system

Abstract

The system according to the embodiment aims to extract useful information from online reviews and present appropriate improvements and success factors. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, an extraction unit, and a presentation unit. The collection unit collects online reviews. The analysis unit analyzes the reviews collected by the collection unit and performs sentiment analysis. The extraction unit extracts important points from the reviews based on the results of the sentiment analysis performed by the analysis unit. The presentation unit presents necessary improvements and success factors for the store based on the important points extracted by the extraction unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have faced the challenge of making it difficult to efficiently extract useful information from online reviews and identify appropriate areas for improvement and success factors.

[0005] The system according to the embodiment aims to extract useful information from online reviews and present appropriate improvements and success factors. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, an extraction unit, and a presentation unit. The collection unit collects online reviews. The analysis unit analyzes the reviews collected by the collection unit and performs sentiment analysis. The extraction unit extracts important points from the reviews based on the results of the sentiment analysis performed by the analysis unit. The presentation unit presents necessary improvements and success factors for the store based on the important points extracted by the extraction unit. [Effects of the Invention]

[0007] The system according to the embodiment can extract useful information from online reviews and suggest appropriate improvements and success factors. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A review analysis system according to an embodiment of the present invention analyzes online reviews of restaurants and clearly identifies areas for improvement and success factors for the restaurant. This review analysis system collects online reviews, and a generation AI analyzes the collected reviews and performs sentiment analysis. Based on the results of the sentiment analysis, important points are extracted from the reviews, and based on the extracted important points, the system clearly identifies areas for improvement and success factors for the restaurant. For example, the review analysis system collects reviews from multiple review sites and stores them in a database. For example, reviews may be collected from restaurant review sites and social media. Next, the review analysis system analyzes the collected reviews using a generation AI and performs sentiment analysis. The generation AI analyzes the text data of the reviews and determines whether they contain positive or negative sentiment. For example, a review stating "the food was delicious" is determined to have a positive sentiment, and a review stating "the service was poor" is determined to have a negative sentiment. Next, the review analysis system extracts important points from the reviews based on the results of the sentiment analysis. The generation AI extracts particularly important points from the reviews based on the results of the sentiment analysis. For example, points such as "the taste of the food" and "the quality of the service" are extracted. Finally, the review analysis system clearly presents the restaurant's necessary improvements and success factors based on the extracted key points. Based on the extracted points, the generation AI presents specific improvements and success factors for the restaurant. For example, it makes suggestions such as "introduce new recipes to improve the taste of the food" or "strengthen staff training to improve service quality." This allows the review analysis system to effectively utilize online reviews and clearly identify areas for improvement and success factors. This will enable the restaurant to improve the quality of its service and food, and increase customer satisfaction. This allows the review analysis system to effectively analyze a restaurant's online reviews and clearly present areas for improvement and success factors.

[0029] A review analysis system according to an embodiment includes a collection unit, an analysis unit, an extraction unit, and a presentation unit. The collection unit collects online reviews. The collection unit can collect reviews using, for example, web scraping or an API. For example, the collection unit collects reviews from restaurant review sites, social media, and the like, and stores them in a database. The collection unit can also collect reviews using a generation AI. The analysis unit analyzes the reviews collected by the collection unit and performs sentiment analysis. The analysis unit analyzes text data of the reviews using, for example, natural language processing technology, and determines positive and negative sentiment. For example, the analysis unit determines a review stating "the food was delicious" as a positive sentiment and a review stating "the service was poor" as a negative sentiment. The analysis unit can also perform sentiment analysis using a generation AI. The extraction unit extracts important points from the reviews based on the results of the sentiment analysis performed by the analysis unit. The extraction unit extracts particularly important points from the reviews based on the results of the sentiment analysis. For example, the extraction unit extracts points such as "the taste of the food" and "the quality of the service." The extraction unit can also extract important points using a generation AI. The presentation unit presents improvements and success factors needed for the restaurant based on the important points extracted by the extraction unit. The presentation unit presents specific improvements and success factors for the restaurant based on the extracted points, for example. For example, the presentation unit makes suggestions such as "introduce new recipes to improve the taste of the food" or "strengthen staff training to improve the quality of service." The presentation unit can also present improvements and success factors using a generation AI. As a result, the review analysis system according to the embodiment can effectively analyze online reviews of restaurants and clearly present improvements and success factors.

[0030] The collection unit may collect reviews using web scraping or an API. For example, the collection unit may collect reviews using web scraping. For example, the collection unit may collect reviews from a website using a tool such as Python's BeautifulSoup or Scrapy. The collection unit may also collect reviews using an API. For example, the collection unit may collect reviews using an API of a specific platform. When using an API, the collection unit sets an authentication method and obtains necessary data. This allows the collection unit to efficiently collect reviews from a variety of sources.

[0031] The analysis unit can analyze the review text data using natural language processing technology and determine positive or negative emotions. The analysis unit can analyze the review text data using, for example, morphological analysis. For example, the analysis unit can use morphological analysis to divide the review text data into words and determine the part of speech of each word. The analysis unit can also analyze the review text data using grammatical analysis. For example, the analysis unit can use grammatical analysis to analyze the structure of the review sentence and identify sentence elements such as the subject, predicate, and object. The analysis unit can also analyze the review text data using semantic analysis. For example, the analysis unit can use semantic analysis to analyze the meaning of the review sentence and determine positive or negative emotions. This allows the analysis unit to accurately determine the sentiment of the review.

[0032] The extraction unit can extract frequently occurring keywords or phrases based on the results of the sentiment analysis. For example, the extraction unit extracts frequently occurring keywords based on the results of the sentiment analysis. For example, the extraction unit identifies keywords that appear frequently in reviews based on the results of the sentiment analysis and extracts those keywords. The extraction unit can also extract frequently occurring phrases based on the results of the sentiment analysis. For example, the extraction unit identifies phrases that appear frequently in reviews based on the results of the sentiment analysis and extracts those phrases. The extraction unit can also extract frequently occurring keywords or phrases using co-occurrence network analysis. For example, the extraction unit uses co-occurrence network analysis to identify keywords or phrases that appear together in reviews and extracts those keywords or phrases. This allows the extraction unit to efficiently extract important points.

[0033] The presentation unit can present specific improvement points and success factors for the restaurant based on the extracted points. The presentation unit presents specific improvement points for the restaurant based on the extracted points. For example, the presentation unit makes suggestions such as "introduce new recipes to improve the taste of the food" or "strengthen staff training to improve the quality of service." The presentation unit can also present specific success factors for the restaurant based on the extracted points. For example, the presentation unit makes suggestions such as "conduct regular surveys to increase customer satisfaction" or "introduce a reward program to increase repeat customers." The presentation unit can also present improvement points and success factors using generative AI. This allows the presentation unit to clearly present specific improvement points and success factors for the restaurant.

