System

Abstract

An object of a system according to an embodiment is to accurately and quickly analyze review information of a product, extract important information, and generate and update a summary.SOLUTION: A system includes a collection part, an analysis part, a summarization part, and an update part. The collection unit collects data of product reviews. The analysis unit analyzes the review information collected by the collection unit using a natural language processing technique. The summarizer extracts important information based on the analysis result obtained by the analyzer, and generates a summary. The updating unit updates the summary generated by the summarizing unit in real time.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have difficulty accurately and quickly grasping product review information, and efficient information extraction and summarization are required.

[0005] The system according to the embodiment aims to accurately and quickly analyze product review information, extract important information, and generate and update summaries. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a summarization unit, and an update unit. The collection unit collects product review data. The analysis unit analyzes the review information collected by the collection unit using natural language processing technology. The summarization unit extracts important information based on the analysis results obtained by the analysis unit and generates a summary. The update unit updates the summary generated by the summarization unit in real time. [Effects of the Invention]

[0007] The system according to the embodiment can accurately and quickly analyze product review information, extract important information, and generate and update summaries. [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 product review assistant according to an embodiment of the present invention is a system that efficiently collects, analyzes, summarizes, and updates product review data. The product review assistant uses a generation AI to collect product review data and natural language processing technology to analyze customer sentiment and ratings from the collected review information. Furthermore, it extracts important information and generates a summary based on the analysis results. For example, the product review assistant collects review information from various platforms on the Internet. For example, it can obtain review information from e-commerce sites, social networking sites, etc. Next, it analyzes the collected review information using natural language processing technology. For example, it analyzes the text data of the reviews to determine customer sentiment and ratings. Furthermore, it extracts important information and generates a summary based on the analysis results. For example, it extracts points that customers particularly value and areas that need improvement and provides them as a summary. This allows companies to efficiently understand review information and use it in their marketing strategies. The product review assistant can also update information in real time. For example, it can automatically update information using generation AIs every time a new review is posted, providing the latest review information. This allows companies to always have the latest review information. This allows the product review assistant to accurately, quickly, and efficiently understand product review information. For example, it can save time and improve data accuracy, and real-time updates can be used to improve marketing strategies.

[0029] A product review assistant according to an embodiment includes a collection unit, an analysis unit, a summarization unit, and an update unit. The collection unit collects product review data. For example, the collection unit uses a generation AI to collect review information from various platforms on the Internet. For example, the collection unit can acquire review information from e-commerce sites, social networking sites, and the like. The collection unit can also automatically collect review information using the generation AI. For example, the collection unit inputs a prompt to the generation AI, such as "Please collect the latest review information," and the generation AI collects review information from the Internet. The analysis unit analyzes the review information collected by the collection unit using natural language processing technology. For example, the analysis unit analyzes text data of reviews to determine customer sentiment and ratings. For example, the analysis unit can distinguish between positive and negative ratings and quantify customer sentiment. The analysis unit can also use the generation AI to grasp overall trends in the review information. For example, the analysis unit inputs a prompt to the generation AI, such as "Please analyze the sentiment of this review," and the generation AI analyzes the sentiment of the review. The summarization unit extracts important information based on the analysis results obtained by the analysis unit and generates a summary. For example, the summarization unit extracts points that customers particularly value and points that need improvement, and provides them as a summary. For example, the summarization unit can summarize review information using a generation AI. For example, the summarization unit inputs a prompt to the generation AI, such as "Please summarize the main points of this review," and the generation AI extracts the main points of the review and creates a summary. The update unit updates the summary generated by the summarization unit in real time. For example, the update unit automatically updates the information every time a new review is posted. For example, the update unit can collect the latest review information and update the summary using the generation AI. For example, the update unit inputs a prompt to the generation AI, such as "Please collect new review information and update the summary," and the generation AI collects the latest review information and updates the summary. This allows the product review assistant according to the embodiment to efficiently collect, analyze, summarize, and update product review information.For example, companies can quickly and accurately grasp review information and use it in their marketing strategies.

[0030] The collection unit can collect review information from multiple platforms on the Internet. For example, the collection unit collects review information from multiple platforms on the Internet. For example, the collection unit can acquire review information from e-commerce sites, social media, etc. The collection unit can also automatically collect review information from various platforms on the Internet using a generation AI. For example, the collection unit inputs a prompt to the generation AI saying, "Please collect the latest review information," and the generation AI collects review information on the Internet. This makes it possible to collect review information from a wide range of data sources. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0031] The analysis unit can analyze the text data of the reviews and determine the customer's sentiment and evaluation. The analysis unit can, for example, analyze the text data of the reviews and determine the customer's sentiment and evaluation. For example, the analysis unit can identify positive and negative evaluations and quantify the customer's sentiment. The analysis unit can also use the generation AI to grasp the overall trend of the review information. For example, the analysis unit inputs a prompt to the generation AI, such as "Please analyze the sentiment of this review," and the generation AI analyzes the sentiment of the review. This makes it possible to accurately determine the customer's sentiment and evaluation. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI.

[0032] The summarization unit can extract points that customers particularly value and points that need improvement, and provide them as summaries. For example, the summarization unit can extract points that customers particularly value and points that need improvement, and provide them as summaries. For example, the summarization unit can summarize review information using a generation AI. For example, the summarization unit inputs a prompt such as "Please summarize the main points of this review" to the generation AI, and the generation AI extracts the main points of the review and creates a summary. This allows important information to be summarized efficiently. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using AI, or may be performed without using AI.

[0033] The update unit can automatically update the information every time a new review is posted. For example, the update unit can automatically update the information every time a new review is posted. For example, the update unit can use a generation AI to collect the latest review information and update the summary. For example, the update unit inputs a prompt to the generation AI saying, "Please collect new review information and update the summary," and the generation AI collects the latest review information and updates the summary. This makes it possible to provide the latest review information in real time. Some or all of the above-described processing in the update unit may be performed, for example, using AI or without using AI.

