit can identify a highly reliable reviewer by considering the geographical background of the reviewer.

[0045] When identifying a reviewer, the identification unit can determine the reliability based on literature in the reviewer's related field of expertise. For example, the identification unit analyzes literature in the reviewer's related field of expertise to determine reliability. For example, the identification unit evaluates reliability by referring to literature in the reviewer's field of expertise. The identification unit can also evaluate the reliability highly if there are many literature in the reviewer's field of expertise. For example, the identification unit evaluates the reliability highly if there are many literature in the reviewer's field of expertise. The identification unit can also evaluate the reliability by comprehensively considering the literature in the reviewer's field of expertise. For example, the identification unit evaluates the reliability by comprehensively considering the literature in the reviewer's field of expertise. In this way, the identification unit can identify a highly reliable reviewer by referring to literature in the reviewer's field of expertise.

[0046] When identifying a reviewer, the identification unit can determine the reliability based on the market value of the reviewer. The identification unit, for example, analyzes the market value of the reviewer and determines the reliability. For example, if the market value of the reviewer is high, the identification unit can evaluate the reliability as high. Also, if the market value of the reviewer is low, the identification unit can evaluate the reliability as low. For example, if the market value of the reviewer is low, the identification unit can evaluate the reliability as low. Also, the identification unit can evaluate the reliability by comprehensively considering the market value of the reviewer. For example, the identification unit evaluates the reliability by comprehensively considering the market value of the reviewer. In this way, the identification unit can identify a highly reliable reviewer by considering the market value of the reviewer.

[0047] When generating the avatar, the generation unit can create the avatar by reflecting the detailed content of the reviewer's past reviews. The generation unit, for example, generates the avatar based on the detailed content of the reviewer's past reviews. For example, the generation unit analyzes the text content of the reviewer's past reviews to generate the avatar. The generation unit can also generate the avatar by reflecting the ratings of the reviewer's past reviews. For example, the generation unit analyzes the star ratings of the reviewer's past reviews to generate the avatar. The generation unit can also generate the avatar by comprehensively considering the content of the reviewer's past reviews. For example, the generation unit generates the avatar by comprehensively considering the content of the reviewer's past reviews. In this way, the generation unit can generate a highly reliable avatar by reflecting the detailed content of the reviewer's past reviews.

[0048] When generating an avatar, the generation unit can increase the reliability of the avatar based on the reviewer's evaluation history. The generation unit, for example, analyzes the reviewer's evaluation history and increases the reliability of the avatar. For example, if the reviewer's evaluation history is high, the generation unit generates a highly reliable avatar. Furthermore, if the reviewer's evaluation history is low, the generation unit can also generate a less reliable avatar. For example, if the reviewer's evaluation history is low, the generation unit generates a less reliable avatar. Furthermore, the generation unit can generate a highly reliable avatar by comprehensively considering the reviewer's evaluation history. For example, the generation unit generates a highly reliable avatar by comprehensively considering the reviewer's evaluation history. In this way, the generation unit can generate a highly reliable avatar by improving the reliability of the avatar based on the reviewer's evaluation history.

[0049] When generating an avatar, the generation unit can create the avatar by reflecting the reviewer's expertise and experience. The generation unit, for example, analyzes the reviewer's expertise and generates the avatar. For example, the generation unit analyzes the qualifications and work history that indicate the reviewer's expertise and generates the avatar. The generation unit can also analyze the reviewer's experience and generate the avatar. For example, the generation unit analyzes the content of the reviewer's past reviews and generates the avatar. The generation unit can also generate the avatar by comprehensively considering the reviewer's expertise and experience. For example, the generation unit generates the avatar by comprehensively considering the reviewer's expertise and experience. In this way, the generation unit can generate a highly reliable avatar by reflecting the reviewer's expertise and experience.

[0050] When generating an avatar, the generation unit can create an avatar that reflects the reviewer's geographical background. The generation unit, for example, analyzes the reviewer's geographical background and generates the avatar. For example, if the reviewer's geographical background is similar to that of the user, the generation unit generates an avatar that reflects that background. Furthermore, if the reviewer's geographical background is different, the generation unit can also generate an avatar that reflects that background. For example, if the reviewer's geographical background is different, the generation unit generates an avatar that reflects that background. Furthermore, the generation unit can generate an avatar by comprehensively considering the reviewer's geographical background. For example, the generation unit generates an avatar by comprehensively considering the reviewer's geographical background. In this way, the generation unit can generate a highly reliable avatar by reflecting the reviewer's geographical background.

[0051] When generating an avatar, the generation unit can create the avatar based on literature in the reviewer's field of expertise related to the reviewer. The generation unit, for example, analyzes literature in the reviewer's field of expertise and generates the avatar. For example, the generation unit references literature in the reviewer's field of expertise and generates an avatar that reflects that knowledge. Furthermore, if there is a large amount of literature in the reviewer's field of expertise, the generation unit can also generate an avatar that reflects that knowledge. For example, if there is a large amount of literature in the reviewer's field of expertise, the generation unit can generate an avatar that reflects that knowledge. Furthermore, the generation unit can generate an avatar by comprehensively considering the literature in the reviewer's field of expertise. For example, the generation unit generates an avatar by comprehensively considering the literature in the reviewer's field of expertise. In this way, the generation unit can generate a highly reliable avatar by referencing literature in the reviewer's field of expertise.

[0052] When generating an avatar, the generation unit can create an avatar that reflects the market value of the reviewer. The generation unit, for example, analyzes the market value of the reviewer and generates an avatar. For example, if the market value of the reviewer is high, the generation unit generates an avatar that reflects that value. Also, if the market value of the reviewer is low, the generation unit can generate an avatar that reflects that value. For example, if the market value of the reviewer is low, the generation unit generates an avatar that reflects that value. Also The generation unit can also generate an avatar by comprehensively considering the market value of the reviewer. For example, the generation unit generates an avatar by comprehensively considering the market value of the reviewer. This allows the generation unit to generate a highly reliable avatar by reflecting the market value of the reviewer.

[0053] When receiving a question, the reception unit can provide an appropriate interface based on the user's past question history. The reception unit, for example, analyzes the user's past question history and provides an appropriate interface. For example, the reception unit automatically displays questions that the user has frequently asked in the past as candidates. The reception unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. For example, the reception unit preferentially suggests input methods that the user has used in the past. The reception unit can also predict and suggest question content to be used in a specific time period based on the user's past question history. For example, the reception unit predicts and suggests question content to be used in a specific time period based on the user's past question history. In this way, the reception unit can provide an optimal interface by referring to the user's past question history.

[0054] The reception unit can adjust the interface based on the user's current interests when receiving a question. The reception unit, for example, analyzes the user's current interests and adjusts the interface. For example, the reception unit preferentially receives questions related to products in which the user is currently interested. The reception unit can also automatically suggest related questions based on the user's current interests. For example, the reception unit automatically suggests related questions based on the user's current interests. The reception unit can also provide an optimal interface by comprehensively considering the user's current interests. For example, the reception unit provides an optimal interface by comprehensively considering the user's current interests. In this way, the reception unit can provide a more appropriate interface by customizing the interface based on the user's current interests.

[0055] The reception unit can improve the interface based on user feedback when receiving a question. The reception unit, for example, analyzes the user feedback and improves the interface. For example, the reception unit improves the interface design based on the user feedback. The reception unit can also simplify the input procedure based on the user feedback. For example, the reception unit simplifies the input procedure based on the user feedback. The reception unit can also optimize the interface by comprehensively considering the user feedback. For example, the reception unit optimizes the interface by comprehensively considering the user feedback. In this way, the reception unit improves the interface by reflecting the user feedback, thereby improving convenience.