[0034] When collecting reviews, the collection unit can prioritize collecting reviews during specific time periods or event periods. For example, the collection unit can concentrate collection during peak times (e.g., lunch time or dinner time) at the restaurant to obtain real-time feedback. The collection unit can also concentrate collection during specific event periods (e.g., Christmas or Valentine's Day) to understand customer reactions to the event. Furthermore, the collection unit can concentrate collection during the introduction period of a new menu item at the restaurant to quickly obtain customer evaluations of the new menu item. This allows the collection unit to efficiently collect reviews during specific time periods or event periods. Specific definitions of specific time periods or event periods include, for example, weekends or sales periods. Some or all of the above-described processing in the collection unit may be performed using or without the generation AI. For example, in order to prioritize collecting reviews during specific time periods or event periods, the collection unit inputs collection conditions to the generation AI, and the generation AI executes collection.

[0035] When collecting reviews, the collection unit can evaluate the reliability of a specific reviewer and prioritize collecting reliable reviews. For example, the collection unit prioritizes collecting reviews from reviewers who have posted many reviews in the past and received high ratings from other users. The collection unit can also analyze the reviewer's profile information and prioritize collecting reviews from reliable reviewers. Furthermore, the collection unit can refer to the reviewer's past review history and prioritize collecting reviews from reviewers who have provided consistent ratings. This allows the collection unit to obtain more accurate feedback by preferentially collecting reliable reviews. The evaluation of the reviewer's reliability is based on, for example, the reviewer's past review history and the reviewer's ratings. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, to evaluate the reviewer's reliability, the collection unit inputs the reviewer's data into the generation AI, and the generation AI evaluates the reliability.

[0036] When collecting reviews, the collection unit can prioritize collecting highly relevant reviews by taking into account the user's geographical location information. For example, the collection unit can prioritize collecting reviews from users living near a restaurant to obtain region-specific feedback. The collection unit can also prioritize collecting reviews from tourists to understand the evaluation of services for tourists. Furthermore, the collection unit can prioritize collecting reviews from specific regions to analyze differences in evaluations between regions. In this way, the collection unit can obtain region-specific feedback by preferentially collecting reviews with high geographical relevance. The collection of geographical location information is performed using, for example, GPS data or IP addresses. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, to obtain the user's geographical location information, the collection unit inputs location data into the generation AI, and the generation AI analyzes the location information.

[0037] When collecting reviews, the collection unit can analyze the user's social media activity and collect relevant reviews. For example, the collection unit analyzes the user's social media posts and prioritizes collecting posts related to restaurants. The collection unit can also evaluate the user's number of followers and influence and prioritize collecting reviews from influential users. Furthermore, the collection unit can take into account the frequency of the user's social media activity and prioritize collecting reviews from active users. This allows the collection unit to efficiently collect highly relevant reviews by analyzing social media activity. Analysis of social media activity is performed based on, for example, the content of posts and the number of likes. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, to analyze the user's social media activity, the collection unit inputs social media data into the generation AI, which then analyzes the activity.

[0038] During sentiment analysis, the analysis unit can evaluate the intensity of sentiment by taking into account the context of the review. For example, the analysis unit analyzes the context of the review to identify parts where positive sentiment is strongly expressed. The analysis unit can also analyze the context of the review to identify parts where negative sentiment is strongly expressed. Furthermore, the analysis unit can analyze the context of the review to identify parts where neutral sentiment is strongly expressed. This allows the analysis unit to accurately evaluate the intensity of sentiment by taking the context of the review into consideration. Analysis of the context of the review is performed based on, for example, surrounding sentences or related topics. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, to analyze the context of the review, the analysis unit inputs text data into the generation AI, and the generation AI analyzes the context.

[0039] During sentiment analysis, the analysis unit can evaluate the reliability of a reviewer's sentiment by referring to the reviewer's past review history. For example, the analysis unit may refer to the reviewer's past review history and evaluate the sentiment of a reviewer who has provided consistent ratings as highly reliable. The analysis unit may also refer to the reviewer's past review history and evaluate the sentiment of a reviewer who has provided extreme ratings as unreliable. Furthermore, the analysis unit may refer to the reviewer's past review history and evaluate the sentiment of a reviewer who exhibits a specific trend as highly reliable. In this way, the analysis unit can evaluate the reliability of a reviewer's sentiment by referring to the reviewer's past review history. The reference to the reviewer's past review history is performed based on, for example, past ratings and posting frequency. Some or all of the above-described processing in the analysis unit may be performed using or without the generation AI. For example, to analyze the reviewer's past review history, the analysis unit inputs reviewer data into the generation AI, which then analyzes the history.

[0040] During sentiment analysis, the analysis unit can analyze emotional trends by taking into account the geographical distribution of reviews. For example, the analysis unit analyzes reviews from a specific region to understand emotional trends specific to that region. The analysis unit can also analyze reviews from tourists to understand evaluations of services provided to tourists. Furthermore, the analysis unit can analyze reviews from users living near a restaurant to obtain feedback specific to the region. In this way, the analysis unit can understand emotional trends specific to the region by taking geographical distribution into account. The analysis of geographical distribution is performed based on, for example, the number of reviews per region or keywords specific to the region. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, to analyze the geographical distribution of reviews, the analysis unit inputs location data into the generation AI, which then analyzes the distribution.

[0041] During sentiment analysis, the analysis unit can improve the accuracy of sentiment by referring to literature related to the review. For example, the analysis unit can improve the accuracy of positive sentiment by referring to literature related to the review. The analysis unit can also improve the accuracy of negative sentiment by referring to literature related to the review. Furthermore, the analysis unit can improve the accuracy of neutral sentiment by referring to literature related to the review. In this way, the analysis unit can improve the accuracy of sentiment analysis by referring to related literature. The reference to related literature is performed based on, for example, specific research papers or industry reports. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, to improve the accuracy of sentiment analysis, the analysis unit inputs related literature into the generation AI, and the generation AI analyzes the literature.

[0042] The extraction unit can improve the accuracy of extraction by taking into account the interrelationships between reviews when extracting keywords and phrases. The extraction unit, for example, analyzes the interrelationships between reviews and extracts highly relevant keywords and phrases. The extraction unit can also analyze the interrelationships between reviews and extract frequently occurring keywords and phrases. Furthermore, the extraction unit can analyze the interrelationships between reviews and extract important keywords and phrases. In this way, the extraction unit can improve the accuracy of extraction by taking into account the interrelationships between reviews. The analysis of the interrelationships between reviews is performed based on, for example, co-occurrence network analysis or relevance scores. Some or all of the above-mentioned processing in the extraction unit may be performed using or without the generation AI. For example, the extraction unit inputs text data to the generation AI to analyze the interrelationships between reviews, and the generation AI analyzes the interrelationships.

[0043] The extraction unit can extract keywords and phrases while taking into account reviewer attribute information. For example, the extraction unit extracts keywords and phrases related to specific attributes by taking into account the reviewer's age and gender. The extraction unit can also extract region-specific keywords and phrases by taking into account the reviewer's place of residence. Furthermore, the extraction unit can extract keywords and phrases related to specific interests by taking into account the reviewer's occupation and hobbies. In this way, the extraction unit can extract keywords and phrases related to specific attributes by taking into account the reviewer's attribute information. The reviewer's attribute information is collected based on, for example, age, gender, region, etc. Some or all of the above-mentioned processing in the extraction unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the extraction unit inputs attribute data to a generation AI to analyze the reviewer's attribute information, and the generation AI analyzes the attribute information.

