system

Abstract

The system according to the embodiment aims to analyze word-of-mouth data, extract strengths and weaknesses of a service, and propose areas for improvement. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, an extraction unit, and a provision unit. The collection unit collects word-of-mouth data. The analysis unit analyzes the word-of-mouth data collected by the collection unit. The extraction unit extracts strengths and weaknesses based on the results of the analysis by the analysis unit. The provision unit suggests points to be reviewed based on the strengths and weaknesses 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 technology has had the problem of not being able to effectively utilize word-of-mouth data to extract the strengths and weaknesses of a service and propose areas for improvement.

[0005] The system according to the embodiment aims to analyze word-of-mouth data, extract strengths and weaknesses of a service, and propose areas for improvement. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, an extraction unit, and a provision unit. The collection unit collects word-of-mouth data. The analysis unit analyzes the word-of-mouth data collected by the collection unit. The extraction unit extracts strengths and weaknesses based on the results of the analysis by the analysis unit. The provision unit suggests points to be reviewed based on the strengths and weaknesses extracted by the extraction unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze word-of-mouth data, extract strengths and weaknesses of a service, and propose areas for improvement. [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 data analysis system according to an embodiment of the present invention collects review data, analyzes it using AI, extracts strengths and weaknesses, and proposes areas to be improved. The review data analysis system collects review data, analyzes it using AI, extracts strengths and weaknesses, and proposes areas to be improved, thereby clarifying the strengths and weaknesses of the target and proposing areas to be improved. For example, the review data analysis system collects review data. For example, the review data analysis system automatically collects review data through an API. Next, the review data analysis system uses AI to analyze the collected review data. The AI ​​analyzes the review data using natural language processing technology and extracts strengths and weaknesses. For example, the AI ​​analyzes the review data and extracts positive and negative reviews. Next, the review data analysis system proposes areas to be improved based on the strengths and weaknesses extracted by the AI. For example, if "fast delivery" is listed as a strength, the manager can consider measures to further strengthen this strength. Furthermore, if "insufficient product description" is identified as a weakness, the manager can take measures to improve the product description. This allows the review data analysis system to enable managers and executives to utilize review data to improve the value of their services. For example, restaurant managers can improve their menus and services based on review data. Sellers can also improve their products and services based on review data. Furthermore, AI periodically updates the results of the review data analysis, providing managers and executives with the latest information. This allows managers and executives to always be aware of areas for improvement based on the latest review data. For example, by regularly collecting review data and providing the results of AI analysis to managers, managers can quickly take appropriate measures. In this way, by having AI analyze review data, managers and executives can understand their company's strengths and weaknesses and identify areas that need improvement. This can help improve the value of each service.

[0029] A word-of-mouth data analysis system according to an embodiment includes a collection unit, an analysis unit, an extraction unit, and a provision unit. The collection unit collects word-of-mouth data. The word-of-mouth data includes, for example, text, audio, and images, but is not limited to these examples. The collection unit automatically collects word-of-mouth data, for example, through an API. The collection unit can also collect word-of-mouth data using web scraping technology. The collection unit can also provide an interface that allows users to directly input word-of-mouth data. For example, the collection unit automatically collects word-of-mouth data through an API. The collection unit can collect word-of-mouth data using, for example, a REST API. The collection unit can also collect word-of-mouth data using GraphQL. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. The analysis unit analyzes the word-of-mouth data collected by the collection unit. The analysis is performed using, for example, natural language processing technology, but is not limited to these examples. For example, the analysis unit analyzes the word-of-mouth data using morphological analysis. The analysis unit can also analyze the word-of-mouth data using grammatical analysis. The analysis unit can also analyze the review data using semantic analysis. For example, the analysis unit can analyze the review data using morphological analysis and calculate the frequency of word occurrence. Grammatical analysis is used to analyze the structure of a sentence and understand its meaning. Semantic analysis is used to analyze the meaning of a sentence and understand its content. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. The extraction unit extracts strengths and weaknesses based on the results of the analysis by the analysis unit. Strengths and weaknesses are extracted based on, for example, positive evaluations and negative evaluations, but are not limited to such examples. For example, the extraction unit extracts positive evaluations as strengths. The extraction unit can also extract negative evaluations as weaknesses. The extraction unit can also extract strengths and weaknesses based on the frequency of evaluations. For example, the extraction unit extracts items with a high frequency of positive evaluations as strengths. Items with a high frequency of negative evaluations are extracted as weaknesses.Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. The providing unit suggests points to be reviewed based on the strengths and weaknesses extracted by the extraction unit. The points to be reviewed may be suggested based on, for example, areas for improvement or strengthening, but are not limited to such examples. For example, the providing unit suggests measures to further strengthen strengths. The providing unit may also suggest measures to improve weaknesses. The providing unit may also display the analysis results in dashboard format. For example, the providing unit visually displays the analysis results using graphs or charts. The analysis results may also be displayed in table format. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. As a result, the review data analysis system according to the embodiment can efficiently collect, analyze, extract, and provide review data, thereby clarifying the strengths and weaknesses of a target and suggesting points to be reviewed.

[0030] The collection unit can automatically collect review data through an API. The collection unit collects review data using, for example, a REST API. For example, the collection unit sends a request to a specific endpoint to obtain review data. The collection unit can also collect review data using GraphQL. For example, the collection unit sends a query to obtain the required review data. The collection unit can also perform authentication using an API key to collect review data. For example, the collection unit performs authentication using an API key to obtain review data. This automatically collecting review data through an API improves the efficiency of data collection. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0031] The analysis unit can analyze the review data using natural language processing. The analysis unit analyzes the review data using, for example, morphological analysis. For example, the analysis unit divides the review data into morphemes and calculates the frequency of occurrence of each morpheme. The analysis unit can also analyze the review data using grammatical analysis. For example, the analysis unit analyzes the structure of a sentence to understand the meaning of the sentence. The analysis unit can also analyze the review data using semantic analysis. For example, the analysis unit analyzes the meaning of a sentence to understand the content of the sentence. In this way, the use of natural language processing improves the analysis accuracy of the review data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0032] The providing unit can display the analysis results in a dashboard format. The providing unit displays the analysis results using, for example, a graph. For example, the providing unit visually displays the analysis results using a bar graph or a line graph. The providing unit can also display the analysis results using a chart. For example, the providing unit visually displays the analysis results using a pie chart or a heat map. The providing unit can also display the analysis results in a table format. For example, the providing unit summarizes the analysis results in a table and displays them visually. In this way, displaying the analysis results in a dashboard format makes it easier for the user to visually understand the results. Some or all of the above-described processing in the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0033] The providing unit can periodically update the word-of-mouth data and provide the latest information. The providing unit, for example, updates the word-of-mouth data daily. For example, the providing unit collects word-of-mouth data daily and updates the analysis results. The providing unit can also update the word-of-mouth data weekly. For example, the providing unit collects word-of-mouth data weekly and updates the analysis results. The providing unit can also update the word-of-mouth data monthly. For example, the providing unit collects word-of-mouth data monthly and updates the analysis results. By periodically updating the word-of-mouth data, it is possible to always provide review points based on the latest information. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0034] When collecting review data, the collection unit can analyze the user's past review posting history and select the optimal collection method. The collection unit, for example, uses data mining technology to analyze the user's past review posting history. For example, the collection unit analyzes the user's past posting frequency and content to select the optimal collection method. The collection unit can also customize the collection method based on the user's past review posting history. For example, if the user has frequently posted reviews in the past, a simple interface can be provided to quickly collect reviews. Alternatively, if the user has posted detailed reviews in the past, more detailed input options can be provided to collect more in-depth feedback. Alternatively, if the user has posted negative reviews in the past, guidelines can be provided to encourage positive feedback. In this way, the optimal collection method can be selected by analyzing the user's past review posting history. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without AI.

[0035] When collecting review data, the collection unit can filter the review data based on the user's current areas of interest and activity status. The collection unit, for example, analyzes social media posts and search history to identify the user's current areas of interest and activity status. For example, the collection unit can analyze the user's social media posts to identify topics of interest. The collection unit can also analyze the user's search history to identify products and services of current interest. The collection unit filters the review data based on the user's current areas of interest and activity status. For example, the collection unit can prioritize collection of review data related to products and services of current interest to the user. The collection unit can also collect related review data based on places recently visited or services used by the user. The collection unit can also analyze the user's social media activity to collect review data related to topics of interest to the user. In this way, by filtering based on the user's current areas of interest and activity status, highly relevant review data can be collected. Some or all of the above-described processing by the collection unit may be performed, for example, using AI or without AI.