[0056] When receiving a question, the reception unit can provide an appropriate interface based on the user's device information. The reception unit, for example, analyzes the user's device information and provides an appropriate interface. For example, if the user is using a smartphone, the reception unit provides an interface that matches the screen size. Furthermore, if the user is using a tablet, the reception unit can also provide an interface optimized for a large screen. For example, if the user is using a tablet, the reception unit can provide an interface optimized for a large screen. Furthermore, if the user is using a smartwatch, the reception unit can also provide a simple and highly visible interface. For example, if the user is using a smartwatch, the reception unit provides a simple and highly visible interface. In this way, the reception unit can provide an optimal interface by taking the user's device information into consideration.

[0057] When receiving a question, the reception unit can make the interface multilingual in accordance with the user's language setting. The reception unit, for example, analyzes the language setting of the user's device and makes the interface multilingual. For example, the reception unit automatically sets the interface language based on the language setting of the user's device. The reception unit can also provide a language switching function when the user uses multiple languages. For example, the reception unit provides a language switching function when the user uses multiple languages. The reception unit can also provide the interface in a specific language when the user selects that language. For example, the reception unit provides the interface in that language when the user selects a specific language. In this way, the reception unit can make the interface multilingual in accordance with the user's language setting, thereby improving convenience.

[0058] The reception unit can adjust the interface based on the user's occupation or lifestyle when receiving a question. The reception unit, for example, analyzes the user's occupation information and adjusts the interface. For example, the reception unit preferentially receives related question content based on the user's occupation. The reception unit can also analyze the user's lifestyle information and adjust the interface. For example, the reception unit provides an optimal interface based on the user's lifestyle. The reception unit can also customize the interface by comprehensively considering the user's occupation and lifestyle. For example, the reception unit customizes the interface by comprehensively considering the user's occupation and lifestyle. In this way, the reception unit can provide a more appropriate interface by customizing the interface based on the user's occupation and lifestyle.

[0059] The answering unit can adjust the level of detail of the answer based on the importance of the question when generating an answer. The answering unit, for example, analyzes the importance of the question and adjusts the level of detail of the answer. For example, the answering unit provides a detailed answer when the importance of the question is high. Also, the answering unit can provide a concise answer when the importance of the question is low. For example, the answering unit provides a concise answer when the importance of the question is low. Also, the answering unit can provide an optimal answer by comprehensively considering the importance of the question. For example, the answering unit provides an optimal answer by comprehensively considering the importance of the question. In this way, the answering unit can By adjusting the detail of the answer based on the importance of the question, you can provide more relevant answers.

[0060] The answering unit can apply different answering algorithms based on the category of the question when generating an answer. The answering unit, for example, analyzes the category of the question and applies different answering algorithms. For example, the answering unit applies a specialized answering algorithm to a technical question. The answering unit can also apply a concise answering algorithm to a general question. For example, the answering unit applies a concise answering algorithm to a general question. The answering unit can also apply an optimal answering algorithm by comprehensively considering the category of the question. For example, the answering unit applies an optimal answering algorithm by comprehensively considering the category of the question. In this way, the answering unit can provide a more appropriate answer by applying different answering algorithms depending on the category of the question.

[0061] When generating an answer, the answering unit can improve the accuracy of the answer based on the user's past question results. The answering unit, for example, analyzes the user's past question results and improves the accuracy of the answer. For example, the answering unit improves the accuracy of the answer based on the user's past question results. The answering unit can also analyze the user's past question results and provide an optimal answer. For example, the answering unit can analyze the user's past question results and provide an optimal answer. The answering unit can also improve the accuracy of the answer by comprehensively considering the user's past question results. For example, the answering unit improves the accuracy of the answer by comprehensively considering the user's past question results. In this way, the answering unit can improve the accuracy of the answer by referring to the user's past question results.

[0062] When generating an answer, the answering unit can determine the priority of the answers based on the time when the question was submitted. The answering unit, for example, analyzes the time when the question was submitted and determines the priority of the answers. For example, the answering unit provides the answer preferentially if the question was submitted early. The answering unit can also provide the answer later if the question was submitted late. For example, the answering unit provides the answer later if the question was submitted late. The answering unit can also determine the optimal priority of the answers by comprehensively considering the time when the question was submitted. For example, the answering unit determines the optimal priority of the answers by comprehensively considering the time when the question was submitted. In this way, the answering unit can provide a more appropriate answer by determining the priority of the answers based on the time when the question was submitted.

[0063] When generating an answer, the answering unit can adjust the order of answers based on the relevance of the question. The answering unit, for example, analyzes the relevance of the question and adjusts the order of the answers. For example, if the relevance of the question is high, the answering unit provides the answer preferentially. Furthermore, if the relevance of the question is low, the answering unit can also provide the answer at a later date. For example, if the relevance of the question is low, the answering unit provides the answer at a later date. Furthermore, the answering unit can also determine the optimal order of answers by comprehensively considering the relevance of the question. For example, the answering unit determines the optimal order of answers by comprehensively considering the relevance of the question. In this way, the answering unit can provide a more appropriate answer by adjusting the order of answers based on the relevance of the question.

[0064] When generating an answer, the answer unit can adjust the use of technical terminology in the answer based on the user's level of expertise. The answer unit, for example, analyzes the user's level of expertise and adjusts the use of technical terminology in the answer. For example, if the user's level of expertise is high, the answer unit provides an answer that uses a lot of technical terminology. Furthermore, if the user's level of expertise is low, the answer unit can also provide an answer that explains in simple language. For example, if the user's level of expertise is low, the answer unit provides an answer that explains in simple language. Furthermore, the answer unit can adjust the use of optimal technical terminology by comprehensively considering the user's level of expertise. For example, the answer unit adjusts the use of optimal technical terminology by comprehensively considering the user's level of expertise. In this way, the answer unit can provide a more appropriate answer by adjusting the use of technical terminology in the answer according to the user's level of expertise.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The collection unit can also analyze the user's purchase history and preferentially collect related reviews. For example, the collection unit preferentially collects reviews related to products that the user has purchased in the past. The collection unit can also preferentially collect reviews related to products in a category that the user frequently purchases. Furthermore, the collection unit can collect reviews related to new products that the user may be interested in based on the user's purchase history. In this way, the collection unit can collect more relevant reviews by taking the user's purchase history into consideration.

[0067] The identification unit may also consider the reviewer's social media activity when evaluating the reviewer's credibility. For example, the identification unit may analyze the reviewer's number of followers and engagement rate on social media to evaluate credibility. The identification unit may also evaluate the quality and consistency of the content the reviewer shares on social media. Furthermore, the identification unit may evaluate the reviewer's expertise and credibility based on the reviewer's social media activity history. As a result, the identification unit can identify more reliable reviewers by considering the reviewer's social media activity.

[0068] The generation unit can also reflect the reviewer's personality and style when generating the reviewer's avatar. For example, the generation unit analyzes the reviewer's writing style and expression methods in past reviews and reflects them in the avatar. The generation unit can also generate an avatar that reflects the reviewer's preferences and interests. Furthermore, the generation unit can generate an avatar that reflects the tone and emotions of the reviewer's past reviews. In this way, the generation unit can generate a more realistic and reliable avatar by reflecting the reviewer's personality and style.