[0034] The collection unit can analyze the user's past review collection history and select a collection method. The collection unit, for example, analyzes the user's past review collection history and selects the optimal collection method. For example, the collection unit prioritizes collecting review information from platforms that the user has frequently used in the past. The collection unit can also prioritize collecting reviews that the user has given high ratings to in the past. The collection unit can also concentrate collection during a specific time period based on the user's past collection history. This makes it possible to select the optimal collection method based on the user's past history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0035] The collection unit can filter the review information based on the user's areas of interest when collecting the review information. For example, the collection unit filters the review information based on the user's areas of interest when collecting the review information. For example, the collection unit collects review information limited to product categories in which the user is currently interested. The collection unit can also preferentially collect review information related to keywords recently searched by the user. The collection unit can also preferentially collect review information of influencers followed by the user. This makes it possible to collect highly relevant review information based on the user's areas of interest. Some or all of the above-described processing in the collection unit may be performed using AI, for example, or may be performed without using AI.

[0036] The collection unit can select the optimal collection means depending on the user's input method when collecting review information. For example, when collecting review information, the collection unit selects the optimal collection means depending on the user's input method. For example, when the user uses voice input, the collection unit prioritizes collecting voice reviews. Furthermore, when the user uses text input, the collection unit can also prioritize collecting text reviews. Furthermore, when the user uses image input, the collection unit can also prioritize collecting reviews with images. This makes it possible to select the optimal collection means depending on the user's input method. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI.

[0037] The collection unit can prioritize collecting highly relevant reviews based on the user's geographical location information when collecting review information. For example, the collection unit prioritizes collecting highly relevant reviews by taking the user's geographical location information into consideration when collecting review information. For example, the collection unit prioritizes collecting review information about stores and services close to the user's current location. The collection unit can also prioritize collecting review information about places the user has visited in the past. The collection unit can also collect region-specific review information based on the user's geographical location information. This makes it possible to collect highly relevant review information based on the user's geographical location information. Some or all of the above-described processing in the collection unit may be performed using AI, for example, or may be performed without using AI.

[0038] The collection unit can analyze the user's social media activities and collect related reviews when collecting review information. For example, the collection unit analyzes the user's social media activities and collects related reviews when collecting review information. For example, the collection unit prioritizes collecting review information for brands and products that the user follows on social media. The collection unit can also analyze the content of the user's social media posts to collect related review information. The collection unit can also collect related review information by referring to the activities of the user's friends on social media. In this way, it is possible to collect related review information based on the user's social media activities. Some or all of the above-described processing in the collection unit may be performed, for example, using AI or without using AI.

[0039] The collection unit can adjust the collection method by reflecting the user's past feedback when collecting review information. For example, the collection unit adjusts the collection method by reflecting the user's past feedback when collecting review information. For example, the collection unit preferentially uses a collection method that the user has previously given a high rating to. The collection unit can also improve and customize a collection method for which the user has previously provided feedback. The collection unit can also optimize the collection method based on the user's past feedback. This makes it possible to optimize the collection method based on the user's past feedback. Some or all of the above-described processing in the collection unit may be performed, for example, using AI or without using AI.

[0040] The analysis unit can adjust the level of detail of the analysis based on the importance of the review during analysis. For example, the analysis unit adjusts the level of detail of the analysis based on the importance of the review during analysis. For example, the analysis unit analyzes reviews with high importance in detail and analyzes reviews with low importance in a simplified manner. The analysis unit can also allocate more resources to analyze reviews with high importance. The analysis unit can also only perform simple keyword extraction for reviews with low importance. This allows for optimal analysis depending on the importance of the review. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI.

[0041] The analysis unit can apply different analysis algorithms depending on the review category during analysis. For example, the analysis unit applies different analysis algorithms depending on the review category during analysis. For example, the analysis unit selects and applies an optimal analysis algorithm for each product category. The analysis unit can also apply an analysis algorithm using specific evaluation criteria to a service category. The analysis unit can also use different natural language processing techniques depending on the characteristics of each category. This makes it possible to apply an optimal analysis algorithm depending on the review category. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI.

[0042] The analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. For example, the analysis unit can adjust the analysis algorithm based on the user's past analysis results. The analysis unit can also extract specific patterns from the user's past analysis results and reflect them in the analysis. The analysis unit can also incorporate the user's past analysis results as feedback to improve the accuracy of the analysis. This makes it possible to improve the accuracy of the analysis based on the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI.

[0043] The analysis unit can determine the priority of analysis based on the time of review submission during analysis. The analysis unit, for example, determines the priority of analysis based on the time of review submission during analysis. For example, the analysis unit prioritizes analysis of the most recent reviews and postpones older reviews. The analysis unit can also prioritize analysis of reviews submitted in a concentrated period. The analysis unit can also prioritize analysis of reviews related to seasons or events. This makes it possible to determine optimal analysis priorities based on the time of review submission. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or may be performed without using AI.

[0044] The analysis unit can adjust the order of analysis based on the relevance of the reviews during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of the reviews during analysis. For example, the analysis unit prioritizes analyzing reviews that are highly relevant to a product. The analysis unit can also prioritize analyzing reviews that are highly relevant to a service. The analysis unit can also prioritize analyzing reviews related to a specific keyword. This makes it possible to determine the optimal order of analysis based on the relevance of the reviews. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or may be performed without using AI.

[0045] The analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise during analysis. For example, the analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise during analysis. For example, if the user has technical knowledge, the analysis unit can provide analysis results that use a lot of technical terms. Furthermore, if the user only has general knowledge, the analysis unit can provide analysis results that avoid technical terms. Furthermore, the analysis unit can select appropriate terms according to the user's level of expertise and provide analysis results. This makes it possible to provide appropriate analysis results according to the user's level of expertise. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0046] The summarization unit can adjust the level of detail of the summary based on the importance of the review when generating the summary. For example, the summarization unit adjusts the level of detail of the summary based on the importance of the review when generating the summary. For example, the summarization unit provides a detailed summary for a review with a high importance. The summarization unit can also provide a concise summary for a review with a low importance. The summarization unit can also provide a summary including detailed analysis results for a review with a high importance. This makes it possible to provide a summary with an optimal level of detail depending on the importance of the review. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using AI or without using AI.

[0047] The summarization unit can apply different summarization algorithms depending on the review category when generating summaries. For example, the summarization unit selects and applies an optimal summarization algorithm for each product category. The summarization unit can also apply a summarization algorithm using specific evaluation criteria to a service category. The summarization unit can also use different natural language processing techniques depending on the characteristics of each category. This makes it possible to apply an optimal summarization algorithm depending on the review category. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI.