[0044] The extraction unit can extract keywords and phrases while taking into account the geographical distribution of reviews. For example, the extraction unit analyzes reviews from a specific region and extracts keywords and phrases specific to that region. The extraction unit can also analyze reviews by tourists and extract keywords and phrases related to tourists. Furthermore, the extraction unit can analyze reviews by users living near a restaurant and extract keywords and phrases specific to that region. In this way, the extraction unit can extract keywords and phrases specific to that region by taking geographical distribution into account. The analysis of the geographical distribution is performed based on, for example, the number of reviews per region and keywords specific to that region. Some or all of the above-mentioned processing in the extraction unit may be performed using or without the generation AI. For example, to analyze the geographical distribution of reviews, the extraction unit inputs location data into the generation AI, which then analyzes the distribution.

[0045] When extracting keywords and phrases, the extraction unit can improve the accuracy of the extraction by referring to literature related to the review. For example, the extraction unit can improve the accuracy of positive keywords and phrases by referring to literature related to the review. The extraction unit can also improve the accuracy of negative keywords and phrases by referring to literature related to the review. Furthermore, the extraction unit can improve the accuracy of neutral keywords and phrases by referring to literature related to the review. In this way, the extraction unit can improve the accuracy of the extraction by referring to the related literature. The reference to the related literature is based on, for example, specific research papers or industry reports. Some or all of the above-mentioned processing in the extraction unit may be performed using or without the generation AI. For example, to improve the accuracy of the extraction, the extraction unit inputs related literature into the generation AI, which then analyzes the literature.

[0046] When presenting improvement points and success factors, the presentation unit can select the optimal presentation method by referring to past presentation history. For example, the presentation unit refers to presentation methods that have been successful in the past and presents improvement points and success factors in a similar manner. The presentation unit can also avoid presentation methods that have failed in the past and present improvement points and success factors in a different manner. Furthermore, the presentation unit can analyze past presentation history and select the most effective presentation method. In this way, the presentation unit can select the optimal presentation method by referring to the past presentation history. The reference to the past presentation history is performed based on, for example, past feedback or evaluations of presentation results. Some or all of the above-mentioned processing in the presentation unit may be performed using or without the generation AI. For example, to analyze the past presentation history, the presentation unit inputs presentation data to the generation AI, and the generation AI analyzes the history.

[0047] The presentation unit can take into consideration the reviewer's attribute information when presenting improvement points and success factors. For example, the presentation unit can take into consideration the reviewer's age and gender to present improvement points and success factors related to specific attributes. The presentation unit can also take into consideration the reviewer's place of residence to present improvement points and success factors specific to the region. Furthermore, the presentation unit can take into consideration the reviewer's occupation and hobbies to present improvement points and success factors related to specific interests. In this way, the presentation unit can present improvement points and success factors related to specific attributes by taking into consideration the reviewer's attribute information. The reviewer's attribute information is collected based on, for example, age, gender, region, etc. Some or all of the above-mentioned processing in the presentation unit may be performed using or without the generation AI. For example, the presentation unit inputs attribute data into the generation AI to analyze the reviewer's attribute information, and the generation AI analyzes the attribute information.

[0048] The presentation unit can take into account the geographical distribution of reviews when presenting improvement points and success factors. For example, the presentation unit analyzes reviews from a specific region and presents improvement points and success factors specific to that region. The presentation unit can also analyze tourist reviews and present improvement points and success factors related to tourists. Furthermore, the presentation unit can analyze reviews from users living near the restaurant and present improvement points and success factors specific to the region. In this way, the presentation unit can present improvement points and success factors specific to the region by taking geographical distribution into consideration. Analysis of the geographical distribution is performed based on, for example, the number of reviews per region or keywords specific to the region. Some or all of the above-mentioned processing in the presentation unit may be performed using or without the generation AI. For example, to analyze the geographical distribution of reviews, the presentation unit inputs location data into the generation AI, which then analyzes the distribution.

[0049] When presenting improvement points and success factors, the presentation unit can improve the accuracy of the presentation by referring to related literature of the review. For example, the presentation unit can improve the accuracy of positive improvement points and success factors by referring to related literature of the review. The presentation unit can also improve the accuracy of negative improvement points and success factors by referring to related literature of the review. Furthermore, the presentation unit can improve the accuracy of neutral improvement points and success factors by referring to related literature of the review. In this way, the presentation unit can improve the accuracy of the presentation by referring to related literature. Reference to related literature is made based on, for example, specific research papers or industry reports. Some or all of the above-mentioned processing in the presentation unit may be performed using or without the generation AI. For example, to improve the accuracy of the presentation, the presentation unit inputs related literature into the generation AI, which then analyzes the literature.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The review analysis system can further consider the user's purchasing history when performing analysis. For example, the analysis unit can evaluate the reliability of reviews based on the user's past purchases and visit frequency. The analysis unit can also analyze the evaluation of a specific menu item in detail based on the user's purchasing history. Furthermore, the analysis unit can prioritize the analysis of reviews by repeat customers based on the user's purchasing history and place importance on the opinions of repeat customers. This allows the review analysis system to perform more accurate analysis by considering the user's purchasing history.

[0052] The review analysis system can further consider the frequency with which users post reviews during its analysis. For example, the analysis unit can prioritize the analysis of reviews from users who post reviews frequently and emphasize the opinions of active users. The analysis unit can also carefully analyze reviews from users who post reviews infrequently and evaluate their reliability. Furthermore, the analysis unit can analyze reviews from users who post reviews intensively during a specific period and grasp trends during that period. In this way, the review analysis system can perform a more reliable analysis by considering the frequency with which users post reviews.

[0053] The review analysis system can further consider a user's social media activity when conducting analysis. For example, the analysis unit can analyze the content of a user's social media posts to collect opinions related to restaurants. The analysis unit can also evaluate the number of users' followers and influence, and place emphasis on reviews from influential users. Furthermore, the analysis unit can consider the frequency of a user's social media activity and prioritize the analysis of opinions from active users. In this way, the review analysis system can collect a wider range of opinions and improve the accuracy of the analysis by taking into account a user's social media activity.

[0054] The review analysis system can further consider the user's geographical location information when performing analysis. For example, the analysis unit can prioritize analysis of reviews from users living near a restaurant and emphasize feedback specific to that region. The analysis unit can also analyze reviews from tourists and understand the evaluation of services for tourists. Furthermore, the analysis unit can analyze reviews from specific regions and analyze differences in evaluations between regions. In this way, the review analysis system can collect region-specific feedback and improve the accuracy of analysis by considering the user's geographical location information.