[0036] When collecting word-of-mouth data, the collection unit can select an appropriate collection means depending on the user's input method. The collection unit, for example, analyzes the user's device or interface to identify the user's input method. For example, if the user prefers voice input, the collection unit can collect word-of-mouth data using voice recognition technology. Alternatively, if the user prefers text input, the collection unit can provide a simple text input form to collect word-of-mouth data. Alternatively, if the user provides feedback using an image, the collection unit can collect word-of-mouth data using image analysis technology. This improves user convenience by selecting the optimal collection means depending on the user's input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0037] When collecting review data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. The collection unit, for example, uses GPS data or an IP address to acquire the user's geographical location information. For example, the collection unit acquires the user's GPS data and collects review data based on the user's current location. The collection unit can also analyze the user's IP address to identify the geographical location information. The collection unit prioritizes collecting highly relevant review data based on the user's geographical location information. For example, the collection unit prioritizes collecting review data related to places close to the user's current location. The collection unit can also prioritize collecting review data related to places the user has visited in the past. The collection unit can also prioritize collecting review data related to places the user plans to visit in the future. In this way, by taking the user's geographical location information into account, highly relevant review data can be prioritized. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0038] When collecting review data, the collection unit can analyze the user's social media activity and collect related review data. The collection unit, for example, uses social media analysis technology to analyze the user's social media activity. For example, the collection unit analyzes the content of the user's social media posts and collects related review data. The collection unit can also analyze the user's social media check-in information and collect related review data. The collection unit can also collect related review data by referring to the activities of the user's friends on social media. In this way, related review data can be efficiently collected by analyzing the user's social media activity. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0039] When collecting word-of-mouth data, the collection unit can customize the collection method by reflecting the user's past feedback. The collection unit, for example, uses data mining technology to reflect the user's past feedback. For example, the collection unit analyzes the user's past feedback and selects the optimal collection method. The collection unit can also customize the collection method based on the user's past feedback. For example, the collection unit can preferentially provide collection methods (audio, text, etc.) that the user has previously preferred. The collection method can also be customized based on feedback the user has previously provided. The optimal collection timing can also be determined from the user's past feedback. In this way, the optimal collection method can be provided by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0040] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the review data. The analysis unit, for example, uses data mining technology to evaluate the importance of the review data. For example, the analysis unit evaluates the importance of the review data and performs a detailed analysis on data with high importance. The analysis unit can also perform a simplified analysis on data with low importance. The analysis unit can also perform an analysis with an appropriate level of detail on data with medium importance. For example, a detailed analysis is performed on review data with high importance, and specific improvements are proposed. A simplified analysis is performed on review data with low importance, and only an overview is presented. An analysis with an appropriate level of detail is performed on review data with medium importance, providing balanced information. In this way, by adjusting the level of detail of the analysis based on the importance of the review data, an appropriate level of analysis result can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0041] During analysis, the analysis unit can apply different analysis algorithms depending on the category of review data. The analysis unit, for example, uses clustering technology to identify the category of review data. For example, the analysis unit clusters the review data by category and applies an analysis algorithm appropriate for each category. The analysis unit can also select different analysis algorithms depending on the category of review data. For example, to review data about products, an analysis algorithm specialized in product quality and functionality can be applied. To review data about services, an analysis algorithm specialized in service response and customer satisfaction can be applied. To review data about restaurants, an analysis algorithm specialized in food taste and service speed can be applied. In this way, by applying different analysis algorithms depending on the category of review data, the accuracy of analysis is improved. Some or all of the above-mentioned processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0042] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, uses data mining technology to analyze the user's past analysis results. For example, the analysis unit analyzes the user's past analysis results and finds common patterns. The analysis unit can also adjust the analysis algorithm based on the user's past analysis results. For example, the analysis unit adjusts the analysis algorithm based on feedback provided by the user in the past to improve accuracy. The analysis unit can also improve the accuracy of analysis for specific categories or topics by referring to the user's past analysis results. In this way, the accuracy of the analysis is improved by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or without AI.

[0043] During analysis, the analysis unit can determine the analysis priority based on the posting date of the review data. The analysis unit, for example, uses timestamp analysis technology to evaluate the posting date of the review data. For example, the analysis unit analyzes the timestamp of the review data to identify the posting date. The analysis unit can also determine the analysis priority based on the posting date of the review data. For example, the analysis unit can prioritize analysis of recently posted review data to provide the latest information. The analysis unit can also determine the analysis priority based on current trends while referring to review data posted in the past. It can also prioritize analysis of review data posted in a specific period to understand trends for that period. In this way, by determining the analysis priority based on the posting date of the review data, the latest information can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI or without AI.

[0044] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the review data. The analysis unit, for example, uses relevance analysis technology to evaluate the relevance of the review data. For example, the analysis unit analyzes the content of the review data and evaluates the relevance. The analysis unit can also adjust the order of analysis based on the relevance of the review data. For example, review data with high relevance can be analyzed preferentially to quickly provide important information. Review data with medium relevance can also be analyzed next to achieve overall balance. Review data with low relevance can also be analyzed last to provide supplemental information. In this way, by adjusting the order of analysis based on the relevance of the review data, important information can be quickly provided. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or without AI.

[0045] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. The analysis unit, for example, uses questionnaires or past data to evaluate the user's level of expertise. For example, the analysis unit can analyze the user's questionnaire responses to identify the user's level of expertise. The analysis unit can also analyze the user's past data to evaluate the user's level of expertise. The analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide detailed analysis results that use a lot of technical terms. If the user has general knowledge, the analysis unit can provide easy-to-understand analysis results with less technical terms. If the user is a beginner, the analysis unit can provide analysis results in simple language, avoiding technical terms. In this way, by adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easy for the user to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0046] The extraction unit can improve the accuracy of extraction by taking into account the interrelationships between the review data during extraction. The extraction unit, for example, uses co-occurrence analysis technology to evaluate the interrelationships between the review data. For example, the extraction unit finds commonalities between the review data and more accurately extracts strengths and weaknesses. The extraction unit can also analyze the interrelationships between the review data and extract related strengths and weaknesses together. The extraction unit can also maintain consistency of the extraction results by taking into account the interrelationships between the review data. For example, the extraction unit can analyze the co-occurrence relationships between the review data and extract related strengths and weaknesses. It can also analyze causal relationships and identify the causes of the strengths and weaknesses. In this way, by taking into account the interrelationships between the review data, the accuracy of extracting strengths and weaknesses is improved. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI or without AI.

[0047] The extraction unit can extract the review data while taking into account the attribute information of the poster of the review data. The extraction unit, for example, uses data mining technology to identify the attribute information of the poster of the review data. For example, the extraction unit analyzes the poster's age and gender to extract strengths and weaknesses. The extraction unit can also extract strengths and weaknesses while taking into account the poster's region and cultural background. The extraction unit can also extract strengths and weaknesses while referring to the poster's purchase history and usage frequency. For example, the extraction unit extracts strengths and weaknesses based on the poster's age and gender. The strengths and weaknesses can also be extracted while taking into account the region and cultural background. The strengths and weaknesses can also be extracted while referring to the purchase history and usage frequency. In this way, by taking into account the attribute information of the poster of the review data, strengths and weaknesses can be extracted with greater accuracy. Some or all of the above-described processing by the extraction unit may be performed using, for example, AI, or may be performed without using AI.

[0048] The extraction unit can weight the extraction based on the posting frequency of the review data during extraction. The extraction unit, for example, uses data mining technology to evaluate the posting frequency of the review data. For example, the extraction unit analyzes the posting frequency of the review data and weights it. The extraction unit can also extract strengths and weaknesses based on the posting frequency of the review data. For example, a high weight can be set for frequently posted review data, and strengths and weaknesses can be extracted. Alternatively, a low weight can be set for rarely posted review data, and strengths and weaknesses can be extracted. Alternatively, an appropriate weight can be set for review data posted with a moderate frequency, and strengths and weaknesses can be extracted. In this way, weighting based on the posting frequency of the review data allows important information to be preferentially extracted. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI, or may be performed without using AI.