[0048] The summarization unit can improve the accuracy of the summary by referring to the user's past summarization results when generating a summary. For example, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results when generating a summary. For example, the summarization unit can adjust the summarization algorithm based on the user's past summarization results. The summarization unit can also extract specific patterns from the user's past summarization results and reflect them in the summary. The summarization unit can also incorporate the user's past summarization results as feedback to improve the accuracy of the summary. This makes it possible to improve the accuracy of the summary based on the user's past summarization results. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using AI or without using AI.

[0049] The summarization unit can determine the priority of summaries based on the time of review submission when generating summaries. For example, the summarization unit determines the priority of summaries based on the time of review submission when generating summaries. For example, the summarization unit prioritizes summarizing the most recent reviews and postpones older reviews. The summarization unit can also prioritize summarizing reviews that were submitted in a concentrated period of time. The summarization unit can also prioritize summarizing reviews related to seasons or events. This makes it possible to determine the optimal priority of summaries based on the time of review submission. Some or all of the above-described processing in the summarization unit may be performed using AI, for example, or may be performed without using AI.

[0050] The summarization unit can adjust the order of summaries based on the relevance of reviews when generating summaries. For example, the summarization unit adjusts the order of summaries based on the relevance of reviews when generating summaries. For example, the summarization unit prioritizes summarizing reviews that are highly relevant to a product. The summarization unit can also prioritize summarizing reviews that are highly relevant to a service. The summarization unit can also prioritize summarizing reviews related to a specific keyword. This makes it possible to determine an optimal order of summaries based on the relevance of reviews. Some or all of the above-described processing in the summarization unit may be performed using AI, for example, or may be performed without using AI.

[0051] The summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise when generating a summary. For example, the summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise when generating a summary. For example, if the user has technical knowledge, the summarization unit can provide a summary that uses a lot of technical terms. Alternatively, if the user only has general knowledge, the summarization unit can provide a summary that avoids technical terms. Alternatively, the summarization unit can select appropriate terms according to the user's level of expertise and provide a summary. This makes it possible to provide an appropriate summary according to the user's level of expertise. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI.

[0052] The update unit can select the optimal update timing by referring to past update history when updating. For example, the update unit selects the optimal update timing by referring to past update history when updating. For example, the update unit selects the most effective update timing from the past update history. The update unit can also analyze the past update history and perform updates at times when users responded well. The update unit can also concentrate updates in specific time periods based on the past update history. This makes it possible to select the optimal update timing based on the past update history. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without using AI.

[0053] The update unit can customize the update content by reflecting user feedback during an update. The update unit, for example, customizes the update content by reflecting user feedback during an update. For example, the update unit adjusts the update content based on user feedback. The update unit can also prioritize updating specific information by reflecting user feedback. The update unit can also customize the update content based on user feedback. This makes it possible to optimize the update content based on user feedback. Some or all of the above-described processing in the update unit may be performed using AI, for example, or may be performed without using AI.

[0054] The update unit can determine the update priority based on the importance of the new review at the time of update. The update unit, for example, determines the update priority based on the importance of the new review at the time of update. For example, the update unit prioritizes updating reviews with high importance. The update unit can also postpone updating reviews with low importance. The update unit can also allocate more resources to reviews with high importance for updating. This makes it possible to determine the optimal update priority according to the importance of the new review. Some or all of the above-mentioned processing in the update unit may be performed using AI, for example, or may be performed without using AI.

[0055] The update unit can select update content taking into consideration the geographic distribution of reviews when updating. For example, the update unit selects update content taking into consideration the geographic distribution of reviews when updating. For example, the update unit prioritizes updating review information for stores and services close to the user's current location. The update unit can also prioritize updating review information for places the user has previously visited. The update unit can also update region-specific review information based on the user's geographic location information. This makes it possible to provide optimal update content based on the geographic distribution of reviews. Some or all of the above-described processing in the update unit may be performed using AI, for example, or may be performed without using AI.

[0056] The update unit can improve the accuracy of the updated content by referring to related literature of the review during an update. The update unit can improve the accuracy of the updated content by referring to related literature of the review during an update, for example. For example, the update unit can improve the accuracy of the review information by referring to related literature. The update unit can also increase the reliability of the review information based on the related literature. The update unit can also improve the level of detail of the review information by referring to related literature. This can improve the accuracy of the updated content based on the related literature of the review. Some or all of the above-described processing in the update unit can be performed using AI, for example, or can be performed without using AI.

[0057] The update unit can select update content taking into consideration the market value of the review when updating. The update unit, for example, selects update content taking into consideration the market value of the review when updating. For example, the update unit prioritizes updating reviews with high market value. The update unit can also postpone updating reviews with low market value. The update unit can also allocate more resources to reviews with high market value when updating. This makes it possible to provide optimal update content based on the market value of the review. Some or all of the above-mentioned processing in the update unit may be performed, for example, using AI, or may be performed without using AI.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The collection unit can also analyze the user's purchase history and preferentially collect related review information. For example, the collection unit preferentially collects review information related to products the user has purchased in the past. The collection unit can also preferentially collect product reviews in categories that the user frequently purchases. Furthermore, the collection unit can also preferentially collect review information for products that the user has given high ratings to in the past. This makes it possible to collect highly relevant review information based on the user's purchase history.

[0060] When analyzing the review text data, the analysis unit can also evaluate the reliability of the review. For example, the analysis unit can analyze the review poster's past review history and prioritize analysis of highly reliable reviews. The analysis unit can also evaluate whether the review content is specific and prioritize analysis of specific reviews. Furthermore, the analysis unit can also take into account the posting date and time of the review and prioritize analysis of the most recent reviews. This allows for efficient analysis of highly reliable review information.

[0061] The summarization unit may customize the content of the summary based on the user's areas of interest when generating the summary. For example, the summarization unit may prioritize summarizing review information related to product categories in which the user is interested. The summarization unit may also summarize review information related to keywords recently searched by the user. Furthermore, the summarization unit may summarize review information from influencers the user follows. This allows for providing a highly relevant summary based on the user's areas of interest.

[0062] The update unit can also customize the update content by reflecting user feedback when updating review information. For example, the update unit can prioritize updating specific information based on user feedback. The update unit can also adjust the update frequency by reflecting user feedback. Furthermore, the update unit can customize the display method of the update content based on user feedback. This makes it possible to provide optimal update content based on user feedback.