[0069] When a user inputs a question, the reception unit can customize the interface according to the category and content of the question. For example, the reception unit can provide detailed input options for technical questions. The reception unit can also provide concise input options for general questions. Furthermore, the reception unit can automatically suggest related question candidates based on the content of the user's question. In this way, the reception unit can provide a more appropriate question input environment by customizing the interface according to the content of the user's question.

[0070] The processing flow of the first embodiment will be briefly explained below.

[0071] Step 1: The collection unit collects product reviews. The collection unit can automatically collect product reviews from, for example, an online platform. The collection unit can also collect reviews manually entered by users. Step 2: The identification unit analyzes the reviews collected by the collection unit and identifies reliable reviewers. The identification unit evaluates the reliability of the reviewers based on, for example, the ratings of their past reviews and feedback from other users. Step 3: The generator generates an avatar of the reviewer identified by the identifier, for example, based on the reviewer's past reviews and ratings. Step 4: The reception unit provides an interface through which the user can input a question to the avatar generated by the generation unit. The reception unit provides an interface through which the user can input a question by text input or voice input, for example. Step 5: The answering unit generates an answer to the question input by the receiving unit. The answering unit generates an answer to the user's question using, for example, an LLM.

[0072] (Example 2) A review support system according to an embodiment of the present invention generates avatars of reliable reviewers and allows users to directly ask questions. This review support system collects product reviews and analyzes them using a large-scale language model (LLM). Based on the analysis results, a reliable reviewer is identified, and the LLM generates an avatar for the reviewer. This avatar is based on the reviewer's past reviews and ratings, allowing users to directly ask questions. For example, when a user asks, "How durable is this product?", the LLM responds as the reviewer's avatar. This mechanism allows users to obtain additional information while referring to reliable reviews, thereby making purchasing decisions more reliable. For example, the review support system collects product reviews and analyzes them using an LLM. The system analyzes the content and ratings of reviewers' past reviews in detail to identify reliable reviewers. For example, the system evaluates the reviewer's trustworthiness based on the ratings of the reviewer's past reviews and feedback from other users. The system then identifies a reliable reviewer and generates an avatar for the reviewer. This avatar is based on the reviewer's past reviews and ratings, allowing users to directly ask questions. For example, if a user asks, "How durable is this product?", the LLM will respond as the reviewer's avatar. In addition, an interface is provided for users to ask questions. A UI / UX is designed to make it easy for users to ask questions, and a feedback function is also introduced to ensure the quality of the answers generated by the LLM. For example, when a user asks a question, the quality of the answer generated by the LLM can be evaluated and feedback provided to improve the quality of the answer. This mechanism allows users to obtain additional information while referring to reliable reviews, making purchasing decisions more reliable. As a result, the review support system allows users to ask questions directly through the avatar of a reliable reviewer and obtain reliable information.

[0073] A review support system according to an embodiment includes a collection unit, an identification unit, a generation unit, a reception unit, and an answering unit. The collection unit collects product reviews. The collection unit can automatically collect product reviews from, for example, an online platform. The collection unit can also collect reviews manually entered by a user. The identification unit analyzes the reviews collected by the collection unit to identify reliable reviewers. The identification unit evaluates the reviewer's reliability based on, for example, ratings of past reviews and feedback from other users. The generation unit generates an avatar for the reviewer identified by the identification unit. The generation unit generates the avatar based on, for example, the reviewer's past reviews and ratings. The reception unit provides an interface through which a user inputs a question to the avatar generated by the generation unit. The reception unit provides an interface through which a user can input a question by, for example, text input or voice input. The answering unit generates an answer to the question input by the reception unit. The answering unit generates an answer to the user's question using, for example, an LLM. As a result, the review support system according to the embodiment allows the user to ask questions directly through the avatar of a reliable reviewer and obtain highly reliable information.

[0074] The collection unit can analyze the content and ratings of the reviewer's past reviews. For example, the collection unit analyzes the content of the reviewer's past reviews using text analysis technology. For example, the collection unit analyzes the text content of the reviewer's past reviews and extracts the reviewer's ratings. The collection unit can also analyze the star ratings of the reviewer's past reviews. For example, the collection unit aggregates the star ratings of the reviewer's past reviews and evaluates the reviewer's reliability. The collection unit can also analyze feedback from other users. For example, the collection unit analyzes comments and ratings from other users and evaluates the reviewer's reliability. In this way, the collection unit can identify highly reliable reviewers by analyzing the content and ratings of the reviewer's past reviews in detail.

[0075] The identification unit can determine the trustworthiness based on the ratings of the reviewer's past reviews and feedback from other users. The identification unit, for example, analyzes the ratings of the reviewer's past reviews to determine trustworthiness. For example, the identification unit aggregates the star ratings of the reviewer's past reviews and evaluates trustworthiness. The identification unit can also analyze feedback from other users to determine trustworthiness. For example, the identification unit analyzes comments and ratings from other users to evaluate the reviewer's trustworthiness. In this way, the identification unit can identify a reliable reviewer by evaluating the reviewer's trustworthiness highly.

[0076] The generation unit can create an avatar based on the reviewer's past reviews and ratings. The generation unit generates an avatar based on, for example, the content of the reviewer's past reviews. For example, the generation unit analyzes the text content of the reviewer's past reviews to generate an avatar. The generation unit can also generate an avatar based on the ratings of the reviewer's past reviews. For example, the generation unit analyzes the star ratings of the reviewer's past reviews to generate an avatar. The generation unit can also generate an avatar based on feedback from other users. For example, the generation unit analyzes comments and ratings from other users to generate an avatar. In this way, the generation unit can provide a highly reliable avatar by generating an avatar based on the reviewer's past reviews and ratings.

[0077] The reception unit can provide an interface through which the user inputs a question. For example, the reception unit provides an interface through which the user can input a question by text input. For example, the reception unit provides an interface through which the user can input a question into a text box. The reception unit can also provide an interface through which the user can input a question by voice input. For example, the reception unit provides an interface through which the user can input a question by voice using a microphone. In this way, the reception unit provides an interface through which the user can easily input a question, thereby improving convenience.

[0078] The answering unit can determine the quality of the answer generated by the LLM when a user asks a question and provide feedback. For example, the answering unit evaluates the quality of the answer generated by the LLM when a user asks a question. For example, the answering unit evaluates the accuracy and relevance of the answer generated by the LLM. The answering unit can also evaluate the quality of the answer based on feedback from the user. For example, the answering unit evaluates the quality of the answer based on ratings and comments from the user. Furthermore, the answering unit can improve the quality of the answer by providing feedback. For example, the answering unit improves the answer generation algorithm of the LLM based on feedback from the user. As a result, the answering unit evaluates the quality of the answer and provides feedback, thereby improving the quality of the answer.

[0079] The collection unit can estimate a user's emotions and adjust the timing of review collection based on the estimated user's emotions. The collection unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the collection unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The collection unit can also estimate the user's emotions using voice analysis technology. For example, the collection unit analyzes the tone and speed of the user's voice to estimate the emotions. The collection unit can also estimate the user's emotions using text analysis technology. For example, the collection unit analyzes the user's text messages to estimate the emotions. The collection unit also adjusts the timing of review collection based on the estimated user's emotions. For example, if the user is feeling stressed, the collection unit collects reviews during a relaxed time. If the user is excited, the collection unit can collect reviews immediately. If the user is tired, the collection unit can collect reviews after a rest. In this way, the collection unit can adjust the timing of review collection according to the user's emotions, thereby collecting reviews at a more appropriate time.