[0049] The extraction unit can perform extraction while taking into account the geographic distribution of the review data. For example, the extraction unit uses a geographic information system (GIS) to evaluate the geographic distribution of the review data. For example, the extraction unit analyzes the geographic distribution of the review data and extracts strengths and weaknesses that reflect the characteristics of each region. The extraction unit can also extract review data that covers a wide geographical area in a balanced manner. For example, the extraction unit can preferentially extract review data that is frequently posted in a specific region. The extraction unit can also extract strengths and weaknesses by taking into account the characteristics of each region. In this way, by taking the geographic distribution of the review data into account, strengths and weaknesses that reflect the characteristics of each region can be extracted. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI or without AI.

[0050] During extraction, the extraction unit can improve the accuracy of extraction by referring to literature related to the review data. The extraction unit, for example, uses literature search technology to refer to literature related to the review data. For example, the extraction unit refers to related academic papers and research reports to extract strengths and weaknesses. The extraction unit can also refer to related industry reports and market research to extract strengths and weaknesses. The extraction unit can also refer to related news articles and blog posts to extract strengths and weaknesses. In this way, by referring to literature related to the review data, the accuracy of extracting strengths and weaknesses is improved. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI or without using AI.

[0051] The extraction unit can perform extraction while taking into consideration the market value of the review data. The extraction unit, for example, uses economic indicator analysis technology to evaluate the market value of the review data. For example, the extraction unit analyzes the market value of the review data and preferentially extracts information with high value. The extraction unit can also extract strengths and weaknesses based on the market value of the review data. For example, review data with high market value can be preferentially extracted. Review data with medium market value can also be extracted next. Review data with low market value can also be extracted last. In this way, by taking the market value of the review data into consideration, highly valuable information can be preferentially extracted. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI, or may be performed without using AI.

[0052] The providing unit can adjust the level of detail of points to be reviewed based on the analysis results of the review data when providing the points. The providing unit, for example, uses data mining technology to evaluate the analysis results of the review data. For example, the providing unit analyzes the analysis results of the review data and provides detailed review points for important analysis results. The providing unit can also provide simplified review points for general analysis results. The providing unit can also provide review points with an appropriate level of detail for analysis results with medium importance. For example, detailed review points are provided for important analysis results. Simplified review points are provided for general analysis results. Review points with an appropriate level of detail are provided for analysis results with medium importance. In this way, by adjusting the level of detail based on the analysis results of the review data, it is possible to provide review points at an appropriate level. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without using AI.

[0053] The providing unit can apply different providing algorithms depending on the category of the review data when providing the data. The providing unit, for example, uses clustering technology to identify the category of the review data. For example, the providing unit clusters the review data by category and applies a providing algorithm appropriate for each category. The providing unit can also select different providing algorithms depending on the category of the review data. For example, a providing algorithm specialized in product quality and functionality can be applied to review data about a product. A providing algorithm specialized in service response and customer satisfaction can be applied to review data about a service. A providing algorithm specialized in food taste and service speed can be applied to review data about a restaurant. In this way, by applying different providing algorithms depending on the category of the review data, the accuracy of providing data is improved. Some or all of the above-mentioned processing by the providing unit may be performed using, for example, AI, or may be performed without using AI.

[0054] The providing unit can improve the accuracy of the provision by referring to the user's past provision results when providing the results. The providing unit, for example, uses data mining technology to analyze the user's past provision results. For example, the providing unit analyzes the user's past provision results and finds common patterns. The providing unit can also adjust the provision algorithm based on the user's past provision results. For example, the providing unit adjusts the provision algorithm based on feedback provided by the user in the past to improve accuracy. The providing unit can also improve the accuracy of the provision for a specific category or topic by referring to the user's past provision results. In this way, the accuracy of the provision is improved by referring to the user's past provision results. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without AI.

[0055] The providing unit can determine the priority of points to be reviewed based on the posting date of the review data when providing the data. The providing unit, for example, uses timestamp analysis technology to evaluate the posting date of the review data. For example, the providing unit analyzes the timestamp of the review data to identify the posting date. The providing unit can also determine the priority of points to be reviewed based on the posting date of the review data. For example, the providing unit can prioritize points to be reviewed based on recently posted review data. The providing unit can also provide points to be reviewed based on current trends while referring to review data posted in the past. The providing unit can also provide points to be reviewed based on review data posted in a concentrated period of time. In this way, by determining the priority of points to be reviewed based on the posting date of the review data, the latest information can be provided preferentially. Some or all of the above-described processing by the providing unit may be performed using AI, for example, or may be performed without using AI.

[0056] The providing unit can adjust the order of points to be reviewed based on the relevance of the review data when providing the data. The providing unit, for example, uses relevance analysis technology to evaluate the relevance of the review data. For example, the providing unit analyzes the content of the review data and evaluates the relevance. The providing unit can also adjust the order of points to be reviewed based on the relevance of the review data. For example, the providing unit can provide points to be reviewed preferentially based on review data with high relevance. The providing unit can also provide points to be reviewed next based on review data with medium relevance. The providing unit can also provide points to be reviewed last based on review data with low relevance. In this way, by adjusting the order of points to be reviewed based on the relevance of the review data, important information can be provided quickly. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without using AI.

[0057] The providing unit can adjust the use of technical terms in the points to be reviewed according to the user's level of expertise when providing the review. The providing unit, for example, uses a questionnaire or past data to evaluate the user's level of expertise. For example, the providing unit analyzes the user's questionnaire responses to identify the user's level of expertise. The providing unit can also analyze the user's past data to evaluate the user's level of expertise. The providing unit adjusts the use of technical terms in the points to be reviewed according to the user's level of expertise. For example, if the user has technical expertise, the providing unit can provide detailed review points that use a lot of technical terms. If the user has general knowledge, the providing unit can provide easy-to-understand review points with less technical terms. If the user is a beginner, the providing unit can avoid technical terms and provide review points in simple language. In this way, by adjusting the use of technical terms according to the user's level of expertise, it is possible to provide review points that are easy for the user to understand. Some or all of the above-mentioned processing by the providing unit may be performed, for example, using AI or without AI.

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

[0059] When collecting review data, the collection unit can analyze the user's past review posting history and select the optimal collection method. For example, the collection unit analyzes the user's past posting frequency and content and selects the optimal collection method. The collection unit can also customize the collection method based on the user's past review posting history. For example, if the user has frequently posted reviews in the past, a simple interface can be provided to quickly collect reviews. If the user has posted detailed reviews in the past, more detailed input options can be provided to collect more in-depth feedback. If the user has posted negative reviews in the past, guidelines can be provided to encourage positive feedback. In this way, the optimal collection method can be selected by analyzing the user's past review posting history. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without AI.

[0060] When collecting review data, the collection unit can filter the review data based on the user's current areas of interest and activity status. For example, the collection unit analyzes social media posts and search history to identify the user's current areas of interest and activity status. For example, the collection unit can analyze the user's social media posts to identify topics of interest. The collection unit can also analyze the user's search history to identify products and services of current interest. The collection unit filters the review data based on the user's current areas of interest and activity status. For example, the collection unit can prioritize collection of review data related to products and services of current interest to the user. The collection unit can also collect related review data based on places recently visited by the user or services used by the user. The collection unit can also analyze the user's social media activity to collect review data related to topics of interest to the user. In this way, by filtering based on the user's current areas of interest and activity status, highly relevant review data can be collected. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0061] When collecting word-of-mouth data, the collection unit can select an appropriate collection means depending on the user's input method. For example, the collection unit analyzes the user's device or interface to identify the user's input method. For example, if the user prefers voice input, the collection unit can collect word-of-mouth data using voice recognition technology. Alternatively, if the user prefers text input, the collection unit can provide a simple text input form to collect word-of-mouth data. Alternatively, if the user provides feedback using an image, the collection unit can collect word-of-mouth data using image analysis technology. This improves user convenience by selecting the optimal collection means depending on the user's input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0062] When collecting review data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, the collection unit uses GPS data or an IP address to acquire the user's geographical location information. For example, the collection unit acquires the user's GPS data and collects review data based on the user's current location. The collection unit can also analyze the user's IP address to identify the user's geographical location information. The collection unit prioritizes collecting highly relevant review data based on the user's geographical location information. For example, the collection unit prioritizes collecting review data related to places close to the user's current location. The collection unit can also prioritize collecting review data related to places the user has visited in the past. The collection unit can also prioritize collecting review data related to places the user plans to visit in the future. In this way, by taking the user's geographical location information into account, highly relevant review data can be prioritized. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0063] When collecting review data, the collection unit can analyze the user's social media activity and collect related review data. For example, the collection unit uses social media analysis technology to analyze the user's social media activity. For example, the collection unit analyzes the content of the user's social media posts and collects related review data. The collection unit can also analyze the user's social media check-in information and collect related review data. The collection unit can also collect related review data by referring to the activities of the user's friends on social media. In this way, related review data can be efficiently collected by analyzing the user's social media activity. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

