System

Abstract

To provide a system according to an embodiment that efficiently extracts a negative evaluation from word-of-mouth data, and organizes the negative evaluation to provide.SOLUTION: A system according to an embodiment comprises: a collection unit; an analysis unit; a classification unit; and a providing unit. The collection unit is configured to collect word-of-mouth data. The analysis unit is configured to analyze the word-of-mouth data collected by the collection unit, and extract a negative evaluation from the word-of-mouth data. The classification unit is configured to classify and organize the negative evaluation extracted by the analysis unit. The providing unit is configured to provide a user with information organized by the classification unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to efficiently extract and organize negative reviews from word-of-mouth data.

[0005] The system according to the embodiment aims to efficiently extract negative reviews from word-of-mouth data, organize them, and provide them. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a classification 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 and extracts negative reviews. The classification unit classifies and organizes the negative reviews extracted by the analysis unit. The provision unit provides the information organized by the classification unit to a user. Effect of the Invention

[0007] The system according to the embodiment can efficiently extract negative reviews from word-of-mouth data, organize them, and provide them. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The system according to the embodiment of the present invention uses a generation AI to analyze the word-of-mouth data of a product and extracts the reason why the product was not so good after use. This system operates when the user inputs an instruction to the generation AI, such as "Tell me the reason why people thought the product was not so good after use." The generation AI analyzes the input instruction and collects the word-of-mouth data of the product. For example, the generation AI collects word-of-mouth data from word-of-mouth sites and review sites on the Internet and stores it in a database. The generation AI then analyzes the collected word-of-mouth data and identifies the reason why the user thought the product was not so good. The generation AI extracts negative evaluations and dissatisfaction points from the word-of-mouth data and classifies and organizes them. For example, reasons such as "poor usability," "no effect felt," and "high price" are identified. Finally, the generation AI provides the identified "reason why the product was not so good" to the user. This allows the user to efficiently grasp the evaluation of the product without having to visually inspect each word-of-mouth. In addition, since the generation AI automatically analyzes the word-of-mouth data, it is possible to significantly reduce time and effort. This allows the system to efficiently allow the user to select products and consider improvements.

[0029] The system according to the embodiment includes a collection unit, an analysis unit, a classification unit, and a provision unit. The collection unit collects word-of-mouth data using a generation AI. The collection unit can collect word-of-mouth data from, for example, word-of-mouth sites and review sites on the Internet. The collection unit can use the generation AI to filter the word-of-mouth data based on, for example, specific keywords or phrases, and collect highly relevant data. The analysis unit analyzes the word-of-mouth data collected by the collection unit and extracts negative evaluations. The analysis unit can use the generation AI to analyze the word-of-mouth data using, for example, natural language processing technology, and extract negative evaluations and dissatisfaction points. The classification unit classifies and organizes the negative evaluations extracted by the analysis unit. The classification unit can use the generation AI to classify and organize the negative evaluations based on reasons such as "poor usability," "no effect felt," and "high price." The provision unit provides the user with the information organized by the classification unit. The provision unit can use the generation AI to provide information in, for example, text format, graphs, charts, etc. This allows the system to efficiently collect, analyze, classify, and provide word-of-mouth data.

[0030] The collection unit collects word-of-mouth data using the generation AI. Specifically, the collection unit can automatically collect word-of-mouth data from word-of-mouth and review sites on the Internet. The generation AI uses web scraping technology to extract text data from specified websites and store it in a database. In addition, the generation AI can filter word-of-mouth data based on specific keywords and phrases to collect only highly relevant data. For example, keywords such as "ease of use," "effectiveness," and "price" are set, and word-of-mouth data containing these keywords is preferentially collected. In addition, the generation AI also has a filtering function that removes irrelevant information such as spam and advertisements to eliminate duplication of collected data and maintain data quality. This allows the collection unit to collect word-of-mouth data efficiently and with high accuracy and provide it to the analysis unit. In addition, the collection unit can update the collected data in real time and always keep the latest word-of-mouth information. This can improve the freshness and reliability of data throughout the system.