[0080] When collecting reviews, the collection unit can select reviews to collect based on the reviewer's past posting frequency and consistency of content. The collection unit, for example, analyzes the reviewer's past posting frequency to select reviews. For example, if a reviewer posts frequently, the collection unit prioritizes collecting those reviews. The collection unit can also analyze the consistency of the reviewer's past posting content to select reviews. For example, if a reviewer's past posting content is consistent, the collection unit prioritizes collecting those reviews. The collection unit can also collect reviews even if the reviewer posts infrequently, as long as the content is consistent. In this way, the collection unit can collect highly reliable reviews by taking into account the reviewer's past posting frequency and consistency of content.

[0081] When collecting reviews, the collection unit can prioritize collecting reviews that include specific keywords or phrases. For example, the collection unit prioritizes collecting reviews that include specific keywords. For example, the collection unit prioritizes collecting reviews that include keywords such as "reliability" and "durability." The collection unit can also prioritize collecting reviews that include specific phrases. For example, the collection unit prioritizes collecting reviews that include phrases such as "recommended" and "repurchase." The collection unit can also collect reviews that include negative keywords. For example, the collection unit also collects reviews that include negative keywords such as "dissatisfaction" and "problem." In this way, the collection unit can collect highly relevant reviews by prioritized collection of reviews that include specific keywords or phrases.

[0082] When collecting reviews, the collection unit can prioritize collecting reliable reviews based on the reviewer's evaluation history. For example, the collection unit analyzes the reviewer's evaluation history and prioritizes collecting reliable reviews. The collection unit preferentially collects reviews from highly rated reviewers. The collection unit can also preferentially collect reviews from reviewers who have received a lot of feedback from other users. For example, the collection unit preferentially collects reviews from reviewers who have received a lot of feedback from other users. The collection unit can also preferentially collect reviews from reviewers who have been evaluated as highly reliable in the past. For example, the collection unit preferentially collects reviews from reviewers who have been evaluated as highly reliable in the past. In this way, the collection unit can obtain highly reliable information by preferentially collecting highly reliable reviews based on the reviewer's evaluation history.

[0083] The collection unit can estimate the user's emotions and determine the priority of reviews to be collected based on the estimated user's emotions. The collection unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the collection unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The collection unit can also estimate the user's emotions using voice analysis technology. For example, the collection unit analyzes the tone and speed of the user's voice to estimate the emotions. The collection unit can also estimate the user's emotions using text analysis technology. For example, the collection unit analyzes the user's text messages to estimate the emotions. The collection unit can also determine the priority of reviews to be collected based on the estimated user's emotions. For example, the collection unit can prioritize collecting reliable reviews when the user is feeling anxious. The collection unit can also prioritize collecting the most recent reviews when the user is excited. The collection unit can also prioritize collecting detailed reviews when the user is relaxed. In this way, the collection unit can collect more appropriate reviews by determining the priority of reviews to be collected according to the user's emotions.

[0084] When collecting reviews, the collection unit can prioritize collecting relevant reviews based on the reviewer's geographical location information. The collection unit, for example, analyzes the reviewer's geographical location information and prioritizes collecting highly relevant reviews. For example, the collection unit prioritizes collecting reviews by reviewers who are close to the user's region. The collection unit can also prioritize collecting reviews by reviewers in the same country or region. For example, the collection unit prioritizes collecting reviews by reviewers in the same country or region. The collection unit can also prioritize collecting reviews that are highly geographically relevant. For example, the collection unit prioritizes collecting reviews that are highly geographically relevant. In this way, the collection unit can collect highly relevant reviews by taking the reviewer's geographical location information into consideration.

[0085] The collection unit can analyze the reviewer's social media activity and collect related reviews when collecting reviews. The collection unit, for example, analyzes the reviewer's social media activity and collects related reviews. For example, the collection unit analyzes the reviewer's social media activity and collects related reviews. The collection unit can also collect reviews taking into account the reviewer's number of followers on social media. For example, the collection unit collects reviews taking into account the reviewer's number of followers on social media. The collection unit can also collect related reviews based on the reviewer's social media posts. For example, the collection unit collects related reviews based on the reviewer's social media posts. In this way, the collection unit can collect highly relevant reviews by analyzing the reviewer's social media activity.

[0086] When collecting reviews, the collection unit can adjust the collection method based on the reviewer's past feedback. The collection unit, for example, determines the priority of reviews to be collected based on the reviewer's past feedback. For example, the collection unit determines the priority of reviews to be collected based on the reviewer's past feedback. The collection unit can also customize the content of reviews to be collected based on the reviewer's past feedback. For example, the collection unit customizes the content of reviews to be collected based on the reviewer's past feedback. The collection unit can also adjust the timing of reviews to be collected based on the reviewer's past feedback. For example, the collection unit adjusts the timing of reviews to be collected based on the reviewer's past feedback. In this way, the collection unit can customize the collection method by reflecting the reviewer's past feedback and collect more appropriate reviews.

[0087] The identification unit can estimate the user's emotions and adjust the criteria for identifying a reliable reviewer based on the estimated user's emotions. The identification unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the identification unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The identification unit can also estimate the user's emotions using voice analysis technology. For example, the identification unit analyzes the tone and speed of the user's voice to estimate the emotions. The identification unit can also estimate the user's emotions using text analysis technology. For example, the identification unit analyzes the user's text messages to estimate the emotions. The identification unit can also adjust the criteria for identifying a reliable reviewer based on the estimated user's emotions. For example, the identification unit can prioritize identifying a reliable reviewer when the user is anxious. The identification unit can prioritize identifying the most recent reviewer when the user is excited. The identification unit can also prioritize identifying a reviewer who provides detailed reviews when the user is relaxed. This allows the identification unit to adjust the criteria for identifying reliable reviewers according to the user's feelings, thereby enabling the identification unit to identify more appropriate reviewers.

[0088] When identifying a reviewer, the identification unit can determine the reliability based on the quality and quantity of the reviewer's past reviews. The identification unit, for example, analyzes the quality of the reviewer's past reviews to determine reliability. For example, the identification unit analyzes the text content of the reviewer's past reviews to evaluate reliability. The identification unit can also analyze the quantity of the reviewer's past reviews to determine reliability. For example, the identification unit analyzes the frequency with which the reviewer has posted past reviews to evaluate reliability. The identification unit can also evaluate reliability by taking into account the balance between the quality and quantity of the reviewer's past reviews. For example, the identification unit evaluates reliability by taking into account the balance between the quality and quantity of the reviewer's past reviews. In this way, the identification unit can identify highly reliable reviewers by taking into account the quality and quantity of the reviewer's past reviews.

[0089] When identifying a reviewer, the identification unit can determine reliability based on the reviewer's expertise or experience. The identification unit, for example, analyzes the reviewer's expertise to determine reliability. For example, the identification unit analyzes the reviewer's qualifications and work history that indicate the reviewer's expertise to evaluate reliability. The identification unit can also analyze the reviewer's experience to determine reliability. For example, the identification unit analyzes the content of the reviewer's past reviews to evaluate reliability. The identification unit can also evaluate reliability by comprehensively considering the reviewer's expertise and experience. For example, the identification unit evaluates reliability by comprehensively considering the reviewer's expertise and experience. In this way, the identification unit can identify highly reliable reviewers by considering the reviewer's expertise and experience.