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

[0065] Step 1: The collection unit collects review data. Review data includes text, audio, and images. The collection unit can automatically collect review data through an API or use web scraping technology. It can also provide an interface that allows users to directly input review data. For example, review data can be collected using a REST API or GraphQL. Step 2: The analysis unit analyzes the review data collected by the collection unit. The analysis is performed using natural language processing techniques, including morphological analysis, grammatical analysis, and semantic analysis. For example, morphological analysis is used to calculate the frequency of word occurrence, grammatical analysis is used to analyze the structure of a sentence, and semantic analysis is used to understand the content of a sentence. Step 3: The extraction unit extracts strengths and weaknesses based on the results of the analysis by the analysis unit. Strengths and weaknesses are extracted based on positive and negative evaluations. For example, positive evaluations are extracted as strengths and negative evaluations are extracted as weaknesses. Strengths and weaknesses can also be extracted based on the frequency of evaluations. Step 4: The provision department proposes points to be reviewed based on the strengths and weaknesses extracted by the extraction department. Points to be reviewed are proposed based on areas for improvement or strengthening. For example, measures to further strengthen strengths and measures to improve weaknesses are proposed. The provision department can also display the analysis results in dashboard format and visually display them using graphs and charts.

[0066] (Example 2) A review data analysis system according to an embodiment of the present invention collects review data, analyzes it using AI, extracts strengths and weaknesses, and proposes areas to be improved. The review data analysis system collects review data, analyzes it using AI, extracts strengths and weaknesses, and proposes areas to be improved, thereby clarifying the strengths and weaknesses of the target and proposing areas to be improved. For example, the review data analysis system collects review data. For example, the review data analysis system automatically collects review data through an API. Next, the review data analysis system uses AI to analyze the collected review data. The AI ​​analyzes the review data using natural language processing technology and extracts strengths and weaknesses. For example, the AI ​​analyzes the review data and extracts positive and negative reviews. Next, the review data analysis system proposes areas to be improved based on the strengths and weaknesses extracted by the AI. For example, if "fast delivery" is listed as a strength, the manager can consider measures to further strengthen this strength. Furthermore, if "insufficient product description" is identified as a weakness, the manager can take measures to improve the product description. This allows the review data analysis system to enable managers and executives to utilize review data to improve the value of their services. For example, restaurant managers can improve their menus and services based on review data. Sellers can also improve their products and services based on review data. Furthermore, AI periodically updates the results of the review data analysis, providing managers and executives with the latest information. This allows managers and executives to always be aware of areas for improvement based on the latest review data. For example, by regularly collecting review data and providing the results of AI analysis to managers, managers can quickly take appropriate measures. In this way, by having AI analyze review data, managers and executives can understand their company's strengths and weaknesses and identify areas that need improvement. This can help improve the value of each service.

[0067] A word-of-mouth data analysis system according to an embodiment includes a collection unit, an analysis unit, an extraction unit, and a provision unit. The collection unit collects word-of-mouth data. The word-of-mouth data includes, for example, text, audio, and images, but is not limited to these examples. The collection unit automatically collects word-of-mouth data, for example, through an API. The collection unit can also collect word-of-mouth data using web scraping technology. The collection unit can also provide an interface that allows users to directly input word-of-mouth data. For example, the collection unit automatically collects word-of-mouth data through an API. The collection unit can collect word-of-mouth data using, for example, a REST API. The collection unit can also collect word-of-mouth data using GraphQL. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. The analysis unit analyzes the word-of-mouth data collected by the collection unit. The analysis is performed using, for example, natural language processing technology, but is not limited to these examples. For example, the analysis unit analyzes the word-of-mouth data using morphological analysis. The analysis unit can also analyze the word-of-mouth data using grammatical analysis. The analysis unit can also analyze the review data using semantic analysis. For example, the analysis unit can analyze the review data using morphological analysis and calculate the frequency of word occurrence. Grammatical analysis is used to analyze the structure of a sentence and understand its meaning. Semantic analysis is used to analyze the meaning of a sentence and understand its content. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. The extraction unit extracts strengths and weaknesses based on the results of the analysis by the analysis unit. Strengths and weaknesses are extracted based on, for example, positive evaluations and negative evaluations, but are not limited to such examples. For example, the extraction unit extracts positive evaluations as strengths. The extraction unit can also extract negative evaluations as weaknesses. The extraction unit can also extract strengths and weaknesses based on the frequency of evaluations. For example, the extraction unit extracts items with a high frequency of positive evaluations as strengths. Items with a high frequency of negative evaluations are extracted as weaknesses.Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. The providing unit suggests points to be reviewed based on the strengths and weaknesses extracted by the extraction unit. The points to be reviewed may be suggested based on, for example, areas for improvement or strengthening, but are not limited to such examples. For example, the providing unit suggests measures to further strengthen strengths. The providing unit may also suggest measures to improve weaknesses. The providing unit may also display the analysis results in dashboard format. For example, the providing unit visually displays the analysis results using graphs or charts. The analysis results may also be displayed in table format. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. As a result, the review data analysis system according to the embodiment can efficiently collect, analyze, extract, and provide review data, thereby clarifying the strengths and weaknesses of a target and suggesting points to be reviewed.

[0068] The collection unit can automatically collect review data through an API. The collection unit collects review data using, for example, a REST API. For example, the collection unit sends a request to a specific endpoint to obtain review data. The collection unit can also collect review data using GraphQL. For example, the collection unit sends a query to obtain the required review data. The collection unit can also perform authentication using an API key to collect review data. For example, the collection unit performs authentication using an API key to obtain review data. This automatically collecting review data through an API improves the efficiency of data collection. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0069] The analysis unit can analyze the review data using natural language processing. The analysis unit analyzes the review data using, for example, morphological analysis. For example, the analysis unit divides the review data into morphemes and calculates the frequency of occurrence of each morpheme. The analysis unit can also analyze the review data using grammatical analysis. For example, the analysis unit analyzes the structure of a sentence to understand the meaning of the sentence. The analysis unit can also analyze the review data using semantic analysis. For example, the analysis unit analyzes the meaning of a sentence to understand the content of the sentence. In this way, the use of natural language processing improves the analysis accuracy of the review data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0070] The providing unit can display the analysis results in a dashboard format. The providing unit displays the analysis results using, for example, a graph. For example, the providing unit visually displays the analysis results using a bar graph or a line graph. The providing unit can also display the analysis results using a chart. For example, the providing unit visually displays the analysis results using a pie chart or a heat map. The providing unit can also display the analysis results in a table format. For example, the providing unit summarizes the analysis results in a table and displays them visually. In this way, displaying the analysis results in a dashboard format makes it easier for the user to visually understand the results. Some or all of the above-described processing in the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0071] The providing unit can periodically update the word-of-mouth data and provide the latest information. The providing unit, for example, updates the word-of-mouth data daily. For example, the providing unit collects word-of-mouth data daily and updates the analysis results. The providing unit can also update the word-of-mouth data weekly. For example, the providing unit collects word-of-mouth data weekly and updates the analysis results. The providing unit can also update the word-of-mouth data monthly. For example, the providing unit collects word-of-mouth data monthly and updates the analysis results. By periodically updating the word-of-mouth data, it is possible to always provide review points based on the latest information. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0072] The collection unit can estimate a user's emotions and adjust the timing of collecting word-of-mouth data based on the estimated user emotions. The collection unit, for example, uses a sentiment analysis algorithm to estimate the user's emotions. For example, the collection unit analyzes the user's text data and calculates a sentiment score. The collection unit can also estimate the user's emotions using survey results. For example, the collection unit analyzes the user's survey responses and calculates a sentiment score. The collection unit adjusts the timing of collecting word-of-mouth data based on the user's emotions. For example, if the user expresses positive emotions, word-of-mouth data can be collected immediately to reflect real-time feedback. Alternatively, if the user expresses negative emotions, word-of-mouth data can be collected after a certain period of time to obtain feedback when the user's emotions have calmed down. Alternatively, if the user expresses neutral emotions, word-of-mouth data can be collected according to a regular schedule. In this way, by adjusting the collection timing according to the user's emotions, word-of-mouth data can be collected at a more appropriate time. Some or all of the above-described processing in the collection unit may be performed, for example, using AI or without AI.