[0031] The analysis unit analyzes the word-of-mouth data collected by the collection unit and extracts negative evaluations. Specifically, the analysis unit uses the generation AI to analyze the word-of-mouth data using natural language processing technology. The generation AI performs sentiment analysis of the text and can automatically classify evaluations into positive, negative, and neutral. For example, it extracts text containing negative expressions such as "difficult to use," "ineffective," and "too expensive" from the word-of-mouth data. In addition, the generation AI analyzes the co-occurrence of words and sentence structure to understand the context, achieving more accurate sentiment analysis. Furthermore, the analysis unit can analyze the extracted negative evaluations in detail and identify specific dissatisfaction and problems. For example, if there are many evaluations that are "difficult to use," it extracts detailed problems such as "complex interface" and "unintuitive operation" as specific reasons. This allows the analysis unit to efficiently extract useful information from the collected word-of-mouth data and provide it to the classification unit.

[0032] The classification unit classifies and organizes the negative evaluations extracted by the analysis unit. Specifically, the classification unit uses the generation AI to classify the negative evaluations based on reasons such as "poor usability," "no effect felt," and "high price." The generation AI can automatically assign each evaluation to an appropriate category using a text classification algorithm. For example, an evaluation that is "difficult to use" is classified as "poor usability," and an evaluation that is "ineffective" is classified as "no effect felt." In addition, even if multiple evaluations are included at the same time, the generation AI can appropriately divide each evaluation and classify them into multiple categories. Furthermore, the classification unit can organize the classified evaluations and perform statistical information and trend analysis. For example, the number of evaluations in each category during a specific period is tallied to determine which problems are most frequently pointed out. In addition, the classification unit can analyze fluctuations in evaluations over time and evaluate the effectiveness of improvements. This allows the classification unit to efficiently classify and organize negative evaluations and provide them to the provision unit.

[0033] The providing unit provides the information organized by the classification unit to the user. Specifically, the providing unit can use the generating AI to provide information in text format, graphs, charts, etc. The generating AI can display information in the optimal format according to the needs of the user. For example, the statistical information of negative evaluations can be visually displayed in graphs and charts, allowing the user to grasp the trend of the problem at a glance. It can also generate detailed text reports to detail the evaluation contents and specific problems in each category. Furthermore, the providing unit has a filtering function that provides information limited to a specific category or period that the user is interested in. For example, it is possible to display only evaluations on a specific product or service, or to analyze fluctuations in evaluations over a specific period. This allows the providing unit to efficiently provide the information the user needs and assist in identifying problems and planning improvement measures. Furthermore, the providing unit can collect feedback from users and continuously improve the accuracy and usefulness of the information provided. This allows the providing unit to provide high-quality information to users and improve the value of the entire system.

[0034] The collection unit can collect word-of-mouth data from word-of-mouth sites or review sites on the Internet. The collection unit, for example, collects word-of-mouth data from word-of-mouth sites and review sites on the Internet. The collection unit can use the generation AI to filter the word-of-mouth data based on, for example, specific keywords or phrases, and collect highly relevant data. For example, in order to collect word-of-mouth data for a specific product, the collection unit inputs a prompt to the generation AI saying, "Please collect word-of-mouth data for this product." The generation AI collects related word-of-mouth data from word-of-mouth sites and review sites on the Internet, and stores it in a database. This allows the collection unit to obtain a wide range of word-of-mouth data.

[0035] The analysis unit can extract negative evaluations or points of dissatisfaction from the word-of-mouth data. The analysis unit, for example, extracts negative evaluations and points of dissatisfaction from the word-of-mouth data. The analysis unit can use the generation AI, for example, natural language processing technology, to analyze the word-of-mouth data and extract negative evaluations and points of dissatisfaction. For example, the analysis unit extracts negative evaluations such as "poor usability," "no effect felt," and "expensive" from the word-of-mouth data. The generation AI can detect specific keywords and phrases from the word-of-mouth data and extract negative evaluations based on them. This allows the analysis unit to clarify areas for improvement of the product.

[0036] The classification unit can classify and organize the extracted negative evaluations into at least one of the following reasons: "poor usability," "no effect felt," and "high price." The classification unit, for example, classifies and organizes the extracted negative evaluations into at least one of the following reasons: "poor usability," "no effect felt," and "high price." The classification unit can use the generation AI to classify and organize the negative evaluations, for example, based on specific keywords or phrases. For example, the classification unit classifies and organizes the negative evaluations from the word-of-mouth data based on reasons such as "poor usability," "no effect felt," and "high price." The generation AI can detect specific keywords or phrases from the word-of-mouth data and classify and organize the negative evaluations based on them. This allows the classification unit to make it easier for users to understand the content of the evaluations.