[0055] The review analysis system can further consider user attribute information when performing analysis. For example, the analysis unit can consider the user's age and gender to prioritize analysis of reviews related to specific attributes. The analysis unit can also consider the user's occupation and hobbies to perform detailed analysis of reviews related to specific interests. Furthermore, the analysis unit can consider the user's place of residence to emphasize region-specific reviews. In this way, the review analysis system can collect feedback related to specific attributes by considering the user's attribute information, thereby improving the accuracy of analysis.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The collection unit collects online reviews. The collection unit can collect reviews using, for example, web scraping or an API. For example, the collection unit collects reviews from restaurant review sites and social media, and stores them in a database. The collection unit can also collect reviews using generative AI. Step 2: The analysis unit analyzes the reviews collected by the collection unit and performs sentiment analysis. The analysis unit uses, for example, natural language processing technology to analyze the text data of the reviews and determine positive or negative sentiment. For example, the analysis unit may determine a review that states "the food was delicious" as a positive sentiment and a review that states "the service was bad" as a negative sentiment. The analysis unit can also perform sentiment analysis using generative AI. Step 3: The extraction unit extracts important points from the reviews based on the results of the sentiment analysis performed by the analysis unit. The extraction unit extracts particularly important points from the reviews based on the results of the sentiment analysis. For example, the extraction unit extracts points such as "the taste of the food" and "the quality of the service." The extraction unit can also extract important points using generative AI. Step 4: The presentation unit presents the restaurant with necessary improvements and success factors based on the key points extracted by the extraction unit. For example, the presentation unit presents specific improvements and success factors for the restaurant based on the extracted points. For example, the presentation unit may make suggestions such as "introduce new recipes to improve the taste of the food" or "strengthen staff training to improve the quality of service." The presentation unit can also use generative AI to present improvements and success factors.

[0058] (Example 2) A review analysis system according to an embodiment of the present invention analyzes online reviews of restaurants and clearly identifies areas for improvement and success factors for the restaurant. This review analysis system collects online reviews, and a generation AI analyzes the collected reviews and performs sentiment analysis. Based on the results of the sentiment analysis, important points are extracted from the reviews, and based on the extracted important points, the system clearly identifies areas for improvement and success factors for the restaurant. For example, the review analysis system collects reviews from multiple review sites and stores them in a database. For example, reviews may be collected from restaurant review sites and social media. Next, the review analysis system analyzes the collected reviews using a generation AI and performs sentiment analysis. The generation AI analyzes the text data of the reviews and determines whether they contain positive or negative sentiment. For example, a review stating "the food was delicious" is determined to have a positive sentiment, and a review stating "the service was poor" is determined to have a negative sentiment. Next, the review analysis system extracts important points from the reviews based on the results of the sentiment analysis. The generation AI extracts particularly important points from the reviews based on the results of the sentiment analysis. For example, points such as "the taste of the food" and "the quality of the service" are extracted. Finally, the review analysis system clearly presents the restaurant's necessary improvements and success factors based on the extracted key points. Based on the extracted points, the generation AI presents specific improvements and success factors for the restaurant. For example, it makes suggestions such as "introduce new recipes to improve the taste of the food" or "strengthen staff training to improve service quality." This allows the review analysis system to effectively utilize online reviews and clearly identify areas for improvement and success factors. This will enable the restaurant to improve the quality of its service and food, and increase customer satisfaction. This allows the review analysis system to effectively analyze a restaurant's online reviews and clearly present areas for improvement and success factors.

[0059] A review analysis system according to an embodiment includes a collection unit, an analysis unit, an extraction unit, and a presentation unit. The collection unit collects online reviews. The collection unit can collect reviews using, for example, web scraping or an API. For example, the collection unit collects reviews from restaurant review sites, social media, and the like, and stores them in a database. The collection unit can also collect reviews using a generation AI. The analysis unit analyzes the reviews collected by the collection unit and performs sentiment analysis. The analysis unit analyzes text data of the reviews using, for example, natural language processing technology, and determines positive and negative sentiment. For example, the analysis unit determines a review stating "the food was delicious" as a positive sentiment and a review stating "the service was poor" as a negative sentiment. The analysis unit can also perform sentiment analysis using a generation AI. The extraction unit extracts important points from the reviews based on the results of the sentiment analysis performed by the analysis unit. The extraction unit extracts particularly important points from the reviews based on the results of the sentiment analysis. For example, the extraction unit extracts points such as "the taste of the food" and "the quality of the service." The extraction unit can also extract important points using a generation AI. The presentation unit presents improvements and success factors needed for the restaurant based on the important points extracted by the extraction unit. The presentation unit presents specific improvements and success factors for the restaurant based on the extracted points, for example. For example, the presentation unit makes suggestions such as "introduce new recipes to improve the taste of the food" or "strengthen staff training to improve the quality of service." The presentation unit can also present improvements and success factors using a generation AI. As a result, the review analysis system according to the embodiment can effectively analyze online reviews of restaurants and clearly present improvements and success factors.

[0060] The collection unit may collect reviews using web scraping or an API. For example, the collection unit may collect reviews using web scraping. For example, the collection unit may collect reviews from a website using a tool such as Python's BeautifulSoup or Scrapy. The collection unit may also collect reviews using an API. For example, the collection unit may collect reviews using an API of a specific platform. When using an API, the collection unit sets an authentication method and obtains necessary data. This allows the collection unit to efficiently collect reviews from a variety of sources.

[0061] The analysis unit can analyze the review text data using natural language processing technology and determine positive or negative emotions. The analysis unit can analyze the review text data using, for example, morphological analysis. For example, the analysis unit can use morphological analysis to divide the review text data into words and determine the part of speech of each word. The analysis unit can also analyze the review text data using grammatical analysis. For example, the analysis unit can use grammatical analysis to analyze the structure of the review sentence and identify sentence elements such as the subject, predicate, and object. The analysis unit can also analyze the review text data using semantic analysis. For example, the analysis unit can use semantic analysis to analyze the meaning of the review sentence and determine positive or negative emotions. This allows the analysis unit to accurately determine the sentiment of the review.

[0062] The extraction unit can extract frequently occurring keywords or phrases based on the results of the sentiment analysis. For example, the extraction unit extracts frequently occurring keywords based on the results of the sentiment analysis. For example, the extraction unit identifies keywords that appear frequently in reviews based on the results of the sentiment analysis and extracts those keywords. The extraction unit can also extract frequently occurring phrases based on the results of the sentiment analysis. For example, the extraction unit identifies phrases that appear frequently in reviews based on the results of the sentiment analysis and extracts those phrases. The extraction unit can also extract frequently occurring keywords or phrases using co-occurrence network analysis. For example, the extraction unit uses co-occurrence network analysis to identify keywords or phrases that appear together in reviews and extracts those keywords or phrases. This allows the extraction unit to efficiently extract important points.

[0063] The presentation unit can present specific improvement points and success factors for the restaurant based on the extracted points. The presentation unit presents specific improvement points for the restaurant based on the extracted points. For example, the presentation unit makes suggestions such as "introduce new recipes to improve the taste of the food" or "strengthen staff training to improve the quality of service." The presentation unit can also present specific success factors for the restaurant based on the extracted points. For example, the presentation unit makes suggestions such as "conduct regular surveys to increase customer satisfaction" or "introduce a reward program to increase repeat customers." The presentation unit can also present improvement points and success factors using generative AI. This allows the presentation unit to clearly present specific improvement points and success factors for the restaurant.