[0073] When collecting review data, the collection unit can analyze the user's past review posting history and select the optimal collection method. The collection unit, for example, uses data mining technology to analyze the user's past review posting history. For example, the collection unit analyzes the user's past posting frequency and content to select the optimal collection method. The collection unit can also customize the collection method based on the user's past review posting history. For example, if the user has frequently posted reviews in the past, a simple interface can be provided to quickly collect reviews. Alternatively, if the user has posted detailed reviews in the past, more detailed input options can be provided to collect more in-depth feedback. Alternatively, if the user has posted negative reviews in the past, guidelines can be provided to encourage positive feedback. In this way, the optimal collection method can be selected by analyzing the user's past review posting history. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without AI.

[0074] When collecting review data, the collection unit can filter the review data based on the user's current areas of interest and activity status. The collection unit, for example, analyzes social media posts and search history to identify the user's current areas of interest and activity status. For example, the collection unit can analyze the user's social media posts to identify topics of interest. The collection unit can also analyze the user's search history to identify products and services of current interest. The collection unit filters the review data based on the user's current areas of interest and activity status. For example, the collection unit can prioritize collection of review data related to products and services of current interest to the user. The collection unit can also collect related review data based on places recently visited or services used by the user. The collection unit can also analyze the user's social media activity to collect review data related to topics of interest to the user. In this way, by filtering based on the user's current areas of interest and activity status, highly relevant review data can be collected. Some or all of the above-described processing by the collection unit may be performed, for example, using AI or without AI.

[0075] When collecting word-of-mouth data, the collection unit can select an appropriate collection means depending on the user's input method. The collection unit, for example, analyzes the user's device or interface to identify the user's input method. For example, if the user prefers voice input, the collection unit can collect word-of-mouth data using voice recognition technology. Alternatively, if the user prefers text input, the collection unit can provide a simple text input form to collect word-of-mouth data. Alternatively, if the user provides feedback using an image, the collection unit can collect word-of-mouth data using image analysis technology. This improves user convenience by selecting the optimal collection means depending on the user's input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0076] The collection unit can estimate a user's emotions and determine the priority of the review data to be collected based on the estimated user emotions. The collection unit, for example, uses a sentiment analysis algorithm to estimate the user's emotions. For example, the collection unit analyzes the user's text data and calculates a sentiment score. The collection unit can also estimate the user's emotions using survey results. For example, the collection unit analyzes the user's survey responses and calculates a sentiment score. The collection unit determines the priority of the review data to be collected based on the user's emotions. For example, if the user expresses strong positive emotions, the review data can be collected preferentially and reflected immediately. Also, if the user expresses strong negative emotions, the review data can be collected preferentially and countermeasures can be taken quickly. Also, if the user expresses neutral emotions, the review data can be collected according to a regular schedule. In this way, by determining the priority of the review data based on the user's emotions, important data can be collected preferentially. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without AI.

[0077] When collecting review data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. The collection unit, for example, uses GPS data or an IP address to acquire the user's geographical location information. For example, the collection unit acquires the user's GPS data and collects review data based on the user's current location. The collection unit can also analyze the user's IP address to identify the geographical location information. The collection unit prioritizes collecting highly relevant review data based on the user's geographical location information. For example, the collection unit prioritizes collecting review data related to places close to the user's current location. The collection unit can also prioritize collecting review data related to places the user has visited in the past. The collection unit can also prioritize collecting review data related to places the user plans to visit in the future. In this way, by taking the user's geographical location information into account, highly relevant review data can be prioritized. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0078] When collecting review data, the collection unit can analyze the user's social media activity and collect related review data. The collection unit, for example, uses social media analysis technology to analyze the user's social media activity. For example, the collection unit analyzes the content of the user's social media posts and collects related review data. The collection unit can also analyze the user's social media check-in information and collect related review data. The collection unit can also collect related review data by referring to the activities of the user's friends on social media. In this way, related review data can be efficiently collected by analyzing the user's social media activity. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0079] When collecting word-of-mouth data, the collection unit can customize the collection method by reflecting the user's past feedback. The collection unit, for example, uses data mining technology to reflect the user's past feedback. For example, the collection unit analyzes the user's past feedback and selects the optimal collection method. The collection unit can also customize the collection method based on the user's past feedback. For example, the collection unit can preferentially provide collection methods (audio, text, etc.) that the user has previously preferred. The collection method can also be customized based on feedback the user has previously provided. The optimal collection timing can also be determined from the user's past feedback. In this way, the optimal collection method can be provided by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0080] The analysis unit can estimate the user's emotions and adjust the presentation method of the analysis based on the estimated user's emotions. The analysis unit, for example, uses an emotion analysis algorithm to estimate the user's emotions. For example, the analysis unit analyzes the user's text data and calculates an emotion score. The analysis unit can also estimate the user's emotions using survey results. For example, the analysis unit analyzes the user's survey responses and calculates an emotion score. The analysis unit adjusts the presentation method of the analysis based on the user's emotions. For example, if the user is expressing positive emotions, the analysis results can be displayed using bright colors and positive words. If the user is expressing negative emotions, the analysis results can be displayed using subdued colors and neutral words. If the user is expressing neutral emotions, the analysis results can be displayed using normal colors and presentation methods. By adjusting the presentation method of the analysis based on the user's emotions, it is possible to provide analysis results that are easy for the user to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0081] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the review data. The analysis unit, for example, uses data mining technology to evaluate the importance of the review data. For example, the analysis unit evaluates the importance of the review data and performs a detailed analysis on data with high importance. The analysis unit can also perform a simplified analysis on data with low importance. The analysis unit can also perform an analysis with an appropriate level of detail on data with medium importance. For example, a detailed analysis is performed on review data with high importance, and specific improvements are proposed. A simplified analysis is performed on review data with low importance, and only an overview is presented. An analysis with an appropriate level of detail is performed on review data with medium importance, providing balanced information. In this way, by adjusting the level of detail of the analysis based on the importance of the review data, an appropriate level of analysis result can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0082] During analysis, the analysis unit can apply different analysis algorithms depending on the category of review data. The analysis unit, for example, uses clustering technology to identify the category of review data. For example, the analysis unit clusters the review data by category and applies an analysis algorithm appropriate for each category. The analysis unit can also select different analysis algorithms depending on the category of review data. For example, to review data about products, an analysis algorithm specialized in product quality and functionality can be applied. To review data about services, an analysis algorithm specialized in service response and customer satisfaction can be applied. To review data about restaurants, an analysis algorithm specialized in food taste and service speed can be applied. In this way, by applying different analysis algorithms depending on the category of review data, the accuracy of analysis is improved. Some or all of the above-mentioned processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0083] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, uses data mining technology to analyze the user's past analysis results. For example, the analysis unit analyzes the user's past analysis results and finds common patterns. The analysis unit can also adjust the analysis algorithm based on the user's past analysis results. For example, the analysis unit adjusts the analysis algorithm based on feedback provided by the user in the past to improve accuracy. The analysis unit can also improve the accuracy of analysis for specific categories or topics by referring to the user's past analysis results. In this way, the accuracy of the analysis is improved by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or without AI.

[0084] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. The analysis unit, for example, uses an emotion analysis algorithm to estimate the user's emotions. For example, the analysis unit analyzes the user's text data and calculates an emotion score. The analysis unit can also estimate the user's emotions using survey results. For example, the analysis unit analyzes the user's survey responses and calculates an emotion score. The analysis unit adjusts the length of the analysis based on the user's emotions. For example, if the user is in a hurry, the analysis unit can provide a short, to-the-point analysis result. If the user is relaxed, the analysis unit can provide a longer analysis result with detailed explanations. If the user is excited, the analysis unit can provide an analysis result with visually stimulating effects. By adjusting the length of the analysis based on the user's emotions, it is possible to provide an analysis result that meets the user's needs. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0085] During analysis, the analysis unit can determine the analysis priority based on the posting date of the review data. The analysis unit, for example, uses timestamp analysis technology to evaluate the posting date of the review data. For example, the analysis unit analyzes the timestamp of the review data to identify the posting date. The analysis unit can also determine the analysis priority based on the posting date of the review data. For example, the analysis unit can prioritize analysis of recently posted review data to provide the latest information. The analysis unit can also determine the analysis priority based on current trends while referring to review data posted in the past. It can also prioritize analysis of review data posted in a specific period to understand trends for that period. In this way, by determining the analysis priority based on the posting date of the review data, the latest information can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI or without AI.