[0090] When identifying a reviewer, the identification unit can determine reliability based on the consistency of feedback from other users. The identification unit, for example, analyzes the consistency of feedback from other users and determines reliability. For example, the identification unit may evaluate the reliability as high if the feedback from other users is consistently high. Furthermore, the identification unit may evaluate the reliability as low if the feedback from other users is consistently low. For example, the identification unit may evaluate the reliability as low if the feedback from other users is consistently low. Furthermore, the identification unit may evaluate the reliability by comprehensively considering the consistency of feedback from other users. For example, the identification unit evaluates the reliability by comprehensively considering the consistency of feedback from other users. In this way, the identification unit can identify a highly reliable reviewer by considering the consistency of feedback from other users.

[0091] The identification unit can estimate the user's emotions and adjust the display order of reliable reviewers based on the estimated user's emotions. The identification unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the identification unit captures the user's facial expression with a camera and estimates the emotion using a facial expression recognition algorithm. The identification unit can also estimate the user's emotions using voice analysis technology. For example, the identification unit analyzes the tone and speed of the user's voice to estimate the emotion. The identification unit can also estimate the user's emotions using text analysis technology. For example, the identification unit analyzes the user's text messages to estimate the emotion. The identification unit also adjusts the display order of reliable reviewers based on the estimated user's emotions. For example, if the user is feeling anxious, the identification unit can display reliable reviewers at the top. If the user is excited, the identification unit can display the most recent reviewers at the top. If the user is relaxed, the identification unit can display reviewers who provide detailed reviews at the top. In this way, the identification unit can select reliable reviewers according to the user's emotions. By adjusting the display order, you can display more appropriate reviewers.

[0092] When identifying a reviewer, the identification unit can determine the reliability based on the geographical background of the reviewer. The identification unit, for example, analyzes the geographical background of the reviewer and determines the reliability. For example, the identification unit may evaluate the reliability as high if the reviewer's geographical background is close to that of the user. The identification unit can also evaluate the reliability as low if the reviewer's geographical background is different. For example, the identification unit may evaluate the reliability as low if the reviewer's geographical background is different. The identification unit can also evaluate the reliability by comprehensively considering the geographical background of the reviewer. For example, the identification unit evaluates the reliability by comprehensively considering the geographical background of the reviewer. In this way, the identification unit can identify a highly reliable reviewer by considering the geographical background of the reviewer.

[0093] When identifying a reviewer, the identification unit can determine the reliability based on literature in the reviewer's related field of expertise. For example, the identification unit analyzes literature in the reviewer's related field of expertise to determine reliability. For example, the identification unit evaluates reliability by referring to literature in the reviewer's field of expertise. The identification unit can also evaluate the reliability highly if there are many literature in the reviewer's field of expertise. For example, the identification unit evaluates the reliability highly if there are many literature in the reviewer's field of expertise. The identification unit can also evaluate the reliability by comprehensively considering the literature in the reviewer's field of expertise. For example, the identification unit evaluates the reliability by comprehensively considering the literature in the reviewer's field of expertise. In this way, the identification unit can identify a highly reliable reviewer by referring to literature in the reviewer's field of expertise.

[0094] When identifying a reviewer, the identification unit can determine the reliability based on the market value of the reviewer. The identification unit, for example, analyzes the market value of the reviewer and determines the reliability. For example, if the market value of the reviewer is high, the identification unit can evaluate the reliability as high. Also, if the market value of the reviewer is low, the identification unit can evaluate the reliability as low. For example, if the market value of the reviewer is low, the identification unit can evaluate the reliability as low. Also, the identification unit can evaluate the reliability by comprehensively considering the market value of the reviewer. For example, the identification unit evaluates the reliability by comprehensively considering the market value of the reviewer. In this way, the identification unit can identify a highly reliable reviewer by considering the market value of the reviewer.

[0095] The generation unit can estimate the user's emotions and adjust the avatar generation method based on the estimated user's emotions. The generation unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the generation unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The generation unit can also estimate the user's emotions using voice analysis technology. For example, the generation unit analyzes the tone and speed of the user's voice to estimate the emotions. The generation unit can also estimate the user's emotions using text analysis technology. For example, the generation unit analyzes the user's text messages to estimate the emotions. The generation unit also adjusts the avatar generation method based on the estimated user's emotions. For example, if the user is relaxed, the generation unit generates an avatar that progresses at a leisurely pace. If the user is in a hurry, the generation unit can generate an avatar that emphasizes the shortest route. If the user is excited, the generation unit can generate an avatar with visually stimulating effects. In this way, the generation unit can generate a more appropriate avatar by adjusting the avatar generation method according to the user's emotions.

[0096] When generating the avatar, the generation unit can create the avatar by reflecting the detailed content of the reviewer's past reviews. The generation unit, for example, generates the avatar based on the detailed content of the reviewer's past reviews. For example, the generation unit analyzes the text content of the reviewer's past reviews to generate the avatar. The generation unit can also generate the avatar by reflecting the ratings of the reviewer's past reviews. For example, the generation unit analyzes the star ratings of the reviewer's past reviews to generate the avatar. The generation unit can also generate the avatar by comprehensively considering the content of the reviewer's past reviews. For example, the generation unit generates the avatar by comprehensively considering the content of the reviewer's past reviews. In this way, the generation unit can generate a highly reliable avatar by reflecting the detailed content of the reviewer's past reviews.

[0097] When generating an avatar, the generation unit can increase the reliability of the avatar based on the reviewer's evaluation history. The generation unit, for example, analyzes the reviewer's evaluation history and increases the reliability of the avatar. For example, if the reviewer's evaluation history is high, the generation unit generates a highly reliable avatar. Furthermore, if the reviewer's evaluation history is low, the generation unit can also generate a less reliable avatar. For example, if the reviewer's evaluation history is low, the generation unit generates a less reliable avatar. Furthermore, the generation unit can generate a highly reliable avatar by comprehensively considering the reviewer's evaluation history. For example, the generation unit generates a highly reliable avatar by comprehensively considering the reviewer's evaluation history. In this way, the generation unit can generate a highly reliable avatar by improving the reliability of the avatar based on the reviewer's evaluation history.

[0098] When generating an avatar, the generation unit can create the avatar by reflecting the reviewer's expertise and experience. The generation unit, for example, analyzes the reviewer's expertise and generates the avatar. For example, the generation unit analyzes the qualifications and work history that indicate the reviewer's expertise and generates the avatar. The generation unit can also analyze the reviewer's experience and generate the avatar. For example, the generation unit analyzes the content of the reviewer's past reviews and generates the avatar. The generation unit can also generate the avatar by comprehensively considering the reviewer's expertise and experience. For example, the generation unit generates the avatar by comprehensively considering the reviewer's expertise and experience. In this way, the generation unit can generate a highly reliable avatar by reflecting the reviewer's expertise and experience.

[0099] The generation unit can estimate the user's emotions and adjust the display method of the alter ego based on the estimated user's emotions. The generation unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the generation unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The generation unit can also estimate the user's emotions using voice analysis technology. For example, the generation unit can analyze the tone and speed of the user's voice to estimate the emotions. The generation unit can also estimate the user's emotions using text analysis technology. For example, the generation unit can analyze the user's text messages to estimate the emotions. The generation unit can also adjust the display method of the alter ego based on the estimated user's emotions. For example, the generation unit can provide a relaxed display method when the user is relaxed. The generation unit can also provide a concise and quick display method when the user is in a hurry. The generation unit can also provide a visually stimulating display method when the user is excited. In this way, the generation unit can provide a more appropriate display method by adjusting the display method of the alter ego according to the user's emotions.