[0037] The providing unit can provide the classified and organized information to the user in a text format, graph, or chart. The providing unit, for example, provides the classified and organized information to the user in a text format, graph, chart, or the like. The providing unit can provide information based on a specific format, for example, using a generating AI. For example, the providing unit can provide the classified and organized information in a text format. The providing unit can also provide the classified and organized information in a graph or chart format. For example, the providing unit can display the percentage of negative evaluations in a bar graph or pie chart. This allows the providing unit to allow the user to intuitively understand the content of the evaluation.

[0038] The collection unit can analyze the user's past search history at the time of collection and select the optimal collection method. For example, the collection unit can analyze the user's past search history at the time of collection and select the optimal collection method. The collection unit can use the generation AI to preferentially collect related word-of-mouth data, for example, based on keywords or phrases that the user has searched in the past. For example, the collection unit can preferentially collect specific sites and reviews from the user's past search history. The collection unit can also preferentially collect word-of-mouth data of products that the user has given high ratings in the past. This enables the collection unit to collect data efficiently.

[0039] The collection unit can filter based on the user's current field of interest at the time of collection. For example, the collection unit can filter based on the user's current field of interest at the time of collection. The collection unit can use the generation AI to preferentially collect, for example, word-of-mouth data of products in which the user is currently interested. For example, the collection unit can filter and collect word-of-mouth data related to products in a category recently searched by the user. The collection unit can also preferentially collect word-of-mouth data of a specific brand or manufacturer in which the user is interested. This allows the collection unit to collect highly relevant data.

[0040] The collection unit can preferentially collect highly relevant word-of-mouth data in consideration of the geographical location information of the user at the time of collection. For example, the collection unit preferentially collects highly relevant word-of-mouth data in consideration of the geographical location information of the user at the time of collection. The collection unit can preferentially collect, for example, word-of-mouth data of stores and services close to the user's current location using the generation AI. For example, the collection unit can preferentially collect word-of-mouth data related to places the user has visited in the past. The collection unit can also preferentially collect word-of-mouth data related to places the user plans to visit in the future. This allows the collection unit to efficiently collect word-of-mouth data related to the area.

[0041] The collection unit can analyze the user's social media activities at the time of collection and collect related word-of-mouth data. For example, the collection unit can analyze the user's social media activities at the time of collection and collect related word-of-mouth data. The collection unit can use the generation AI to preferentially collect word-of-mouth data of products and services mentioned by the user on social media, for example. For example, the collection unit can preferentially collect word-of-mouth data posted by the user's followers and friends. The collection unit can also preferentially collect word-of-mouth data of products that are hot topics in groups and communities in which the user participates. This allows the collection unit to collect highly relevant word-of-mouth data.

[0042] The analysis unit can adjust the level of detail of the analysis based on the importance of the word-of-mouth data during analysis. The analysis unit, for example, adjusts the level of detail of the analysis based on the importance of the word-of-mouth data during analysis. The analysis unit can use the generation AI to evaluate the importance based on, for example, the number of stars in the evaluation of the word-of-mouth data or the content of the comments, and adjust the level of detail of the analysis based on that. For example, the analysis unit performs a detailed analysis on word-of-mouth data with high importance. In addition, the analysis unit can perform a simplified analysis on word-of-mouth data with low importance. Furthermore, the analysis unit can perform an analysis at an appropriate level of detail on word-of-mouth data with medium importance. This enables the analysis unit to perform efficient analysis.

[0043] The analysis unit can apply different analysis algorithms depending on the category of the word-of-mouth data during analysis. The analysis unit can, for example, apply different analysis algorithms depending on the category of the word-of-mouth data during analysis. The analysis unit can use the generation AI to apply, for example, an optimal analysis algorithm for each product category. For example, the analysis unit can apply different analysis algorithms for each service category. The analysis unit can also apply different analysis algorithms for each region. This allows the analysis unit to apply the optimal analysis algorithm depending on the category of the word-of-mouth data, thereby improving the analysis accuracy.