[0063] When collecting review information, the collection unit can also prioritize collecting highly relevant reviews based on the user's geographical location information. For example, the collection unit can prioritize collecting review information about stores and services close to the user's current location. The collection unit can also prioritize collecting review information about places the user has visited in the past. Furthermore, the collection unit can also collect region-specific review information based on the user's geographical location information. This makes it possible to collect highly relevant review information based on the user's geographical location information.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The collection unit collects product review data. The collection unit uses the generation AI to collect review information from various platforms on the Internet. For example, review information can be obtained from e-commerce sites, social media, etc. The collection unit also inputs a prompt to the generation AI saying, "Please collect the latest review information," and the generation AI automatically collects review information on the Internet. Step 2: The analysis unit uses natural language processing technology to analyze the review information collected by the collection unit. The analysis unit analyzes the review text data and determines customer sentiment and ratings. For example, it can distinguish between positive and negative ratings and quantify customer sentiment. It also inputs a prompt to the generation AI, such as "Please analyze the sentiment of this review," and the generation AI analyzes the sentiment of the review. Step 3: The summarization unit extracts important information based on the analysis results obtained by the analysis unit and generates a summary. The summarization unit extracts points that customers particularly value and areas that need improvement, and provides them as a summary. For example, the generation AI can be given a prompt such as "Please summarize the main points of this review," and the generation AI will extract the main points of the review and create a summary. Step 4: The updater updates the summary generated by the summarizer in real time. The updater automatically updates the information whenever a new review is posted. For example, the generation AI receives a prompt saying, "Collect new review information and update the summary." The generation AI then collects the latest review information and updates the summary.

[0066] (Example 2) A product review assistant according to an embodiment of the present invention is a system that efficiently collects, analyzes, summarizes, and updates product review data. The product review assistant uses a generation AI to collect product review data and natural language processing technology to analyze customer sentiment and ratings from the collected review information. Furthermore, it extracts important information and generates a summary based on the analysis results. For example, the product review assistant collects review information from various platforms on the Internet. For example, it can obtain review information from e-commerce sites, social networking sites, etc. Next, it analyzes the collected review information using natural language processing technology. For example, it analyzes the text data of the reviews to determine customer sentiment and ratings. Furthermore, it extracts important information and generates a summary based on the analysis results. For example, it extracts points that customers particularly value and areas that need improvement and provides them as a summary. This allows companies to efficiently understand review information and use it in their marketing strategies. The product review assistant can also update information in real time. For example, it can automatically update information using generation AIs every time a new review is posted, providing the latest review information. This allows companies to always have the latest review information. This allows the product review assistant to accurately, quickly, and efficiently understand product review information. For example, it can save time and improve data accuracy, and real-time updates can be used to improve marketing strategies.

[0067] A product review assistant according to an embodiment includes a collection unit, an analysis unit, a summarization unit, and an update unit. The collection unit collects product review data. For example, the collection unit uses a generation AI to collect review information from various platforms on the Internet. For example, the collection unit can acquire review information from e-commerce sites, social networking sites, and the like. The collection unit can also automatically collect review information using the generation AI. For example, the collection unit inputs a prompt to the generation AI, such as "Please collect the latest review information," and the generation AI collects review information from the Internet. The analysis unit analyzes the review information collected by the collection unit using natural language processing technology. For example, the analysis unit analyzes text data of reviews to determine customer sentiment and ratings. For example, the analysis unit can distinguish between positive and negative ratings and quantify customer sentiment. The analysis unit can also use the generation AI to grasp overall trends in the review information. For example, the analysis unit inputs a prompt to the generation AI, such as "Please analyze the sentiment of this review," and the generation AI analyzes the sentiment of the review. The summarization unit extracts important information based on the analysis results obtained by the analysis unit and generates a summary. For example, the summarization unit extracts points that customers particularly value and points that need improvement, and provides them as a summary. For example, the summarization unit can summarize review information using a generation AI. For example, the summarization unit inputs a prompt to the generation AI, such as "Please summarize the main points of this review," and the generation AI extracts the main points of the review and creates a summary. The update unit updates the summary generated by the summarization unit in real time. For example, the update unit automatically updates the information every time a new review is posted. For example, the update unit can collect the latest review information and update the summary using the generation AI. For example, the update unit inputs a prompt to the generation AI, such as "Please collect new review information and update the summary," and the generation AI collects the latest review information and updates the summary. This allows the product review assistant according to the embodiment to efficiently collect, analyze, summarize, and update product review information.For example, companies can quickly and accurately grasp review information and use it in their marketing strategies.

[0068] The collection unit can collect review information from multiple platforms on the Internet. For example, the collection unit collects review information from multiple platforms on the Internet. For example, the collection unit can acquire review information from e-commerce sites, social media, etc. The collection unit can also automatically collect review information from various platforms on the Internet using a generation AI. For example, the collection unit inputs a prompt to the generation AI saying, "Please collect the latest review information," and the generation AI collects review information on the Internet. This makes it possible to collect review information from a wide range of data sources. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0069] The analysis unit can analyze the text data of the reviews and determine the customer's sentiment and evaluation. The analysis unit can, for example, analyze the text data of the reviews and determine the customer's sentiment and evaluation. For example, the analysis unit can identify positive and negative evaluations and quantify the customer's sentiment. The analysis unit can also use the generation AI to grasp the overall trend of the review information. For example, the analysis unit inputs a prompt to the generation AI, such as "Please analyze the sentiment of this review," and the generation AI analyzes the sentiment of the review. This makes it possible to accurately determine the customer's sentiment and evaluation. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI.

[0070] The summarization unit can extract points that customers particularly value and points that need improvement, and provide them as summaries. For example, the summarization unit can extract points that customers particularly value and points that need improvement, and provide them as summaries. For example, the summarization unit can summarize review information using a generation AI. For example, the summarization unit inputs a prompt such as "Please summarize the main points of this review" to the generation AI, and the generation AI extracts the main points of the review and creates a summary. This allows important information to be summarized efficiently. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using AI, or may be performed without using AI.