[0100] When generating an avatar, the generation unit can create an avatar that reflects the reviewer's geographical background. The generation unit, for example, analyzes the reviewer's geographical background and generates the avatar. For example, if the reviewer's geographical background is similar to that of the user, the generation unit generates an avatar that reflects that background. Furthermore, if the reviewer's geographical background is different, the generation unit can also generate an avatar that reflects that background. For example, if the reviewer's geographical background is different, the generation unit generates an avatar that reflects that background. Furthermore, the generation unit can generate an avatar by comprehensively considering the reviewer's geographical background. For example, the generation unit generates an avatar by comprehensively considering the reviewer's geographical background. In this way, the generation unit can generate a highly reliable avatar by reflecting the reviewer's geographical background.

[0101] When generating an avatar, the generation unit can create the avatar based on literature in the reviewer's field of expertise related to the reviewer. The generation unit, for example, analyzes literature in the reviewer's field of expertise and generates the avatar. For example, the generation unit references literature in the reviewer's field of expertise and generates an avatar that reflects that knowledge. Furthermore, if there is a large amount of literature in the reviewer's field of expertise, the generation unit can also generate an avatar that reflects that knowledge. For example, if there is a large amount of literature in the reviewer's field of expertise, the generation unit can generate an avatar that reflects that knowledge. Furthermore, the generation unit can generate an avatar by comprehensively considering the literature in the reviewer's field of expertise. For example, the generation unit generates an avatar by comprehensively considering the literature in the reviewer's field of expertise. In this way, the generation unit can generate a highly reliable avatar by referencing literature in the reviewer's field of expertise.

[0102] When generating an avatar, the generation unit can create an avatar that reflects the market value of the reviewer. The generation unit, for example, analyzes the market value of the reviewer and generates an avatar. For example, if the market value of the reviewer is high, the generation unit generates an avatar that reflects that value. Also, if the market value of the reviewer is low, the generation unit can generate an avatar that reflects that value. For example, if the market value of the reviewer is low, the generation unit generates an avatar that reflects that value. Also The generation unit can also generate an avatar by comprehensively considering the market value of the reviewer. For example, the generation unit generates an avatar by comprehensively considering the market value of the reviewer. This allows the generation unit to generate a highly reliable avatar by reflecting the market value of the reviewer.

[0103] The reception unit can estimate the user's emotion and adjust the question reception interface based on the estimated user's emotion. The reception unit, for example, estimates the user's emotion using facial expression recognition technology. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using a facial expression recognition algorithm. The reception unit can also estimate the user's emotion using voice analysis technology. For example, the reception unit can analyze the tone and speed of the user's voice to estimate the emotion. The reception unit can also estimate the user's emotion using text analysis technology. For example, the reception unit can analyze the user's text messages to estimate the emotion. The reception unit can also adjust the question reception interface based on the estimated user's emotion. For example, the reception unit can provide a simple interface and minimize input steps when the user is feeling stressed. The reception unit can also provide detailed input options and suggest customizable input methods when the user is relaxed. The reception unit can also prioritize voice input when the user is in a hurry, allowing the user to input questions quickly. This allows the reception unit to provide a more appropriate interface by adjusting the question reception interface in accordance with the user's emotions.

[0104] When receiving a question, the reception unit can provide an appropriate interface based on the user's past question history. The reception unit, for example, analyzes the user's past question history and provides an appropriate interface. For example, the reception unit automatically displays questions that the user has frequently asked in the past as candidates. The reception unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. For example, the reception unit preferentially suggests input methods that the user has used in the past. The reception unit can also predict and suggest question content to be used in a specific time period based on the user's past question history. For example, the reception unit predicts and suggests question content to be used in a specific time period based on the user's past question history. In this way, the reception unit can provide an optimal interface by referring to the user's past question history.

[0105] The reception unit can adjust the interface based on the user's current interests when receiving a question. The reception unit, for example, analyzes the user's current interests and adjusts the interface. For example, the reception unit preferentially receives questions related to products in which the user is currently interested. The reception unit can also automatically suggest related questions based on the user's current interests. For example, the reception unit automatically suggests related questions based on the user's current interests. The reception unit can also provide an optimal interface by comprehensively considering the user's current interests. For example, the reception unit provides an optimal interface by comprehensively considering the user's current interests. In this way, the reception unit can provide a more appropriate interface by customizing the interface based on the user's current interests.

[0106] The reception unit can improve the interface based on user feedback when receiving a question. The reception unit, for example, analyzes the user feedback and improves the interface. For example, the reception unit improves the interface design based on the user feedback. The reception unit can also simplify the input procedure based on the user feedback. For example, the reception unit simplifies the input procedure based on the user feedback. The reception unit can also optimize the interface by comprehensively considering the user feedback. For example, the reception unit optimizes the interface by comprehensively considering the user feedback. In this way, the reception unit improves the interface by reflecting the user feedback, thereby improving convenience.

[0107] The reception unit can estimate the user's emotions and determine the priority of question reception based on the estimated user's emotions. The reception unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using a facial expression recognition algorithm. The reception unit can also estimate the user's emotions using voice analysis technology. For example, the reception unit analyzes the tone and speed of the user's voice to estimate the emotion. The reception unit can also estimate the user's emotions using text analysis technology. For example, the reception unit analyzes the user's text messages to estimate the emotion. The reception unit can also determine the priority of question reception based on the estimated user's emotions. For example, the reception unit can prioritize urgent questions when the user is feeling anxious. The reception unit can prioritize the most recent questions when the user is excited. The reception unit can prioritize detailed questions when the user is relaxed. In this way, the reception unit can prioritize the reception of questions based on the user's emotions, thereby allowing more appropriate questions to be received.

[0108] When receiving a question, the reception unit can provide an appropriate interface based on the user's device information. The reception unit, for example, analyzes the user's device information and provides an appropriate interface. For example, if the user is using a smartphone, the reception unit provides an interface that matches the screen size. Furthermore, if the user is using a tablet, the reception unit can also provide an interface optimized for a large screen. For example, if the user is using a tablet, the reception unit can provide an interface optimized for a large screen. Furthermore, if the user is using a smartwatch, the reception unit can also provide a simple and highly visible interface. For example, if the user is using a smartwatch, the reception unit provides a simple and highly visible interface. In this way, the reception unit can provide an optimal interface by taking the user's device information into consideration.

[0109] When receiving a question, the reception unit can make the interface multilingual in accordance with the user's language setting. The reception unit, for example, analyzes the language setting of the user's device and makes the interface multilingual. For example, the reception unit automatically sets the interface language based on the language setting of the user's device. The reception unit can also provide a language switching function when the user uses multiple languages. For example, the reception unit provides a language switching function when the user uses multiple languages. The reception unit can also provide the interface in a specific language when the user selects that language. For example, the reception unit provides the interface in that language when the user selects a specific language. In this way, the reception unit can make the interface multilingual in accordance with the user's language setting, thereby improving convenience.

[0110] The reception unit can adjust the interface based on the user's occupation or lifestyle when receiving a question. The reception unit, for example, analyzes the user's occupation information and adjusts the interface. For example, the reception unit preferentially receives related question content based on the user's occupation. The reception unit can also analyze the user's lifestyle information and adjust the interface. For example, the reception unit provides an optimal interface based on the user's lifestyle. The reception unit can also customize the interface by comprehensively considering the user's occupation and lifestyle. For example, the reception unit customizes the interface by comprehensively considering the user's occupation and lifestyle. In this way, the reception unit can provide a more appropriate interface by customizing the interface based on the user's occupation and lifestyle.