[0044] The analysis unit can determine the priority of analysis based on the time of submission of the review data during analysis. The analysis unit, for example, determines the priority of analysis based on the time of submission of the review data during analysis. The analysis unit can use the generation AI to evaluate the time of submission based on, for example, the posting date and time or the latest data, and determine the priority of analysis based on that. For example, the analysis unit prioritizes analysis of the latest review data. In addition, the analysis unit can appropriately analyze past review data. Furthermore, the analysis unit can prioritize analysis of review data that was submitted in a concentrated manner during a specific period. This allows the analysis unit to prioritize analysis of the latest data.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the word-of-mouth data during analysis. The analysis unit can adjust the order of analysis based on the relevance of the word-of-mouth data during analysis, for example. The analysis unit can use the generation AI to evaluate the relevance based on, for example, common keywords or related topics, and adjust the order of analysis based on the evaluation. For example, the analysis unit preferentially analyzes word-of-mouth data with high relevance. Also, the analysis unit can analyze word-of-mouth data with medium relevance next. Furthermore, the analysis unit can analyze word-of-mouth data with low relevance last. This enables the analysis unit to perform efficient analysis.

[0046] The classification unit can improve the accuracy of classification by taking into account the interrelationships of the word-of-mouth data during classification. The classification unit can improve the accuracy of classification by taking into account the interrelationships of the word-of-mouth data during classification, for example. The classification unit can use a generation AI to, for example, extract commonalities in the word-of-mouth data and classify it by taking into account the interrelationships. For example, the classification unit can analyze the correlations of the word-of-mouth data and perform classification with high accuracy. The classification unit can also evaluate the relevance of the word-of-mouth data and perform optimal classification. This enables the classification unit to perform classification with high accuracy.

[0047] The classification unit can perform classification taking into consideration attribute information of the submitter of the word-of-mouth data when classifying. For example, the classification unit performs classification taking into consideration attribute information of the submitter of the word-of-mouth data when classifying. The classification unit can use the generation AI to classify the word-of-mouth data based on, for example, the age or gender of the submitter. For example, the classification unit can classify the word-of-mouth data based on the region or nationality of the submitter. The classification unit can also classify the word-of-mouth data based on the purchase history or usage history of the submitter. This enables the classification unit to perform more detailed classification.

[0048] The classification unit can perform classification taking into consideration the geographical distribution of the word-of-mouth data when classifying. For example, the classification unit performs classification taking into consideration the geographical distribution of the word-of-mouth data when classifying. The classification unit can use the generation AI to classify the word-of-mouth data by region, for example, and extract region-specific evaluations. For example, the classification unit can classify the word-of-mouth data by country, and extract country-specific evaluations. The classification unit can also classify the word-of-mouth data by city, and extract city-specific evaluations. This allows the classification unit to extract region-specific evaluations.

[0049] The classification unit can improve the accuracy of classification by referring to related literature of the word-of-mouth data during classification. The classification unit can, for example, improve the accuracy of classification by referring to related literature of the word-of-mouth data during classification. The classification unit can use the generation AI to, for example, refer to related literature and set classification criteria for the word-of-mouth data. For example, the classification unit can optimize the classification method for the word-of-mouth data based on the related literature. The classification unit can also improve the classification accuracy of the word-of-mouth data by referring to the related literature. This improves the classification accuracy of the classification unit.

[0050] The providing unit can select the optimal information providing method by referring to the user's past usage history at the time of information provision. For example, the providing unit can select the optimal information providing method by referring to the user's past usage history at the time of information provision. The providing unit can use the generation AI to, for example, preferentially select an information providing method that the user has used in the past. For example, the providing unit can select the most effective information providing method from the user's past usage history. The providing unit can also preferentially select an information providing method that the user has given a high rating in the past. This enables the providing unit to provide information efficiently.

[0051] The providing unit can customize the information based on the user's current field of interest at the time of providing. For example, the providing unit customizes the information based on the user's current field of interest at the time of providing. The providing unit can use the generating AI to, for example, preferentially provide information related to a field in which the user is currently interested. For example, the providing unit can customize the information based on keywords recently searched by the user. The providing unit can also provide information related to a specific topic in which the user is interested. This allows the providing unit to provide highly relevant information.

[0052] The providing unit can select the optimal information providing method in consideration of the device information of the user at the time of providing. For example, the providing unit selects the optimal information providing method in consideration of the device information of the user at the time of providing. The providing unit can use the generation AI to select an information providing method that matches the screen size, for example, when the user is using a smartphone. For example, the providing unit can select an information providing method that is optimized for a large screen, when the user is using a tablet. In addition, the providing unit can also select an information providing method that is concise and has high visibility, when the user is using a smartwatch. This allows the providing unit to provide information in an optimal format.