[0071] The update unit can automatically update the information every time a new review is posted. For example, the update unit can automatically update the information every time a new review is posted. For example, the update unit can use a generation AI to collect the latest review information and update the summary. For example, the update unit inputs a prompt to the generation AI saying, "Please collect new review information and update the summary," and the generation AI collects the latest review information and updates the summary. This makes it possible to provide the latest review information in real time. Some or all of the above-described processing in the update unit may be performed, for example, using AI or without using AI.

[0072] The collection unit can estimate the user's emotions and adjust the timing of collecting review information based on the estimated user emotions. The collection unit, for example, estimates the user's emotions and adjusts the timing of collecting review information based on the estimated user emotions. For example, the collection unit increases the frequency of collecting review information when the user is expressing positive emotions. Furthermore, when the user is expressing negative emotions, the collection unit can delay the timing of collection and wait for the emotion to calm down. Furthermore, when the user is expressing neutral emotions, the collection unit can collect review information at the normal collection timing. This allows review information to be collected at the optimal timing depending on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without AI.

[0073] The collection unit can analyze the user's past review collection history and select a collection method. The collection unit, for example, analyzes the user's past review collection history and selects the optimal collection method. For example, the collection unit prioritizes collecting review information from platforms that the user has frequently used in the past. The collection unit can also prioritize collecting reviews that the user has given high ratings to in the past. The collection unit can also concentrate collection during a specific time period based on the user's past collection history. This makes it possible to select the optimal collection method based on the user's past history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0074] The collection unit can filter the review information based on the user's areas of interest when collecting the review information. For example, the collection unit filters the review information based on the user's areas of interest when collecting the review information. For example, the collection unit collects review information limited to product categories in which the user is currently interested. The collection unit can also preferentially collect review information related to keywords recently searched by the user. The collection unit can also preferentially collect review information of influencers followed by the user. This makes it possible to collect highly relevant review information based on the user's areas of interest. Some or all of the above-described processing in the collection unit may be performed using AI, for example, or may be performed without using AI.

[0075] The collection unit can select the optimal collection means depending on the user's input method when collecting review information. For example, when collecting review information, the collection unit selects the optimal collection means depending on the user's input method. For example, when the user uses voice input, the collection unit prioritizes collecting voice reviews. Furthermore, when the user uses text input, the collection unit can also prioritize collecting text reviews. Furthermore, when the user uses image input, the collection unit can also prioritize collecting reviews with images. This makes it possible to select the optimal collection means depending on the user's input method. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI.

[0076] The collection unit can estimate the user's emotions and determine the priority of the review information to be collected based on the estimated user emotions. The collection unit, for example, estimates the user's emotions and determines the priority of the review information to be collected based on the estimated user emotions. For example, when the user expresses positive emotions, the collection unit prioritizes collecting positive review information. Furthermore, when the user expresses negative emotions, the collection unit can also prioritize collecting negative review information. Furthermore, when the user expresses neutral emotions, the collection unit can also collect review information taking into account the overall balance. This makes it possible to determine the priority of the review information to be collected according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI.

[0077] The collection unit can prioritize collecting highly relevant reviews based on the user's geographical location information when collecting review information. For example, the collection unit prioritizes collecting highly relevant reviews by taking the user's geographical location information into consideration when collecting review information. For example, the collection unit prioritizes collecting review information about stores and services close to the user's current location. The collection unit can also prioritize collecting review information about places the user has visited in the past. The collection unit can also collect region-specific review information based on the user's geographical location information. This makes it possible to collect highly relevant review information based on the user's geographical location information. Some or all of the above-described processing in the collection unit may be performed using AI, for example, or may be performed without using AI.

[0078] The collection unit can analyze the user's social media activities and collect related reviews when collecting review information. For example, the collection unit analyzes the user's social media activities and collects related reviews when collecting review information. For example, the collection unit prioritizes collecting review information for brands and products that the user follows on social media. The collection unit can also analyze the content of the user's social media posts to collect related review information. The collection unit can also collect related review information by referring to the activities of the user's friends on social media. In this way, it is possible to collect related review information based on the user's social media activities. Some or all of the above-described processing in the collection unit may be performed, for example, using AI or without using AI.

[0079] The collection unit can adjust the collection method by reflecting the user's past feedback when collecting review information. For example, the collection unit adjusts the collection method by reflecting the user's past feedback when collecting review information. For example, the collection unit preferentially uses a collection method that the user has previously given a high rating to. The collection unit can also improve and customize a collection method for which the user has previously provided feedback. The collection unit can also optimize the collection method based on the user's past feedback. This makes it possible to optimize the collection method based on the user's past feedback. Some or all of the above-described processing in the collection unit may be performed, for example, using AI or without using AI.

[0080] The analysis unit can estimate a user's emotions and adjust the review analysis method based on the estimated user emotions. For example, the analysis unit estimates a user's emotions and adjusts the review analysis method based on the estimated user emotions. For example, if a user expresses positive emotions, the analysis unit emphasizes positive reviews in the analysis. Furthermore, if a user expresses negative emotions, the analysis unit can analyze negative reviews in detail. Furthermore, if a user expresses neutral emotions, the analysis unit can analyze reviews taking into account the overall balance. This allows the optimal analysis method to be selected depending on the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI.

[0081] The analysis unit can adjust the level of detail of the analysis based on the importance of the review during analysis. For example, the analysis unit adjusts the level of detail of the analysis based on the importance of the review during analysis. For example, the analysis unit analyzes reviews with high importance in detail and analyzes reviews with low importance in a simplified manner. The analysis unit can also allocate more resources to analyze reviews with high importance. The analysis unit can also only perform simple keyword extraction for reviews with low importance. This allows for optimal analysis depending on the importance of the review. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI.

[0082] The analysis unit can apply different analysis algorithms depending on the review category during analysis. For example, the analysis unit applies different analysis algorithms depending on the review category during analysis. For example, the analysis unit selects and applies an optimal analysis algorithm for each product category. The analysis unit can also apply an analysis algorithm using specific evaluation criteria to a service category. The analysis unit can also use different natural language processing techniques depending on the characteristics of each category. This makes it possible to apply an optimal analysis algorithm depending on the review category. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI.

[0083] The analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. For example, the analysis unit can adjust the analysis algorithm based on the user's past analysis results. The analysis unit can also extract specific patterns from the user's past analysis results and reflect them in the analysis. The analysis unit can also incorporate the user's past analysis results as feedback to improve the accuracy of the analysis. This makes it possible to improve the accuracy of the analysis based on the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI.