[0064] The collection unit can estimate a user's emotions and adjust the timing of review collection based on the estimated user's emotions. For example, the collection unit estimates a user's emotions and, if the user indicates positive emotions, immediately collects reviews to obtain the most recent positive feedback. Alternatively, the collection unit can estimate a user's emotions and, if the user indicates negative emotions, wait a certain period of time before collecting reviews to obtain feedback after the user's emotions have calmed down. Furthermore, the collection unit can estimate a user's emotions and, if the user indicates neutral emotions, collect reviews at regular intervals to obtain balanced feedback. This allows the collection unit to collect reviews at the optimal timing depending on the user's emotions. The user's emotions are estimated using technologies such as text analysis and facial expression recognition. Some or all of the above-described processing in the collection unit may be performed using a generation AI, or may be performed without using a generation AI. For example, to estimate a user's emotions, the collection unit inputs text data or image data into a generation AI, which then estimates the emotions.

[0065] When collecting reviews, the collection unit can prioritize collecting reviews during specific time periods or event periods. For example, the collection unit can concentrate collection during peak times (e.g., lunch time or dinner time) at the restaurant to obtain real-time feedback. The collection unit can also concentrate collection during specific event periods (e.g., Christmas or Valentine's Day) to understand customer reactions to the event. Furthermore, the collection unit can concentrate collection during the introduction period of a new menu item at the restaurant to quickly obtain customer evaluations of the new menu item. This allows the collection unit to efficiently collect reviews during specific time periods or event periods. Specific definitions of specific time periods or event periods include, for example, weekends or sales periods. Some or all of the above-described processing in the collection unit may be performed using or without the generation AI. For example, in order to prioritize collecting reviews during specific time periods or event periods, the collection unit inputs collection conditions to the generation AI, and the generation AI executes collection.

[0066] When collecting reviews, the collection unit can evaluate the reliability of a specific reviewer and prioritize collecting reliable reviews. For example, the collection unit prioritizes collecting reviews from reviewers who have posted many reviews in the past and received high ratings from other users. The collection unit can also analyze the reviewer's profile information and prioritize collecting reviews from reliable reviewers. Furthermore, the collection unit can refer to the reviewer's past review history and prioritize collecting reviews from reviewers who have provided consistent ratings. This allows the collection unit to obtain more accurate feedback by preferentially collecting reliable reviews. The evaluation of the reviewer's reliability is based on, for example, the reviewer's past review history and the reviewer's ratings. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, to evaluate the reviewer's reliability, the collection unit inputs the reviewer's data into the generation AI, and the generation AI evaluates the reliability.

[0067] The collection unit can estimate a user's emotions and prioritize reviews to be collected based on the estimated user emotions. For example, the collection unit can estimate a user's emotions and prioritize collecting reviews that indicate positive emotions to identify the restaurant's strengths. The collection unit can also estimate a user's emotions and prioritize collecting reviews that indicate negative emotions to quickly identify areas for improvement. Furthermore, the collection unit can estimate a user's emotions and collect reviews that indicate neutral emotions in a balanced manner to understand the overall evaluation. This allows the collection unit to prioritize reviews based on the user's emotions and prioritize collecting important feedback. The review prioritization is determined based on, for example, the intensity of emotions or the reviewer's credibility. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, the collection unit inputs text data or image data into the generation AI to estimate a user's emotions, and the generation AI estimates the emotions and prioritizes the reviews based on the results.

[0068] When collecting reviews, the collection unit can prioritize collecting highly relevant reviews by taking into account the user's geographical location information. For example, the collection unit can prioritize collecting reviews from users living near a restaurant to obtain region-specific feedback. The collection unit can also prioritize collecting reviews from tourists to understand the evaluation of services for tourists. Furthermore, the collection unit can prioritize collecting reviews from specific regions to analyze differences in evaluations between regions. In this way, the collection unit can obtain region-specific feedback by preferentially collecting reviews with high geographical relevance. The collection of geographical location information is performed using, for example, GPS data or IP addresses. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, to obtain the user's geographical location information, the collection unit inputs location data into the generation AI, and the generation AI analyzes the location information.

[0069] When collecting reviews, the collection unit can analyze the user's social media activity and collect relevant reviews. For example, the collection unit analyzes the user's social media posts and prioritizes collecting posts related to restaurants. The collection unit can also evaluate the user's number of followers and influence and prioritize collecting reviews from influential users. Furthermore, the collection unit can take into account the frequency of the user's social media activity and prioritize collecting reviews from active users. This allows the collection unit to efficiently collect highly relevant reviews by analyzing social media activity. Analysis of social media activity is performed based on, for example, the content of posts and the number of likes. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, to analyze the user's social media activity, the collection unit inputs social media data into the generation AI, which then analyzes the activity.

[0070] The analysis unit can estimate the user's emotions and adjust the emotion analysis algorithm based on the estimated user emotions. For example, the analysis unit can adjust the emotion analysis algorithm for reviews that indicate positive emotions to emphasize positive elements. The analysis unit can also adjust the emotion analysis algorithm for reviews that indicate negative emotions to analyze negative elements in detail. Furthermore, the analysis unit can adjust the emotion analysis algorithm for reviews that indicate neutral emotions to perform a balanced analysis. This allows the analysis unit to adjust the emotion analysis algorithm based on the user's emotions, enabling more accurate emotion analysis. The emotion analysis algorithm is adjusted based on, for example, parameter adjustment or learning data update. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, to adjust the emotion analysis algorithm, the analysis unit inputs emotion data into the generation AI, and the generation AI adjusts the algorithm.

[0071] During sentiment analysis, the analysis unit can evaluate the intensity of sentiment by taking into account the context of the review. For example, the analysis unit analyzes the context of the review to identify parts where positive sentiment is strongly expressed. The analysis unit can also analyze the context of the review to identify parts where negative sentiment is strongly expressed. Furthermore, the analysis unit can analyze the context of the review to identify parts where neutral sentiment is strongly expressed. This allows the analysis unit to accurately evaluate the intensity of sentiment by taking the context of the review into consideration. Analysis of the context of the review is performed based on, for example, surrounding sentences or related topics. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, to analyze the context of the review, the analysis unit inputs text data into the generation AI, and the generation AI analyzes the context.

[0072] During sentiment analysis, the analysis unit can evaluate the reliability of a reviewer's sentiment by referring to the reviewer's past review history. For example, the analysis unit may refer to the reviewer's past review history and evaluate the sentiment of a reviewer who has provided consistent ratings as highly reliable. The analysis unit may also refer to the reviewer's past review history and evaluate the sentiment of a reviewer who has provided extreme ratings as unreliable. Furthermore, the analysis unit may refer to the reviewer's past review history and evaluate the sentiment of a reviewer who exhibits a specific trend as highly reliable. In this way, the analysis unit can evaluate the reliability of a reviewer's sentiment by referring to the reviewer's past review history. The reference to the reviewer's past review history is performed based on, for example, past ratings and posting frequency. Some or all of the above-described processing in the analysis unit may be performed using or without the generation AI. For example, to analyze the reviewer's past review history, the analysis unit inputs reviewer data into the generation AI, which then analyzes the history.