[0086] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the review data. The analysis unit, for example, uses relevance analysis technology to evaluate the relevance of the review data. For example, the analysis unit analyzes the content of the review data and evaluates the relevance. The analysis unit can also adjust the order of analysis based on the relevance of the review data. For example, review data with high relevance can be analyzed preferentially to quickly provide important information. Review data with medium relevance can also be analyzed next to achieve overall balance. Review data with low relevance can also be analyzed last to provide supplemental information. In this way, by adjusting the order of analysis based on the relevance of the review data, important information can be quickly provided. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or without AI.

[0087] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. The analysis unit, for example, uses questionnaires or past data to evaluate the user's level of expertise. For example, the analysis unit can analyze the user's questionnaire responses to identify the user's level of expertise. The analysis unit can also analyze the user's past data to evaluate the user's level of expertise. The analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide detailed analysis results that use a lot of technical terms. If the user has general knowledge, the analysis unit can provide easy-to-understand analysis results with less technical terms. If the user is a beginner, the analysis unit can provide analysis results in simple language, avoiding technical terms. In this way, by adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easy for the user to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0088] The extraction unit can estimate the user's emotions and determine the priority of the strengths and weaknesses to be extracted based on the estimated user emotions. The extraction unit, for example, uses an emotion analysis algorithm to estimate the user's emotions. For example, the extraction unit can analyze the user's text data and calculate an emotion score. The extraction unit can also estimate the user's emotions using survey results. For example, the extraction unit can analyze the user's survey responses and calculate an emotion score. The extraction unit determines the priority of the strengths and weaknesses to be extracted based on the user's emotions. For example, if the user expresses positive emotions, the extraction unit can prioritize extracting strengths and highlighting positive feedback. Alternatively, if the user expresses negative emotions, the extraction unit can prioritize extracting weaknesses and highlighting areas for improvement. Alternatively, if the user expresses neutral emotions, the extraction unit can extract strengths and weaknesses in a balanced manner. As a result, by prioritizing the strengths and weaknesses based on the user's emotions, it is possible to prioritize providing information that is important to the user. Some or all of the above-described processing in the extraction unit may be performed, for example, using AI or without AI.

[0089] The extraction unit can improve the accuracy of extraction by taking into account the interrelationships between the review data during extraction. The extraction unit, for example, uses co-occurrence analysis technology to evaluate the interrelationships between the review data. For example, the extraction unit finds commonalities between the review data and more accurately extracts strengths and weaknesses. The extraction unit can also analyze the interrelationships between the review data and extract related strengths and weaknesses together. The extraction unit can also maintain consistency of the extraction results by taking into account the interrelationships between the review data. For example, the extraction unit can analyze the co-occurrence relationships between the review data and extract related strengths and weaknesses. It can also analyze causal relationships and identify the causes of the strengths and weaknesses. In this way, by taking into account the interrelationships between the review data, the accuracy of extracting strengths and weaknesses is improved. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI or without AI.

[0090] The extraction unit can extract the review data while taking into account the attribute information of the poster of the review data. The extraction unit, for example, uses data mining technology to identify the attribute information of the poster of the review data. For example, the extraction unit analyzes the poster's age and gender to extract strengths and weaknesses. The extraction unit can also extract strengths and weaknesses while taking into account the poster's region and cultural background. The extraction unit can also extract strengths and weaknesses while referring to the poster's purchase history and usage frequency. For example, the extraction unit extracts strengths and weaknesses based on the poster's age and gender. The strengths and weaknesses can also be extracted while taking into account the region and cultural background. The strengths and weaknesses can also be extracted while referring to the purchase history and usage frequency. In this way, by taking into account the attribute information of the poster of the review data, strengths and weaknesses can be extracted with greater accuracy. Some or all of the above-described processing by the extraction unit may be performed using, for example, AI, or may be performed without using AI.

[0091] The extraction unit can weight the extraction based on the posting frequency of the review data during extraction. The extraction unit, for example, uses data mining technology to evaluate the posting frequency of the review data. For example, the extraction unit analyzes the posting frequency of the review data and weights it. The extraction unit can also extract strengths and weaknesses based on the posting frequency of the review data. For example, a high weight can be set for frequently posted review data, and strengths and weaknesses can be extracted. Alternatively, a low weight can be set for rarely posted review data, and strengths and weaknesses can be extracted. Alternatively, an appropriate weight can be set for review data posted with a moderate frequency, and strengths and weaknesses can be extracted. In this way, weighting based on the posting frequency of the review data allows important information to be preferentially extracted. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI, or may be performed without using AI.

[0092] The extraction unit can estimate the user's emotions and adjust the display method of the extracted strengths and weaknesses based on the estimated user emotions. The extraction unit, for example, uses an emotion analysis algorithm to estimate the user's emotions. For example, the extraction unit analyzes the user's text data and calculates an emotion score. The extraction unit can also estimate the user's emotions using survey results. For example, the extraction unit analyzes the user's survey responses and calculates an emotion score. The extraction unit adjusts the display method of the extracted strengths and weaknesses based on the user's emotions. For example, if the user is expressing positive emotions, a display method that highlights strengths can be adopted. Alternatively, if the user is expressing negative emotions, a display method that highlights weaknesses can be adopted. Alternatively, if the user is expressing neutral emotions, a display method that highlights strengths and weaknesses can be adopted. In this way, by adjusting the display method based on the user's emotions, it is possible to provide information that is easy for the user to understand. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI.

[0093] The extraction unit can perform extraction while taking into account the geographic distribution of the review data. For example, the extraction unit uses a geographic information system (GIS) to evaluate the geographic distribution of the review data. For example, the extraction unit analyzes the geographic distribution of the review data and extracts strengths and weaknesses that reflect the characteristics of each region. The extraction unit can also extract review data that covers a wide geographical area in a balanced manner. For example, the extraction unit can preferentially extract review data that is frequently posted in a specific region. The extraction unit can also extract strengths and weaknesses by taking into account the characteristics of each region. In this way, by taking the geographic distribution of the review data into account, strengths and weaknesses that reflect the characteristics of each region can be extracted. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI or without AI.

[0094] During extraction, the extraction unit can improve the accuracy of extraction by referring to literature related to the review data. The extraction unit, for example, uses literature search technology to refer to literature related to the review data. For example, the extraction unit refers to related academic papers and research reports to extract strengths and weaknesses. The extraction unit can also refer to related industry reports and market research to extract strengths and weaknesses. The extraction unit can also refer to related news articles and blog posts to extract strengths and weaknesses. In this way, by referring to literature related to the review data, the accuracy of extracting strengths and weaknesses is improved. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI or without using AI.

[0095] The extraction unit can perform extraction while taking into consideration the market value of the review data. The extraction unit, for example, uses economic indicator analysis technology to evaluate the market value of the review data. For example, the extraction unit analyzes the market value of the review data and preferentially extracts information with high value. The extraction unit can also extract strengths and weaknesses based on the market value of the review data. For example, review data with high market value can be preferentially extracted. Review data with medium market value can also be extracted next. Review data with low market value can also be extracted last. In this way, by taking the market value of the review data into consideration, highly valuable information can be preferentially extracted. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using AI, or may be performed without using AI.

[0096] The providing unit can estimate the user's emotions and adjust the display method of the points to be reviewed based on the estimated user emotions. The providing unit, for example, uses an emotion analysis algorithm to estimate the user's emotions. For example, the providing unit analyzes the user's text data and calculates an emotion score. The providing unit can also estimate the user's emotions using survey results. For example, the providing unit analyzes the user's survey responses and calculates an emotion score. The providing unit adjusts the display method of the points to be reviewed based on the user's emotions. For example, if the user is expressing positive emotions, a display method that emphasizes strengths can be adopted. Also, if the user is expressing negative emotions, a display method that emphasizes weaknesses can be adopted. Also, if the user is expressing neutral emotions, a display method that emphasizes strengths and weaknesses can be adopted. In this way, by adjusting the display method based on the user's emotions, it is possible to provide review points that are easy for the user to understand. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without AI.