[0084] The analysis unit can estimate the user's emotions and determine the analysis priorities based on the estimated user emotions. For example, the analysis unit can estimate the user's emotions and determine the analysis priorities based on the estimated user emotions. For example, if the user expresses positive emotions, the analysis unit can prioritize the analysis of positive reviews. Also, if the user expresses negative emotions, the analysis unit can prioritize the analysis of negative reviews. Also, if the user expresses neutral emotions, the analysis unit can determine the analysis priorities taking into account the overall balance. This makes it possible to determine the analysis priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI.

[0085] The analysis unit can determine the priority of analysis based on the time of review submission during analysis. The analysis unit, for example, determines the priority of analysis based on the time of review submission during analysis. For example, the analysis unit prioritizes analysis of the most recent reviews and postpones older reviews. The analysis unit can also prioritize analysis of reviews submitted in a concentrated period. The analysis unit can also prioritize analysis of reviews related to seasons or events. This makes it possible to determine optimal analysis priorities based on the time of review submission. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or may be performed without using AI.

[0086] The analysis unit can adjust the order of analysis based on the relevance of the reviews during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of the reviews during analysis. For example, the analysis unit prioritizes analyzing reviews that are highly relevant to a product. The analysis unit can also prioritize analyzing reviews that are highly relevant to a service. The analysis unit can also prioritize analyzing reviews related to a specific keyword. This makes it possible to determine the optimal order of analysis based on the relevance of the reviews. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or may be performed without using AI.

[0087] The analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise during analysis. For example, the analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise during analysis. For example, if the user has technical knowledge, the analysis unit can provide analysis results that use a lot of technical terms. Furthermore, if the user only has general knowledge, the analysis unit can provide analysis results that avoid technical terms. Furthermore, the analysis unit can select appropriate terms according to the user's level of expertise and provide analysis results. This makes it possible to provide appropriate analysis results according to the user's level of expertise. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0088] The summarization unit can estimate the user's emotion and adjust the summary expression method based on the estimated user's emotion. For example, the summarization unit can estimate the user's emotion and adjust the summary expression method based on the estimated user's emotion. For example, if the user is expressing positive emotion, the summarization unit can provide a summary that uses a lot of positive expressions. Also, if the user is expressing negative emotion, the summarization unit can provide a summary that uses a lot of negative expressions. Also, if the user is expressing neutral emotion, the summarization unit can provide a summary that uses balanced expressions. This makes it possible to provide a summary using an optimal expression method depending on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the summarization unit can be performed, for example, using AI or without AI.

[0089] The summarization unit can adjust the level of detail of the summary based on the importance of the review when generating the summary. For example, the summarization unit adjusts the level of detail of the summary based on the importance of the review when generating the summary. For example, the summarization unit provides a detailed summary for a review with a high importance. The summarization unit can also provide a concise summary for a review with a low importance. The summarization unit can also provide a summary including detailed analysis results for a review with a high importance. This makes it possible to provide a summary with an optimal level of detail depending on the importance of the review. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using AI or without using AI.

[0090] The summarization unit can apply different summarization algorithms depending on the review category when generating summaries. For example, the summarization unit selects and applies an optimal summarization algorithm for each product category. The summarization unit can also apply a summarization algorithm using specific evaluation criteria to a service category. The summarization unit can also use different natural language processing techniques depending on the characteristics of each category. This makes it possible to apply an optimal summarization algorithm depending on the review category. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI.

[0091] The summarization unit can improve the accuracy of the summary by referring to the user's past summarization results when generating a summary. For example, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results when generating a summary. For example, the summarization unit can adjust the summarization algorithm based on the user's past summarization results. The summarization unit can also extract specific patterns from the user's past summarization results and reflect them in the summary. The summarization unit can also incorporate the user's past summarization results as feedback to improve the accuracy of the summary. This makes it possible to improve the accuracy of the summary based on the user's past summarization results. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using AI or without using AI.

[0092] The summarization unit can estimate the user's emotion and adjust the length of the summary based on the estimated user's emotion. For example, the summarization unit can estimate the user's emotion and adjust the length of the summary based on the estimated user's emotion. For example, the summarization unit can provide a detailed summary when the user is expressing positive emotion. The summarization unit can also provide a concise summary when the user is expressing negative emotion. The summarization unit can also provide a summary of a balanced length when the user is expressing neutral emotion. This allows the summary to be provided with an optimal length depending on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the summarization unit can be performed, for example, using AI or without AI.

[0093] The summarization unit can determine the priority of summaries based on the time of review submission when generating summaries. For example, the summarization unit determines the priority of summaries based on the time of review submission when generating summaries. For example, the summarization unit prioritizes summarizing the most recent reviews and postpones older reviews. The summarization unit can also prioritize summarizing reviews that were submitted in a concentrated period of time. The summarization unit can also prioritize summarizing reviews related to seasons or events. This makes it possible to determine the optimal priority of summaries based on the time of review submission. Some or all of the above-described processing in the summarization unit may be performed using AI, for example, or may be performed without using AI.

[0094] The summarization unit can adjust the order of summaries based on the relevance of reviews when generating summaries. For example, the summarization unit adjusts the order of summaries based on the relevance of reviews when generating summaries. For example, the summarization unit prioritizes summarizing reviews that are highly relevant to a product. The summarization unit can also prioritize summarizing reviews that are highly relevant to a service. The summarization unit can also prioritize summarizing reviews related to a specific keyword. This makes it possible to determine an optimal order of summaries based on the relevance of reviews. Some or all of the above-described processing in the summarization unit may be performed using AI, for example, or may be performed without using AI.

[0095] The summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise when generating a summary. For example, the summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise when generating a summary. For example, if the user has technical knowledge, the summarization unit can provide a summary that uses a lot of technical terms. Alternatively, if the user only has general knowledge, the summarization unit can provide a summary that avoids technical terms. Alternatively, the summarization unit can select appropriate terms according to the user's level of expertise and provide a summary. This makes it possible to provide an appropriate summary according to the user's level of expertise. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI.