[0073] The analysis unit can estimate the user's emotions and adjust the order in which the emotion analysis results are displayed based on the estimated user emotions. For example, the analysis unit can prioritize displaying reviews with positive emotions to highlight the restaurant's strengths. The analysis unit can also prioritize displaying reviews with negative emotions to quickly identify areas for improvement. Furthermore, the analysis unit can display reviews with neutral emotions in a balanced manner to grasp the overall evaluation. In this way, the analysis unit can prioritize displaying important information by adjusting the order in which the emotion analysis results are displayed based on the user's emotions. The adjustment of the display order of the emotion analysis results is performed based on, for example, the intensity or importance of the emotions. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit inputs emotion data into the generation AI to display the emotion analysis results, and the generation AI adjusts the display order.

[0074] During sentiment analysis, the analysis unit can analyze emotional trends by taking into account the geographical distribution of reviews. For example, the analysis unit analyzes reviews from a specific region to understand emotional trends specific to that region. The analysis unit can also analyze reviews from tourists to understand evaluations of services provided to tourists. Furthermore, the analysis unit can analyze reviews from users living near a restaurant to obtain feedback specific to the region. In this way, the analysis unit can understand emotional trends specific to the region by taking geographical distribution into account. The analysis of geographical distribution is performed based on, for example, the number of reviews per region or keywords specific to the region. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, to analyze the geographical distribution of reviews, the analysis unit inputs location data into the generation AI, which then analyzes the distribution.

[0075] During sentiment analysis, the analysis unit can improve the accuracy of sentiment by referring to literature related to the review. For example, the analysis unit can improve the accuracy of positive sentiment by referring to literature related to the review. The analysis unit can also improve the accuracy of negative sentiment by referring to literature related to the review. Furthermore, the analysis unit can improve the accuracy of neutral sentiment by referring to literature related to the review. In this way, the analysis unit can improve the accuracy of sentiment analysis by referring to related literature. The reference to related literature is performed based on, for example, specific research papers or industry reports. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, to improve the accuracy of sentiment analysis, the analysis unit inputs related literature into the generation AI, and the generation AI analyzes the literature.

[0076] The extraction unit can estimate the user's emotions and prioritize the keywords and phrases to be extracted based on the estimated user emotions. For example, the extraction unit can prioritize extracting keywords and phrases that indicate positive emotions to highlight the restaurant's strengths. The extraction unit can also prioritize extracting keywords and phrases that indicate negative emotions to quickly identify areas for improvement. Furthermore, the extraction unit can extract keywords and phrases that indicate neutral emotions in a balanced manner to grasp the overall evaluation. This allows the extraction unit to prioritize the keywords and phrases based on the user's emotions, thereby preferentially extracting important information. The priority of keywords and phrases is determined based on, for example, the intensity of emotions and frequency of occurrence. Some or all of the above-mentioned processing in the extraction unit may be performed using or without the generation AI. For example, to estimate the user's emotions, the extraction unit inputs text data into the generation AI, which then estimates the emotions and prioritizes the keywords and phrases based on the results.

[0077] The extraction unit can improve the accuracy of extraction by taking into account the interrelationships between reviews when extracting keywords and phrases. The extraction unit, for example, analyzes the interrelationships between reviews and extracts highly relevant keywords and phrases. The extraction unit can also analyze the interrelationships between reviews and extract frequently occurring keywords and phrases. Furthermore, the extraction unit can analyze the interrelationships between reviews and extract important keywords and phrases. In this way, the extraction unit can improve the accuracy of extraction by taking into account the interrelationships between reviews. The analysis of the interrelationships between reviews is performed based on, for example, co-occurrence network analysis or relevance scores. Some or all of the above-mentioned processing in the extraction unit may be performed using or without the generation AI. For example, the extraction unit inputs text data to the generation AI to analyze the interrelationships between reviews, and the generation AI analyzes the interrelationships.

[0078] The extraction unit can extract keywords and phrases while taking into account reviewer attribute information. For example, the extraction unit extracts keywords and phrases related to specific attributes by taking into account the reviewer's age and gender. The extraction unit can also extract region-specific keywords and phrases by taking into account the reviewer's place of residence. Furthermore, the extraction unit can extract keywords and phrases related to specific interests by taking into account the reviewer's occupation and hobbies. In this way, the extraction unit can extract keywords and phrases related to specific attributes by taking into account the reviewer's attribute information. The reviewer's attribute information is collected based on, for example, age, gender, region, etc. Some or all of the above-mentioned processing in the extraction unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the extraction unit inputs attribute data to a generation AI to analyze the reviewer's attribute information, and the generation AI analyzes the attribute information.

[0079] The extraction unit can estimate the user's emotions and adjust the display method of extracted keywords and phrases based on the estimated user emotions. For example, the extraction unit can highlight keywords and phrases that indicate positive emotions to highlight the restaurant's strengths. The extraction unit can also highlight keywords and phrases that indicate negative emotions to highlight areas for improvement. Furthermore, the extraction unit can display keywords and phrases that indicate neutral emotions in a balanced manner to grasp the overall evaluation. This allows the extraction unit to adjust the display method of keywords and phrases based on the user's emotions, thereby emphasizing important information. The adjustment of the display method of keywords and phrases is performed based on, for example, font size, color, and placement. Some or all of the above-mentioned processing in the extraction unit may be performed using or without the generation AI. For example, to estimate the user's emotions, the extraction unit inputs text data into the generation AI, which then estimates the emotions and adjusts the display method based on the results.

[0080] The extraction unit can extract keywords and phrases while taking into account the geographical distribution of reviews. For example, the extraction unit analyzes reviews from a specific region and extracts keywords and phrases specific to that region. The extraction unit can also analyze reviews by tourists and extract keywords and phrases related to tourists. Furthermore, the extraction unit can analyze reviews by users living near a restaurant and extract keywords and phrases specific to that region. In this way, the extraction unit can extract keywords and phrases specific to that region by taking geographical distribution into account. The analysis of the geographical distribution is performed based on, for example, the number of reviews per region and keywords specific to that region. Some or all of the above-mentioned processing in the extraction unit may be performed using or without the generation AI. For example, to analyze the geographical distribution of reviews, the extraction unit inputs location data into the generation AI, which then analyzes the distribution.

[0081] When extracting keywords and phrases, the extraction unit can improve the accuracy of the extraction by referring to literature related to the review. For example, the extraction unit can improve the accuracy of positive keywords and phrases by referring to literature related to the review. The extraction unit can also improve the accuracy of negative keywords and phrases by referring to literature related to the review. Furthermore, the extraction unit can improve the accuracy of neutral keywords and phrases by referring to literature related to the review. In this way, the extraction unit can improve the accuracy of the extraction by referring to the related literature. The reference to the related literature is based on, for example, specific research papers or industry reports. Some or all of the above-mentioned processing in the extraction unit may be performed using or without the generation AI. For example, to improve the accuracy of the extraction, the extraction unit inputs related literature into the generation AI, which then analyzes the literature.