[0111] The answering unit can estimate the user's emotions and adjust the way the answer is expressed based on the estimated user's emotions. The answering unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the answering unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The answering unit can also estimate the user's emotions using voice analysis technology. For example, the answering unit can analyze the tone and speed of the user's voice to estimate the emotions. The answering unit can also estimate the user's emotions using text analysis technology. For example, the answering unit can analyze the user's text messages to estimate the emotions. Furthermore, the answering unit adjusts the way the answer is expressed based on the estimated user's emotions. For example, the answering unit can provide a simple, highly visible answer when the user is nervous. The answering unit can provide an answer that includes detailed information when the user is relaxed. The answering unit can also provide an answer that focuses on the main points when the user is in a hurry. This allows the answering unit to provide a more appropriate answer by adjusting the way the answer is expressed based on the user's emotions.

[0112] The answering unit can adjust the level of detail of the answer based on the importance of the question when generating an answer. The answering unit, for example, analyzes the importance of the question and adjusts the level of detail of the answer. For example, the answering unit provides a detailed answer when the importance of the question is high. Also, the answering unit can provide a concise answer when the importance of the question is low. For example, the answering unit provides a concise answer when the importance of the question is low. Also, the answering unit can provide an optimal answer by comprehensively considering the importance of the question. For example, the answering unit provides an optimal answer by comprehensively considering the importance of the question. In this way, the answering unit can By adjusting the detail of the answer based on the importance of the question, you can provide more relevant answers.

[0113] The answering unit can apply different answering algorithms based on the category of the question when generating an answer. The answering unit, for example, analyzes the category of the question and applies different answering algorithms. For example, the answering unit applies a specialized answering algorithm to a technical question. The answering unit can also apply a concise answering algorithm to a general question. For example, the answering unit applies a concise answering algorithm to a general question. The answering unit can also apply an optimal answering algorithm by comprehensively considering the category of the question. For example, the answering unit applies an optimal answering algorithm by comprehensively considering the category of the question. In this way, the answering unit can provide a more appropriate answer by applying different answering algorithms depending on the category of the question.

[0114] When generating an answer, the answering unit can improve the accuracy of the answer based on the user's past question results. The answering unit, for example, analyzes the user's past question results and improves the accuracy of the answer. For example, the answering unit improves the accuracy of the answer based on the user's past question results. The answering unit can also analyze the user's past question results and provide an optimal answer. For example, the answering unit can analyze the user's past question results and provide an optimal answer. The answering unit can also improve the accuracy of the answer by comprehensively considering the user's past question results. For example, the answering unit improves the accuracy of the answer by comprehensively considering the user's past question results. In this way, the answering unit can improve the accuracy of the answer by referring to the user's past question results.

[0115] The answering unit can estimate the user's emotions and adjust the length of the answer based on the estimated user's emotions. The answering unit, for example, estimates the user's emotions using facial expression recognition technology. For example, the answering unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The answering unit can also estimate the user's emotions using voice analysis technology. For example, the answering unit can analyze the tone and speed of the user's voice to estimate the emotions. The answering unit can also estimate the user's emotions using text analysis technology. For example, the answering unit can analyze the user's text messages to estimate the emotions. The answering unit can also adjust the length of the answer based on the estimated user's emotions. For example, the answering unit can provide a short and to-the-point answer if the user is in a hurry. The answering unit can also provide a longer answer with detailed explanations if the user is relaxed. The answering unit can also provide an answer with visually stimulating effects if the user is excited. This allows the answering unit to provide a more appropriate answer by adjusting the length of the answer according to the user's emotions.

[0116] When generating an answer, the answering unit can determine the priority of the answers based on the time when the question was submitted. The answering unit, for example, analyzes the time when the question was submitted and determines the priority of the answers. For example, the answering unit provides the answer preferentially if the question was submitted early. The answering unit can also provide the answer later if the question was submitted late. For example, the answering unit provides the answer later if the question was submitted late. The answering unit can also determine the optimal priority of the answers by comprehensively considering the time when the question was submitted. For example, the answering unit determines the optimal priority of the answers by comprehensively considering the time when the question was submitted. In this way, the answering unit can provide a more appropriate answer by determining the priority of the answers based on the time when the question was submitted.

[0117] When generating an answer, the answering unit can adjust the order of answers based on the relevance of the question. The answering unit, for example, analyzes the relevance of the question and adjusts the order of the answers. For example, if the relevance of the question is high, the answering unit provides the answer preferentially. Furthermore, if the relevance of the question is low, the answering unit can also provide the answer at a later date. For example, if the relevance of the question is low, the answering unit provides the answer at a later date. Furthermore, the answering unit can also determine the optimal order of answers by comprehensively considering the relevance of the question. For example, the answering unit determines the optimal order of answers by comprehensively considering the relevance of the question. In this way, the answering unit can provide a more appropriate answer by adjusting the order of answers based on the relevance of the question.

[0118] When generating an answer, the answer unit can adjust the use of technical terminology in the answer based on the user's level of expertise. The answer unit, for example, analyzes the user's level of expertise and adjusts the use of technical terminology in the answer. For example, if the user's level of expertise is high, the answer unit provides an answer that uses a lot of technical terminology. Furthermore, if the user's level of expertise is low, the answer unit can also provide an answer that explains in simple language. For example, if the user's level of expertise is low, the answer unit provides an answer that explains in simple language. Furthermore, the answer unit can adjust the use of optimal technical terminology by comprehensively considering the user's level of expertise. For example, the answer unit adjusts the use of optimal technical terminology by comprehensively considering the user's level of expertise. In this way, the answer unit can provide a more appropriate answer by adjusting the use of technical terminology in the answer according to the user's level of expertise. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, identification unit, generation unit, reception unit, and answering unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects product reviews using the camera 42 and microphone 38B of the smart device 14, and the collected product reviews are analyzed by the identification processing unit 290 of the data processing device 12. The identification unit identifies reliable reviewers by the identification processing unit 290 of the data processing device 12. The generation unit generates avatars of the reviewers by the identification processing unit 290 of the data processing device 12. The reception unit receives a user's question by the control unit 46A of the smart device 14. The answering unit generates an answer to the user's question by the identification processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the collection unit, identification unit, generation unit, reception unit, and answering unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects product reviews using the camera 42 and microphone 238 of the smart glasses 214, and the collected product reviews are analyzed by the identification processing unit 290 of the data processing device 12. The identification unit identifies reliable reviewers by the identification processing unit 290 of the data processing device 12. The generation unit generates reviewer avatars by the identification processing unit 290 of the data processing device 12. The reception unit receives a user's question by the control unit 46A of the smart glasses 214. The answering unit generates an answer to the user's question by the identification processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, identification unit, generation unit, reception unit, and answering unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects product reviews using the camera 42 and microphone 238 of the headset type terminal 314, and the collected product reviews are analyzed by the identification processing unit 290 of the data processing device 12. The identification unit identifies reliable reviewers by the identification processing unit 290 of the data processing device 12. The generation unit generates avatars of the reviewers by the identification processing unit 290 of the data processing device 12. The reception unit receives a user's question by the control unit 46A of the headset type terminal 314. The answering unit generates an answer to the user's question by the identification processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, identification unit, generation unit, reception unit, and answering unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects product reviews using the camera 42 and microphone 238 of the robot 414, and the collected product reviews are analyzed by the identification processing unit 290 of the data processing device 12. The identification unit identifies reliable reviewers by the identification processing unit 290 of the data processing device 12. The generation unit generates avatars of the reviewers by the identification processing unit 290 of the data processing device 12. The reception unit receives a user's question by the control unit 46A of the robot 414. The answering unit generates an answer to the user's question by the identification processing unit 290 of the data processing device 12.