[0096] The update unit can estimate the user's emotion and adjust the information update frequency based on the estimated user's emotion. The update unit, for example, estimates the user's emotion and adjusts the information update frequency based on the estimated user's emotion. For example, the update unit can increase the update frequency when the user is expressing a positive emotion. The update unit can also decrease the update frequency when the user is expressing a negative emotion. The update unit can also maintain the normal update frequency when the user is expressing a neutral emotion. This makes it possible to update information at an optimal frequency depending on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the update unit may be performed using, for example, an AI, or may be performed without using an AI.

[0097] The update unit can select the optimal update timing by referring to past update history when updating. For example, the update unit selects the optimal update timing by referring to past update history when updating. For example, the update unit selects the most effective update timing from the past update history. The update unit can also analyze the past update history and perform updates at times when users responded well. The update unit can also concentrate updates in specific time periods based on the past update history. This makes it possible to select the optimal update timing based on the past update history. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without using AI.

[0098] The update unit can customize the update content by reflecting user feedback during an update. The update unit, for example, customizes the update content by reflecting user feedback during an update. For example, the update unit adjusts the update content based on user feedback. The update unit can also prioritize updating specific information by reflecting user feedback. The update unit can also customize the update content based on user feedback. This makes it possible to optimize the update content based on user feedback. Some or all of the above-described processing in the update unit may be performed using AI, for example, or may be performed without using AI.

[0099] The update unit can determine the update priority based on the importance of the new review at the time of update. The update unit, for example, determines the update priority based on the importance of the new review at the time of update. For example, the update unit prioritizes updating reviews with high importance. The update unit can also postpone updating reviews with low importance. The update unit can also allocate more resources to reviews with high importance for updating. This makes it possible to determine the optimal update priority according to the importance of the new review. Some or all of the above-mentioned processing in the update unit may be performed using AI, for example, or may be performed without using AI.

[0100] The update unit can estimate the user's emotion and adjust the display method of the update content based on the estimated user's emotion. For example, the update unit can estimate the user's emotion and adjust the display method of the update content based on the estimated user's emotion. For example, when the user is expressing positive emotion, the update unit can provide a display method that makes heavy use of positive expressions. When the user is expressing negative emotion, the update unit can also provide a display method that makes heavy use of negative expressions. When the user is expressing neutral emotion, the update unit can also provide a balanced display method. This makes it possible to provide the update content in an optimal display method according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the update unit can be performed, for example, using AI or without AI.

[0101] The update unit can select update content taking into consideration the geographic distribution of reviews when updating. For example, the update unit selects update content taking into consideration the geographic distribution of reviews when updating. For example, the update unit prioritizes updating review information for stores and services close to the user's current location. The update unit can also prioritize updating review information for places the user has previously visited. The update unit can also update region-specific review information based on the user's geographic location information. This makes it possible to provide optimal update content based on the geographic distribution of reviews. Some or all of the above-described processing in the update unit may be performed using AI, for example, or may be performed without using AI.

[0102] The update unit can improve the accuracy of the updated content by referring to related literature of the review during an update. The update unit can improve the accuracy of the updated content by referring to related literature of the review during an update, for example. For example, the update unit can improve the accuracy of the review information by referring to related literature. The update unit can also increase the reliability of the review information based on the related literature. The update unit can also improve the level of detail of the review information by referring to related literature. This can improve the accuracy of the updated content based on the related literature of the review. Some or all of the above-described processing in the update unit can be performed using AI, for example, or can be performed without using AI.

[0103] The update unit can select update content taking into consideration the market value of the review when updating. The update unit, for example, selects update content taking into consideration the market value of the review when updating. For example, the update unit prioritizes updating reviews with high market value. The update unit can also postpone updating reviews with low market value. The update unit can also allocate more resources to reviews with high market value when updating. This makes it possible to provide optimal update content based on the market value of the review. Some or all of the above-mentioned processing in the update unit may be performed, for example, using AI, or may be performed without using AI. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, summarization unit, and update 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 can collect review information using the camera 42 and microphone 38B of the smart device 14 and analyze the collected data by the specific processing unit 290 of the data processing device 12. For example, the analysis unit can analyze the review information using natural language processing technology by the specific processing unit 290 of the data processing device 12 to determine customer sentiment and evaluation. For example, the summarization unit can extract important information and generate a summary by the control unit 46A of the smart device 14. For example, the update unit can update information in real time by the specific processing unit 290 of the data processing device 12 to provide the latest review information. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, summarization unit, and update 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 can collect review information using the camera 42 and microphone 238 of the smart glasses 214 and analyze the collected data by the specific processing unit 290 of the data processing device 12. For example, the analysis unit can analyze the review information using natural language processing technology by the specific processing unit 290 of the data processing device 12 to determine customer sentiment and evaluation. For example, the summarization unit can extract important information and generate a summary by the control unit 46A of the smart glasses 214. For example, the update unit can update information in real time by the specific processing unit 290 of the data processing device 12 to provide the latest review information. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, summarization unit, and update unit, described above, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit can collect review information using the camera 42 and microphone 238 of the headset terminal 314 and analyze the collected data by the specific processing unit 290 of the data processing device 12. For example, the analysis unit can analyze the review information using natural language processing technology by the specific processing unit 290 of the data processing device 12 to determine customer sentiment and evaluation. For example, the summarization unit can extract important information and generate a summary by the control unit 46A of the headset terminal 314. For example, the update unit can update information in real time by the specific processing unit 290 of the data processing device 12 to provide the latest review information. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, summarization unit, and update 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 can collect review information using the camera 42 and microphone 238 of the robot 414 and analyze the collected data by the specific processing unit 290 of the data processing device 12. For example, the analysis unit can analyze the review information using natural language processing technology by the specific processing unit 290 of the data processing device 12 to determine customer sentiment and evaluation. For example, the summarization unit can extract important information and generate a summary by the control unit 46A of the robot 414. For example, the update unit can update information in real time by the specific processing unit 290 of the data processing device 12 to provide the latest review information.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] The collection unit can also analyze the user's purchase history and preferentially collect related review information. For example, the collection unit preferentially collects review information related to products the user has purchased in the past. The collection unit can also preferentially collect product reviews in categories that the user frequently purchases. Furthermore, the collection unit can also preferentially collect review information for products that the user has given high ratings to in the past. This makes it possible to collect highly relevant review information based on the user's purchase history.