[0082] The presentation unit can estimate the user's emotions and adjust the presentation method of the improvement points and success factors based on the estimated user emotions. For example, the presentation unit can emphasize the success factors for a user who expresses positive emotions. The presentation unit can also present the improvement points in detail for a user who expresses negative emotions. Furthermore, the presentation unit can adopt a balanced presentation method for a user who expresses neutral emotions. In this way, the presentation unit can provide more effective feedback by adjusting the presentation method based on the user's emotions. The presentation method of the improvement points and success factors can be adjusted based on, for example, a specific action plan or success case. Some or all of the above-mentioned processing in the presentation unit may be performed using or without the generation AI. For example, to estimate the user's emotions, the presentation unit inputs text data into the generation AI, which then estimates the emotions and adjusts the presentation method based on the results.

[0083] When presenting improvement points and success factors, the presentation unit can select the optimal presentation method by referring to past presentation history. For example, the presentation unit refers to presentation methods that have been successful in the past and presents improvement points and success factors in a similar manner. The presentation unit can also avoid presentation methods that have failed in the past and present improvement points and success factors in a different manner. Furthermore, the presentation unit can analyze past presentation history and select the most effective presentation method. In this way, the presentation unit can select the optimal presentation method by referring to the past presentation history. The reference to the past presentation history is performed based on, for example, past feedback or evaluations of presentation results. Some or all of the above-mentioned processing in the presentation unit may be performed using or without the generation AI. For example, to analyze the past presentation history, the presentation unit inputs presentation data to the generation AI, and the generation AI analyzes the history.

[0084] The presentation unit can take into consideration the reviewer's attribute information when presenting improvement points and success factors. For example, the presentation unit can take into consideration the reviewer's age and gender to present improvement points and success factors related to specific attributes. The presentation unit can also take into consideration the reviewer's place of residence to present improvement points and success factors specific to the region. Furthermore, the presentation unit can take into consideration the reviewer's occupation and hobbies to present improvement points and success factors related to specific interests. In this way, the presentation unit can present improvement points and success factors related to specific attributes by taking into consideration the reviewer's attribute information. The reviewer's attribute information is collected based on, for example, age, gender, region, etc. Some or all of the above-mentioned processing in the presentation unit may be performed using or without the generation AI. For example, the presentation unit inputs attribute data into the generation AI to analyze the reviewer's attribute information, and the generation AI analyzes the attribute information.

[0085] The presentation unit can estimate the user's emotions and prioritize improvements and success factors based on the estimated user emotions. For example, the presentation unit prioritizes success factors for a user who expresses positive emotions. The presentation unit can also prioritize improvements for a user who expresses negative emotions. Furthermore, the presentation unit can present information in a balanced order of priority for a user who expresses neutral emotions. In this way, the presentation unit can prioritize important information by determining priorities based on the user's emotions. The prioritization of improvements and success factors is based on, for example, the intensity or importance of the emotions. Some or all of the above-described processing in the presentation unit may be performed using or without the generation AI. For example, the presentation unit inputs text data to the generation AI to estimate the user's emotions, and the generation AI estimates the emotions and determines the priorities based on the results.

[0086] The presentation unit can take into account the geographical distribution of reviews when presenting improvement points and success factors. For example, the presentation unit analyzes reviews from a specific region and presents improvement points and success factors specific to that region. The presentation unit can also analyze tourist reviews and present improvement points and success factors related to tourists. Furthermore, the presentation unit can analyze reviews from users living near the restaurant and present improvement points and success factors specific to the region. In this way, the presentation unit can present improvement points and success factors specific to the region by taking geographical distribution into consideration. Analysis of the geographical distribution is performed based on, for example, the number of reviews per region or keywords specific to the region. Some or all of the above-mentioned processing in the presentation unit may be performed using or without the generation AI. For example, to analyze the geographical distribution of reviews, the presentation unit inputs location data into the generation AI, which then analyzes the distribution.

[0087] When presenting improvement points and success factors, the presentation unit can improve the accuracy of the presentation by referring to related literature of the review. For example, the presentation unit can improve the accuracy of positive improvement points and success factors by referring to related literature of the review. The presentation unit can also improve the accuracy of negative improvement points and success factors by referring to related literature of the review. Furthermore, the presentation unit can improve the accuracy of neutral improvement points and success factors by referring to related literature of the review. In this way, the presentation unit can improve the accuracy of the presentation by referring to related literature. Reference to related literature is made based on, for example, specific research papers or industry reports. Some or all of the above-mentioned processing in the presentation unit may be performed using or without the generation AI. For example, to improve the accuracy of the presentation, the presentation unit inputs related literature into the generation AI, which then analyzes the literature. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, extraction unit, and presentation unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects reviews from review sites and social networking sites via the communication I / F 44 of the smart device 14 and stores them in the database 24 of the data processing device 12. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs sentiment analysis of the collected reviews. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and extracts important points based on the results of the sentiment analysis. The presentation unit is realized, for example, by the control unit 46A of the smart device 14 and presents areas for improvement and success factors based on the extracted points. === Hard Collateral 1-2 === Each of the multiple elements including the collection unit, analysis unit, extraction unit, and presentation unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects reviews from review sites and SNS via the communication I / F 44 of the smart glasses 214 and stores them in the database 24 of the data processing device 12. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs sentiment analysis of the collected reviews. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and extracts important points based on the results of the sentiment analysis. The presentation unit is realized, for example, by the control unit 46A of the smart glasses 214 and presents areas for improvement and success factors based on the extracted points. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, extraction unit, and presentation unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects reviews from review sites and social networking sites via the communication I / F 44 of the headset type terminal 314 and stores the reviews in the database 24 of the data processing device 12. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs sentiment analysis of the collected reviews. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and extracts important points based on the results of the sentiment analysis. The presentation unit is realized, for example, by the control unit 46A of the headset type terminal 314 and presents areas for improvement and success factors based on the extracted points. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, extraction unit, and presentation unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects reviews from review sites and SNS via the communication I / F 44 of the robot 414 and stores the reviews in the database 24 of the data processing device 12. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs sentiment analysis of the collected reviews. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and extracts important points based on the results of the sentiment analysis. The presentation unit is realized, for example, by the control unit 46A of the robot 414 and presents points for improvement and success factors based on the extracted points.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The review analysis system can further consider the user's purchasing history when performing analysis. For example, the analysis unit can evaluate the reliability of reviews based on the user's past purchases and visit frequency. The analysis unit can also analyze the evaluation of a specific menu item in detail based on the user's purchasing history. Furthermore, the analysis unit can prioritize the analysis of reviews by repeat customers based on the user's purchasing history and place importance on the opinions of repeat customers. This allows the review analysis system to perform more accurate analysis by considering the user's purchasing history.