[0119] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0120] The collection unit can also analyze the user's purchase history and preferentially collect related reviews. For example, the collection unit preferentially collects reviews related to products that the user has purchased in the past. The collection unit can also preferentially collect reviews related to products in a category that the user frequently purchases. Furthermore, the collection unit can collect reviews related to new products that the user may be interested in based on the user's purchase history. In this way, the collection unit can collect more relevant reviews by taking the user's purchase history into consideration.

[0121] The identification unit may also consider the reviewer's social media activity when evaluating the reviewer's credibility. For example, the identification unit may analyze the reviewer's number of followers and engagement rate on social media to evaluate credibility. The identification unit may also evaluate the quality and consistency of the content the reviewer shares on social media. Furthermore, the identification unit may evaluate the reviewer's expertise and credibility based on the reviewer's social media activity history. As a result, the identification unit can identify more reliable reviewers by considering the reviewer's social media activity.

[0122] The generation unit can also reflect the reviewer's personality and style when generating the reviewer's avatar. For example, the generation unit analyzes the reviewer's writing style and expression methods in past reviews and reflects them in the avatar. The generation unit can also generate an avatar that reflects the reviewer's preferences and interests. Furthermore, the generation unit can generate an avatar that reflects the tone and emotions of the reviewer's past reviews. In this way, the generation unit can generate a more realistic and reliable avatar by reflecting the reviewer's personality and style.

[0123] When a user inputs a question, the reception unit can customize the interface according to the category and content of the question. For example, the reception unit can provide detailed input options for technical questions. The reception unit can also provide concise input options for general questions. Furthermore, the reception unit can automatically suggest related question candidates based on the content of the user's question. In this way, the reception unit can provide a more appropriate question input environment by customizing the interface according to the content of the user's question.

[0124] The answering unit can also estimate the user's emotions and adjust the tone and style of the answer based on the estimated user's emotions. For example, if the user is feeling anxious, the answering unit can provide an answer in a gentle tone. If the user is excited, the answering unit can also provide an answer in an energetic tone. Furthermore, if the user is relaxed, the answering unit can also provide an answer in a casual tone. This allows the answering unit to provide a more appropriate answer by adjusting the tone and style of the answer according to the user's emotions.

[0125] The collection unit can also estimate the user's emotions and adjust the review collection method based on the estimated user's emotions. For example, when the user is feeling stressed, the collection unit can collect reviews in the form of simple questions. When the user is relaxed, the collection unit can also collect reviews in the form of detailed questions. Furthermore, when the user is excited, the collection unit can also collect reviews in an interactive format. In this way, the collection unit can collect more appropriate reviews by adjusting the review collection method according to the user's emotions.

[0126] The identification unit can also estimate the user's emotions and adjust the criteria for identifying a reliable reviewer based on the estimated user's emotions. For example, when the user is feeling anxious, the identification unit can preferentially identify a reliable reviewer. Furthermore, when the user is excited, the identification unit can preferentially identify the most recent reviewer. Furthermore, when the user is relaxed, the identification unit can preferentially identify a reviewer who provides a detailed review. In this way, the identification unit can identify a more appropriate reviewer by adjusting the criteria for identifying a reliable reviewer according to the user's emotions.

[0127] The generation unit can also estimate the user's emotions and adjust the method for generating the avatar based on the estimated user's emotions. For example, if the user is relaxed, the generation unit can generate an avatar that moves at a leisurely pace. If the user is in a hurry, the generation unit can also generate an avatar that emphasizes the shortest route. Furthermore, if the user is excited, the generation unit can generate an avatar that adds visually stimulating effects. In this way, the generation unit can generate a more appropriate avatar by adjusting the method for generating the avatar according to the user's emotions.

[0128] The reception unit can also estimate the user's emotions and adjust the question reception interface based on the estimated user's emotions. For example, if the user is feeling stressed, the reception unit can provide a simple interface and minimize input steps. Alternatively, if the user is relaxed, the reception unit can provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input to enable the user to quickly input a question. In this way, the reception unit can provide a more appropriate interface by adjusting the question reception interface according to the user's emotions.

[0129] The answering unit can also estimate the user's emotions and adjust the way the answer is expressed based on the estimated user's emotions. For example, if the user is nervous, the answering unit can provide a simple, highly visible answer. If the user is relaxed, the answering unit can also provide an answer that includes detailed information. Furthermore, if the user is in a hurry, the answering unit can also provide an answer that focuses on the main points. In this way, the answering unit can provide a more appropriate answer by adjusting the way the answer is expressed based on the user's emotions.

[0130] The processing flow of the second embodiment will be briefly explained below.

[0131] Step 1: The collection unit collects product reviews. The collection unit can automatically collect product reviews from, for example, an online platform. The collection unit can also collect reviews manually entered by users. Step 2: The identification unit analyzes the reviews collected by the collection unit and identifies reliable reviewers. The identification unit evaluates the reliability of the reviewers based on, for example, the ratings of their past reviews and feedback from other users. Step 3: The generator generates an avatar of the reviewer identified by the identifier, for example, based on the reviewer's past reviews and ratings. Step 4: The reception unit provides an interface through which the user can input a question to the avatar generated by the generation unit. The reception unit provides an interface through which the user can input a question by text input or voice input, for example. Step 5: The answering unit generates an answer to the question input by the receiving unit. The answering unit generates an answer to the user's question using, for example, an LLM.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0136] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0137] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0150] 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.

[0151] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0152] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0153] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0160] 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.

[0161] 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.

[0162] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0163] 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.

[0164] 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.

[0165] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0166] 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.

[0167] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0168] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0180] 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.

[0181] 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.

[0182] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0183] 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.

[0184] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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).

[0189] 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.

[0190] 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."

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] [Explanation of symbols]

[0204] 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 collection department that collects product reviews; an identification unit that analyzes the reviews collected by the collection unit and identifies reliable reviewers; a generation unit that generates an alter ego of the reviewer identified by the identification unit; a reception unit for allowing a user to input a question to the avatar generated by the generation unit; an answering unit that generates an answer to the question input by the receiving unit; Equipped with A system characterized by:

2. The collecting unit Analyze the reviewer's past reviews and ratings 2. The system of claim 1.

3. The identification unit Determine the trustworthiness of a reviewer based on their past review ratings and feedback from other users 2. The system of claim 1.

4. The generation unit Create an avatar based on a reviewer's past reviews and ratings 2. The system of claim 1.

5. The reception unit Provides an interface for users to enter questions 2. The system of claim 1.

6. The answering section When a user asks a question, they can assess the quality of the answer generated by the LLM and provide feedback.

2. The system of claim 1.

7. The collecting unit Estimate user sentiment and adjust review collection timing based on the estimated user sentiment 2. The system of claim 1.

8. The collecting unit When collecting reviews, we select reviews based on the frequency and consistency of the reviewer's past posts.

2. The system of claim 1.

Images