[0106] When analyzing the review text data, the analysis unit can also evaluate the reliability of the review. For example, the analysis unit can analyze the review poster's past review history and prioritize analysis of highly reliable reviews. The analysis unit can also evaluate whether the review content is specific and prioritize analysis of specific reviews. Furthermore, the analysis unit can also take into account the posting date and time of the review and prioritize analysis of the most recent reviews. This allows for efficient analysis of highly reliable review information.

[0107] The summarization unit may customize the content of the summary based on the user's areas of interest when generating the summary. For example, the summarization unit may prioritize summarizing review information related to product categories in which the user is interested. The summarization unit may also summarize review information related to keywords recently searched by the user. Furthermore, the summarization unit may summarize review information from influencers the user follows. This allows for providing a highly relevant summary based on the user's areas of interest.

[0108] The update unit can also customize the update content by reflecting user feedback when updating review information. For example, the update unit can prioritize updating specific information based on user feedback. The update unit can also adjust the update frequency by reflecting user feedback. Furthermore, the update unit can customize the display method of the update content based on user feedback. This makes it possible to provide optimal update content based on user feedback.

[0109] The collection unit can also estimate the user's emotions and determine the priority of the review information to be collected based on the estimated user's emotions. For example, when the user is expressing positive emotions, the collection unit can preferentially collect positive review information. Also, when the user is expressing negative emotions, the collection unit can preferentially collect negative review information. Furthermore, when the user is expressing neutral emotions, the collection unit can also collect review information taking into account the overall balance. In this way, the priority of the review information to be collected can be determined according to the user's emotions.

[0110] The analysis unit can also estimate the user's emotions and adjust the review analysis method based on the estimated user's emotions. For example, if the user expresses positive emotions, the analysis unit can emphasize positive reviews in the analysis. If the user expresses negative emotions, the analysis unit can also analyze negative reviews in detail. Furthermore, if the user expresses neutral emotions, the analysis unit can analyze reviews taking into account the overall balance. This makes it possible to select the optimal analysis method depending on the user's emotions.

[0111] The summarization unit can also estimate the user's emotions and adjust the way the summary is expressed based on the estimated user's emotions. For example, if the user is expressing positive emotions, the summarization unit can provide a summary that uses a lot of positive expressions. If the user is expressing negative emotions, the summarization unit can provide a summary that uses a lot of negative expressions. Furthermore, if the user is expressing neutral emotions, the summarization unit can provide a summary that uses balanced expressions. This makes it possible to provide a summary in the most appropriate way depending on the user's emotions.

[0112] The update unit can also estimate the user's emotions and adjust the information update frequency based on the estimated user's emotions. For example, the update unit can increase the update frequency when the user is expressing positive emotions. The update unit can also decrease the update frequency when the user is expressing negative emotions. Furthermore, the update unit can maintain the normal update frequency when the user is expressing neutral emotions. This makes it possible to update information at an optimal frequency according to the user's emotions.

[0113] The update unit can also estimate the user's emotion and adjust the display method of the update content based on the estimated user's emotion. For example, when the user is expressing a positive emotion, the update unit can provide a display method that makes use of positive expressions. When the user is expressing a negative emotion, the update unit can also provide a display method that makes use of negative expressions. Furthermore, when the user is expressing a neutral emotion, the update unit can also provide a balanced display method. This makes it possible to provide the update content in an optimal display method according to the user's emotion.

[0114] When collecting review information, the collection unit can also prioritize collecting highly relevant reviews based on the user's geographical location information. For example, the collection unit can prioritize collecting review information about stores and services close to the user's current location. The collection unit can also prioritize collecting review information about places the user has visited in the past. Furthermore, the collection unit can also collect region-specific review information based on the user's geographical location information. This makes it possible to collect highly relevant review information based on the user's geographical location information.

[0115] The processing flow of the second embodiment will be briefly explained below.

[0116] Step 1: The collection unit collects product review data. The collection unit uses the generation AI to collect review information from various platforms on the Internet. For example, review information can be obtained from e-commerce sites, social media, etc. The collection unit also inputs a prompt to the generation AI saying, "Please collect the latest review information," and the generation AI automatically collects review information on the Internet. Step 2: The analysis unit uses natural language processing technology to analyze the review information collected by the collection unit. The analysis unit analyzes the review text data and determines customer sentiment and ratings. For example, it can distinguish between positive and negative ratings and quantify customer sentiment. It also inputs a prompt to the generation AI, such as "Please analyze the sentiment of this review," and the generation AI analyzes the sentiment of the review. Step 3: The summarization unit extracts important information based on the analysis results obtained by the analysis unit and generates a summary. The summarization unit extracts points that customers particularly value and areas that need improvement, and provides them as a summary. For example, the generation AI can be given a prompt such as "Please summarize the main points of this review," and the generation AI will extract the main points of the review and create a summary. Step 4: The updater updates the summary generated by the summarizer in real time. The updater automatically updates the information whenever a new review is posted. For example, the generation AI receives a prompt saying, "Collect new review information and update the summary." The generation AI then collects the latest review information and updates the summary.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] 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.

[0175] 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."

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] [Explanation of symbols]

[0189] 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 unit that collects product review data; an analysis unit that analyzes the review information collected by the collection unit using natural language processing technology; a summarization unit that extracts important information based on the analysis results obtained by the analysis unit and generates a summary; an update unit that updates the summary generated by the summarization unit in real time; A system characterized by:

2. The collecting unit Collect reviews from multiple platforms on the internet 2. The system of claim 1.

3. The analysis unit Analyzes review text data to determine customer sentiment and ratings 2. The system of claim 1.

4. The summary section Extract points that customers particularly value and areas that need improvement, and provide them as a summary 2. The system of claim 1.

5. The update unit Automatically update information whenever a new review is posted 2. The system of claim 1.

6. The collecting unit The system estimates user emotions and adjusts the timing of collecting review information based on the estimated user emotions.

2. The system of claim 1.

7. The collecting unit Analyze users' past review collection history and select collection methods 2. The system of claim 1.

8. The collecting unit When collecting reviews, filter them based on user interests.

2. The system of claim 1.

9. The collecting unit When collecting review information, select the optimal collection method depending on the user's input method.

2. The system of claim 1.

10. The collecting unit Estimate user sentiment and prioritize review information to be collected based on the estimated user sentiment.

2. The system of claim 1.

11. The collecting unit When collecting reviews, prioritize relevant reviews based on the user's geographic location.

2. The system of claim 1.

Images