[0097] The providing unit can adjust the level of detail of points to be reviewed based on the analysis results of the review data when providing the points. The providing unit, for example, uses data mining technology to evaluate the analysis results of the review data. For example, the providing unit analyzes the analysis results of the review data and provides detailed review points for important analysis results. The providing unit can also provide simplified review points for general analysis results. The providing unit can also provide review points with an appropriate level of detail for analysis results with medium importance. For example, detailed review points are provided for important analysis results. Simplified review points are provided for general analysis results. Review points with an appropriate level of detail are provided for analysis results with medium importance. In this way, by adjusting the level of detail based on the analysis results of the review data, it is possible to provide review points at an appropriate level. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without using AI.

[0098] The providing unit can apply different providing algorithms depending on the category of the review data when providing the data. The providing unit, for example, uses clustering technology to identify the category of the review data. For example, the providing unit clusters the review data by category and applies a providing algorithm appropriate for each category. The providing unit can also select different providing algorithms depending on the category of the review data. For example, a providing algorithm specialized in product quality and functionality can be applied to review data about a product. A providing algorithm specialized in service response and customer satisfaction can be applied to review data about a service. A providing algorithm specialized in food taste and service speed can be applied to review data about a restaurant. In this way, by applying different providing algorithms depending on the category of the review data, the accuracy of providing data is improved. Some or all of the above-mentioned processing by the providing unit may be performed using, for example, AI, or may be performed without using AI.

[0099] The providing unit can improve the accuracy of the provision by referring to the user's past provision results when providing the results. The providing unit, for example, uses data mining technology to analyze the user's past provision results. For example, the providing unit analyzes the user's past provision results and finds common patterns. The providing unit can also adjust the provision algorithm based on the user's past provision results. For example, the providing unit adjusts the provision algorithm based on feedback provided by the user in the past to improve accuracy. The providing unit can also improve the accuracy of the provision for a specific category or topic by referring to the user's past provision results. In this way, the accuracy of the provision is improved by referring to the user's past provision results. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without AI.

[0100] The providing unit can estimate the user's emotions and determine the priority of points to be reviewed based on the estimated user emotions. The providing unit, for example, uses an emotion analysis algorithm to estimate the user's emotions. For example, the providing unit analyzes the user's text data and calculates an emotion score. The providing unit can also estimate the user's emotions using survey results. For example, the providing unit analyzes the user's survey responses and calculates an emotion score. The providing unit determines the priority of points to be reviewed based on the user's emotions. For example, if the user is expressing positive emotions, the strengths can be prioritized. Also, if the user is expressing negative emotions, the weaknesses can be prioritized. Also, if the user is expressing neutral emotions, the strengths and weaknesses can be reviewed in a balanced manner. In this way, by determining the priority of points to be reviewed based on the user's emotions, important information can be provided preferentially. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI.

[0101] The providing unit can determine the priority of points to be reviewed based on the posting date of the review data when providing the data. The providing unit, for example, uses timestamp analysis technology to evaluate the posting date of the review data. For example, the providing unit analyzes the timestamp of the review data to identify the posting date. The providing unit can also determine the priority of points to be reviewed based on the posting date of the review data. For example, the providing unit can prioritize points to be reviewed based on recently posted review data. The providing unit can also provide points to be reviewed based on current trends while referring to review data posted in the past. The providing unit can also provide points to be reviewed based on review data posted in a concentrated period of time. In this way, by determining the priority of points to be reviewed based on the posting date of the review data, the latest information can be provided preferentially. Some or all of the above-described processing by the providing unit may be performed using AI, for example, or may be performed without using AI.

[0102] The providing unit can adjust the order of points to be reviewed based on the relevance of the review data when providing the data. The providing unit, for example, uses relevance analysis technology to evaluate the relevance of the review data. For example, the providing unit analyzes the content of the review data and evaluates the relevance. The providing unit can also adjust the order of points to be reviewed based on the relevance of the review data. For example, the providing unit can provide points to be reviewed preferentially based on review data with high relevance. The providing unit can also provide points to be reviewed next based on review data with medium relevance. The providing unit can also provide points to be reviewed last based on review data with low relevance. In this way, by adjusting the order of points to be reviewed based on the relevance of the review data, important information can be provided quickly. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without using AI.

[0103] The providing unit can adjust the use of technical terms in the points to be reviewed according to the user's level of expertise when providing the review. The providing unit, for example, uses a questionnaire or past data to evaluate the user's level of expertise. For example, the providing unit analyzes the user's questionnaire responses to identify the user's level of expertise. The providing unit can also analyze the user's past data to evaluate the user's level of expertise. The providing unit adjusts the use of technical terms in the points to be reviewed according to the user's level of expertise. For example, if the user has technical expertise, the providing unit can provide detailed review points that use a lot of technical terms. If the user has general knowledge, the providing unit can provide easy-to-understand review points with less technical terms. If the user is a beginner, the providing unit can avoid technical terms and provide review points in simple language. In this way, by adjusting the use of technical terms according to the user's level of expertise, it is possible to provide review points that are easy for the user to understand. Some or all of the above-mentioned processing by the providing unit may be performed, for example, using AI or without AI. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, extraction unit, and provision 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 word-of-mouth data using the communication I / F 44 of the smart device 14, and the collected word-of-mouth data is analyzed by the specific processing unit 290 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 analyzes the collected word-of-mouth data. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and extracts strengths and weaknesses based on the analysis results. The provision unit is realized, for example, by the control unit 46A of the smart device 14 and suggests points to be reviewed based on the extracted strengths and weaknesses. === Hard Collateral 1-2 === Each of the multiple elements including the collection unit, analysis unit, extraction unit, and provision 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 word-of-mouth data using the communication I / F 44 of the smart glasses 214, and the collected word-of-mouth data is analyzed by the specific processing unit 290 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 analyzes the collected word-of-mouth data. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and extracts strengths and weaknesses based on the analysis results. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214 and suggests points to be reviewed based on the extracted strengths and weaknesses. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, extraction unit, and provision 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 word-of-mouth data using the communication I / F 44 of the headset type terminal 314, and the collected word-of-mouth data is analyzed by the specific processing unit 290 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 analyzes the collected word-of-mouth data. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and extracts strengths and weaknesses based on the analysis results. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314, and suggests points to be reviewed based on the extracted strengths and weaknesses. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, extraction unit, and provision 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 word-of-mouth data using the communication I / F 44 of the robot 414, and the collected word-of-mouth data is analyzed by the specific processing unit 290 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 analyzes the collected word-of-mouth data. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and extracts strengths and weaknesses based on the analysis results. The provision unit is realized, for example, by the control unit 46A of the robot 414, and suggests points to be reviewed based on the extracted strengths and weaknesses.

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

[0105] When collecting review data, the collection unit can analyze the user's past review posting history and select the optimal collection method. For example, the collection unit analyzes the user's past posting frequency and content and selects the optimal collection method. The collection unit can also customize the collection method based on the user's past review posting history. For example, if the user has frequently posted reviews in the past, a simple interface can be provided to quickly collect reviews. If the user has posted detailed reviews in the past, more detailed input options can be provided to collect more in-depth feedback. If the user has posted negative reviews in the past, guidelines can be provided to encourage positive feedback. In this way, the optimal collection method can be selected by analyzing the user's past review posting history. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without AI.