[0090] The review analysis system can further consider the frequency with which users post reviews during its analysis. For example, the analysis unit can prioritize the analysis of reviews from users who post reviews frequently and emphasize the opinions of active users. The analysis unit can also carefully analyze reviews from users who post reviews infrequently and evaluate their reliability. Furthermore, the analysis unit can analyze reviews from users who post reviews intensively during a specific period and grasp trends during that period. In this way, the review analysis system can perform a more reliable analysis by considering the frequency with which users post reviews.

[0091] The review analysis system can further consider a user's social media activity when conducting analysis. For example, the analysis unit can analyze the content of a user's social media posts to collect opinions related to restaurants. The analysis unit can also evaluate the number of users' followers and influence, and place emphasis on reviews from influential users. Furthermore, the analysis unit can consider the frequency of a user's social media activity and prioritize the analysis of opinions from active users. In this way, the review analysis system can collect a wider range of opinions and improve the accuracy of the analysis by taking into account a user's social media activity.

[0092] The review analysis system can further consider the user's geographical location information when performing analysis. For example, the analysis unit can prioritize analysis of reviews from users living near a restaurant and emphasize feedback specific to that region. The analysis unit can also analyze reviews from tourists and understand the evaluation of services for tourists. Furthermore, the analysis unit can analyze reviews from specific regions and analyze differences in evaluations between regions. In this way, the review analysis system can collect region-specific feedback and improve the accuracy of analysis by considering the user's geographical location information.

[0093] The review analysis system can further consider user attribute information when performing analysis. For example, the analysis unit can consider the user's age and gender to prioritize analysis of reviews related to specific attributes. The analysis unit can also consider the user's occupation and hobbies to perform detailed analysis of reviews related to specific interests. Furthermore, the analysis unit can consider the user's place of residence to emphasize region-specific reviews. In this way, the review analysis system can collect feedback related to specific attributes by considering the user's attribute information, thereby improving the accuracy of analysis.

[0094] The review analysis system can further estimate the user's emotions and evaluate the reliability of the review based on the estimated emotions. For example, the analysis unit can evaluate reviews that show positive emotions as highly reliable and carefully evaluate reviews that show negative emotions. The analysis unit can also evaluate reviews that show neutral emotions in a balanced manner to grasp the overall reliability. Furthermore, the analysis unit can take into account the intensity of emotions and place more importance on reviews that show strong emotions. In this way, the review analysis system can evaluate the reliability of reviews by taking into account the user's emotions and improve the accuracy of the analysis.

[0095] The review analysis system can further estimate the user's emotions and evaluate the importance of the review based on the estimated emotions. For example, the analysis unit can evaluate reviews that show positive emotions as highly important and carefully evaluate reviews that show negative emotions. The analysis unit can also evaluate reviews that show neutral emotions in a balanced manner to grasp the overall importance. Furthermore, the analysis unit can take into account the intensity of emotions and place more importance on reviews that show strong emotions. In this way, the review analysis system can evaluate the importance of reviews by taking into account the user's emotions, thereby improving the accuracy of the analysis.

[0096] The review analysis system can further estimate the user's emotions and adjust the display order of reviews based on the estimated emotions. For example, the analysis unit can prioritize displaying reviews that express positive emotions to highlight the strengths of the restaurant. The analysis unit can also prioritize displaying reviews that express negative emotions to quickly identify areas for improvement. Furthermore, the analysis unit can display reviews that express neutral emotions in a balanced manner to grasp the overall evaluation. In this way, the review analysis system can prioritize displaying important information by taking the user's emotions into consideration and improve the accuracy of the analysis.

[0097] The review analysis system can further estimate user emotions and adjust the review extraction method based on the estimated emotions. For example, the extraction unit can prioritize extracting reviews that express positive emotions to highlight the strengths of a restaurant. The extraction unit can also prioritize extracting reviews that express negative emotions to quickly identify areas for improvement. Furthermore, the extraction unit can extract reviews that express neutral emotions in a balanced manner to grasp the overall evaluation. This allows the review analysis system to prioritize extracting important information and improve the accuracy of analysis by taking user emotions into consideration.

[0098] The review analysis system can further estimate the user's emotions and adjust the review analysis algorithm based on the estimated emotions. For example, the analysis unit can apply an algorithm that emphasizes positive elements to reviews that show positive emotions. The analysis unit can also apply an algorithm that analyzes negative elements in detail to reviews that show negative emotions. Furthermore, the analysis unit can apply an algorithm that performs a balanced analysis to reviews that show neutral emotions. In this way, the review analysis system can adjust the analysis algorithm by taking the user's emotions into consideration and improve the accuracy of the analysis.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The collection unit collects online reviews. The collection unit can collect reviews using, for example, web scraping or an API. For example, the collection unit collects reviews from restaurant review sites and social media, and stores them in a database. The collection unit can also collect reviews using generative AI. Step 2: The analysis unit analyzes the reviews collected by the collection unit and performs sentiment analysis. The analysis unit uses, for example, natural language processing technology to analyze the text data of the reviews and determine positive or negative sentiment. For example, the analysis unit may determine a review that states "the food was delicious" as a positive sentiment and a review that states "the service was bad" as a negative sentiment. The analysis unit can also perform sentiment analysis using generative AI. Step 3: The extraction unit extracts important points from the reviews based on the results of the sentiment analysis performed by the analysis unit. The extraction unit extracts particularly important points from the reviews based on the results of the sentiment analysis. For example, the extraction unit extracts points such as "the taste of the food" and "the quality of the service." The extraction unit can also extract important points using generative AI. Step 4: The presentation unit presents the restaurant with necessary improvements and success factors based on the key points extracted by the extraction unit. For example, the presentation unit presents specific improvements and success factors for the restaurant based on the extracted points. For example, the presentation unit may make suggestions such as "introduce new recipes to improve the taste of the food" or "strengthen staff training to improve the quality of service." The presentation unit can also use generative AI to present improvements and success factors.

[0101] 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.

[0102] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0103] 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.

[0104] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0119] 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.

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

[0122] 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.

[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 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.

[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. 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.

[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 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.

[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 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.

[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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0135] 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.

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

[0138] 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.

[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 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.

[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 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).

[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] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0152] 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.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0159] 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."

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] [Explanation of symbols]

[0173] 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 online reviews; an analysis unit that analyzes the reviews collected by the collection unit and performs sentiment analysis; an extraction unit that extracts important points from the reviews based on the result of the sentiment analysis performed by the analysis unit; A presentation unit that presents necessary improvements and success factors for the store based on the important points extracted by the extraction unit. A system characterized by:

2. The collecting unit Collect reviews using web scraping or APIs The system of claim 1 .

3. The analysis unit Analyzes review text data using natural language processing technology to determine positive or negative sentiment The system of claim 1 .

4. The extraction unit Extracting frequently occurring keywords or phrases based on the results of sentiment analysis The system of claim 1 .

5. The presentation unit Based on the extracted points, we will present specific improvements and success factors for the store. The system of claim 1 .

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

7. The collecting unit When collecting reviews, prioritize reviews during specific times or events. The system of claim 1 .

8. The collecting unit When collecting reviews, evaluate the reliability of specific reviewers and prioritize collecting highly reliable reviews. The system of claim 1 .

Images