[0106] When collecting review data, the collection unit can filter the review data based on the user's current areas of interest and activity status. For example, the collection unit analyzes social media posts and search history to identify the user's current areas of interest and activity status. For example, the collection unit can analyze the user's social media posts to identify topics of interest. The collection unit can also analyze the user's search history to identify products and services of current interest. The collection unit filters the review data based on the user's current areas of interest and activity status. For example, the collection unit can prioritize collection of review data related to products and services of current interest to the user. The collection unit can also collect related review data based on places recently visited by the user or services used by the user. The collection unit can also analyze the user's social media activity to collect review data related to topics of interest to the user. In this way, by filtering based on the user's current areas of interest and activity status, highly relevant review data can be collected. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0107] When collecting word-of-mouth data, the collection unit can select an appropriate collection means depending on the user's input method. For example, the collection unit analyzes the user's device or interface to identify the user's input method. For example, if the user prefers voice input, the collection unit can collect word-of-mouth data using voice recognition technology. Alternatively, if the user prefers text input, the collection unit can provide a simple text input form to collect word-of-mouth data. Alternatively, if the user provides feedback using an image, the collection unit can collect word-of-mouth data using image analysis technology. This improves user convenience by selecting the optimal collection means depending on the user's input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0108] When collecting review data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, the collection unit uses GPS data or an IP address to acquire the user's geographical location information. For example, the collection unit acquires the user's GPS data and collects review data based on the user's current location. The collection unit can also analyze the user's IP address to identify the user's geographical location information. The collection unit prioritizes collecting highly relevant review data based on the user's geographical location information. For example, the collection unit prioritizes collecting review data related to places close to the user's current location. The collection unit can also prioritize collecting review data related to places the user has visited in the past. The collection unit can also prioritize collecting review data related to places the user plans to visit in the future. In this way, by taking the user's geographical location information into account, highly relevant review data can be prioritized. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0109] When collecting review data, the collection unit can analyze the user's social media activity and collect related review data. For example, the collection unit uses social media analysis technology to analyze the user's social media activity. For example, the collection unit analyzes the content of the user's social media posts and collects related review data. The collection unit can also analyze the user's social media check-in information and collect related review data. The collection unit can also collect related review data by referring to the activities of the user's friends on social media. In this way, related review data can be efficiently collected by analyzing the user's social media activity. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0110] The collection unit can estimate a user's emotions and adjust the timing of collecting word-of-mouth data based on the estimated user emotions. For example, the collection unit uses an emotion analysis algorithm to estimate a user's emotions. For example, the collection unit analyzes the user's text data and calculates an emotion score. The collection unit can also estimate a user's emotions using survey results. For example, the collection unit analyzes the user's survey responses and calculates an emotion score. The collection unit adjusts the timing of collecting word-of-mouth data based on the user's emotions. For example, if the user expresses positive emotions, word-of-mouth data can be collected immediately to reflect real-time feedback. Alternatively, if the user expresses negative emotions, word-of-mouth data can be collected after a certain period of time to obtain feedback when the user's emotions have calmed down. Alternatively, if the user expresses neutral emotions, word-of-mouth data can be collected according to a regular schedule. In this way, by adjusting the collection timing according to the user's emotions, word-of-mouth data can be collected at a more appropriate time. Some or all of the above-described processing in the collection unit may be performed, for example, using AI or without AI.

[0111] The collection unit can estimate a user's emotions and prioritize the review data to be collected based on the estimated user emotions. For example, the collection unit uses a sentiment analysis algorithm to estimate the user's emotions. For example, the collection unit analyzes the user's text data and calculates a sentiment score. The collection unit can also estimate the user's emotions using survey results. For example, the collection unit analyzes the user's survey responses and calculates a sentiment score. The collection unit prioritizes the review data to be collected based on the user's emotions. For example, if the user expresses strong positive emotions, the review data can be collected preferentially and reflected immediately. Also, if the user expresses strong negative emotions, the review data can be collected preferentially and countermeasures can be taken quickly. Also, if the user expresses neutral emotions, the review data can be collected according to a regular schedule. In this way, by prioritizing the review data based on the user's emotions, important data can be collected preferentially. Some or all of the above-described processing in the collection unit may be performed using, for example, AI or without AI.

[0112] The analysis unit can estimate the user's emotions and adjust the presentation method of the analysis based on the estimated user's emotions. For example, the analysis unit uses an emotion analysis algorithm to estimate the user's emotions. For example, the analysis unit analyzes the user's text data and calculates an emotion score. The analysis unit can also estimate the user's emotions using survey results. For example, the analysis unit analyzes the user's survey responses and calculates an emotion score. The analysis unit adjusts the presentation method of the analysis based on the user's emotions. For example, if the user is expressing positive emotions, the analysis results can be displayed using bright colors and positive words. If the user is expressing negative emotions, the analysis results can be displayed using subdued colors and neutral words. If the user is expressing neutral emotions, the analysis results can be displayed using normal colors and presentation methods. By adjusting the presentation method of the analysis based on the user's emotions, it is possible to provide analysis results that are easy for the user to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0113] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, the analysis unit uses an emotion analysis algorithm to estimate the user's emotions. For example, the analysis unit analyzes the user's text data and calculates an emotion score. The analysis unit can also estimate the user's emotions using survey results. For example, the analysis unit analyzes the user's survey responses and calculates an emotion score. The analysis unit adjusts the length of the analysis based on the user's emotions. For example, if the user is in a hurry, the analysis unit can provide a short, to-the-point analysis result. If the user is relaxed, the analysis unit can provide a longer analysis result with detailed explanations. If the user is excited, the analysis unit can provide an analysis result with visually stimulating effects. In this way, by adjusting the length of the analysis based on the user's emotions, it is possible to provide an analysis result that meets the user's needs. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0114] The providing unit can estimate the user's emotions and adjust the display method of the points to be reviewed based on the estimated user emotions. For example, the providing unit uses an emotion analysis algorithm to estimate the user's emotions. For example, the providing unit analyzes the user's text data and calculates an emotion score. The providing unit can also estimate the user's emotions using survey results. For example, the providing unit analyzes the user's survey responses and calculates an emotion score. The providing unit adjusts the display method of the points to be reviewed based on the user's emotions. For example, if the user is expressing positive emotions, a display method that emphasizes strengths can be adopted. Also, if the user is expressing negative emotions, a display method that emphasizes weaknesses can be adopted. Also, if the user is expressing neutral emotions, a display method that emphasizes strengths and weaknesses can be adopted. In this way, by adjusting the display method based on the user's emotions, it is possible to provide review points that are easy for the user to understand. Some or all of the above-mentioned processing by the providing unit may be performed using, for example, AI, or may be performed without using AI.

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

[0116] Step 1: The collection unit collects review data. Review data includes text, audio, and images. The collection unit can automatically collect review data through an API or use web scraping technology. It can also provide an interface that allows users to directly input review data. For example, review data can be collected using a REST API or GraphQL. Step 2: The analysis unit analyzes the review data collected by the collection unit. The analysis is performed using natural language processing techniques, including morphological analysis, grammatical analysis, and semantic analysis. For example, morphological analysis is used to calculate the frequency of word occurrence, grammatical analysis is used to analyze the structure of a sentence, and semantic analysis is used to understand the content of a sentence. Step 3: The extraction unit extracts strengths and weaknesses based on the results of the analysis by the analysis unit. Strengths and weaknesses are extracted based on positive and negative evaluations. For example, positive evaluations are extracted as strengths and negative evaluations are extracted as weaknesses. Strengths and weaknesses can also be extracted based on the frequency of evaluations. Step 4: The provision department proposes points to be reviewed based on the strengths and weaknesses extracted by the extraction department. Points to be reviewed are proposed based on areas for improvement or strengthening. For example, measures to further strengthen strengths and measures to improve weaknesses are proposed. The provision department can also display the analysis results in dashboard format and visually display them using graphs and charts.

[0117] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0118] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

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

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

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

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0131] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0135] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

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

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

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

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0151] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

[0154] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0161] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0162] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0163] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0164] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0165] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0166] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0168] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0170] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0171] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0172] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0173] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0174] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the 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.

[0175] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0176] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0177] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0178] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0179] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0180] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0181] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0182] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0183] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0184] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0185] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0186] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0187] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0188] [Explanation of symbols]

[0189] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects word-of-mouth data; an analysis unit that analyzes the word-of-mouth data collected by the collection unit; an extraction unit that extracts strengths and weaknesses based on the results of the analysis by the analysis unit; a providing unit that suggests points to be reviewed based on the strengths and weaknesses extracted by the extracting unit; A system characterized by:

2. The collecting unit Automatically collect review data through APIs 2. The system of claim 1.

3. The analysis unit Analyzing customer reviews using natural language processing 2. The system of claim 1.

4. The providing unit Displaying analysis results in dashboard format 2. The system of claim 1.

5. The providing unit Regularly update your review data to provide the latest information 2. The system of claim 1.

6. The collecting unit To provide a method for estimating user emotions and adjusting the timing of collecting word-of-mouth data based on the estimated user emotions.

2. The system of claim 1.

7. The collecting unit When collecting review data, analyze users' past review posting history and select the appropriate collection method.

2. The system of claim 1.

8. The collecting unit Filtering review data as it is collected based on users' current interests and activities 2. The system of claim 1.

Images