[0053] The providing unit can adjust the way information is provided by analyzing the user's social media activity at the time of providing the information. For example, the providing unit can adjust the way information is provided by analyzing the user's social media activity at the time of providing the information. The providing unit can use the generation AI to preferentially provide information related to topics mentioned by the user on social media, for example. For example, the providing unit can preferentially provide information shared by the user's followers or friends. The providing unit can also provide information related to topics that are trending in groups or communities in which the user participates. This allows the providing unit to provide highly relevant information.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The collection unit can analyze the user's past purchase history and preferentially collect related word-of-mouth data. For example, the collection unit can provide information that matches the user's interests by collecting word-of-mouth data related to products that the user has purchased in the past. The collection unit can also preferentially collect word-of-mouth data on products that the user has given high ratings in the past. Furthermore, the collection unit can collect related word-of-mouth data based on the categories of products that the user has purchased in the past. This allows the collection unit to efficiently collect information that is useful to the user.

[0056] The analysis unit can extract positive evaluations from the word-of-mouth data and provide them to the user. For example, the analysis unit can extract positive evaluations such as "easy to use," "feel effective," and "reasonable price" from the word-of-mouth data. The analysis unit can also classify the positive evaluations by category and provide them to the user. Furthermore, the analysis unit can display the percentage of positive evaluations in a graph or chart and provide it to the user in a format that is visually easy to understand. This allows the analysis unit to make it easier for the user to understand the good points of the product.

[0057] The collection unit can preferentially collect word-of-mouth data specific to a region, taking into consideration the geographical location information of the user. For example, the collection unit can provide information highly relevant to the user by collecting word-of-mouth data of stores and services close to the user's current location. The collection unit can also collect word-of-mouth data related to places the user has visited in the past. Furthermore, the collection unit can collect word-of-mouth data related to places the user plans to visit in the future. This allows the collection unit to efficiently collect word-of-mouth data related to a region.

[0058] The analysis unit can extract evaluations related to specific topics from the word-of-mouth data and provide them to the user. For example, the analysis unit can extract evaluations related to specific topics such as "ease of use," "effectiveness," and "price" from the word-of-mouth data. The analysis unit can also classify the evaluations related to the specific topic by category and provide them to the user. Furthermore, the analysis unit can display the percentage of evaluations related to the specific topic in a graph or chart and provide it to the user in a format that is visually easy to understand. In this way, the analysis unit can make it easier for the user to understand the evaluations related to the specific topic.

[0059] The collection unit can analyze the user's social media activities and preferentially collect related word-of-mouth data. For example, the collection unit can provide information that matches the user's interests by collecting word-of-mouth data on products and services mentioned by the user on social media. The collection unit can also preferentially collect word-of-mouth data posted by the user's followers and friends. Furthermore, the collection unit can collect word-of-mouth data on products that are hot topics in groups and communities in which the user participates. This allows the collection unit to efficiently collect highly relevant word-of-mouth data.

[0060] The analysis unit can extract evaluations related to specific topics from the word-of-mouth data and provide them to the user. For example, the analysis unit can extract evaluations related to specific topics such as "ease of use," "effectiveness," and "price" from the word-of-mouth data. The analysis unit can also classify the evaluations related to the specific topic by category and provide them to the user. Furthermore, the analysis unit can display the percentage of evaluations related to the specific topic in a graph or chart and provide it to the user in a format that is visually easy to understand. In this way, the analysis unit can make it easier for the user to understand the evaluations related to the specific topic.

[0061] The process flow of the first embodiment will be briefly described below.

[0062] Step 1: The collection unit collects word-of-mouth data using the generation AI. The collection unit can collect word-of-mouth data, for example, from word-of-mouth sites and review sites on the Internet. The collection unit can use the generation AI to filter the word-of-mouth data, for example, based on specific keywords or phrases, and collect highly relevant data. Step 2: The analysis unit analyzes the word-of-mouth data collected by the collection unit and extracts negative evaluations. The analysis unit can use the generative AI, for example, natural language processing technology, to analyze the word-of-mouth data and extract negative evaluations and complaints. Step 3: The classification unit classifies and organizes the negative reviews extracted by the analysis unit. Using a generative AI, the classification unit can classify and organize negative reviews based on reasons such as "poor usability," "no visible effect," and "high price." Step 4: The providing unit provides the information organized by the classification unit to the user. The providing unit can provide the information in text format, graphs, charts, etc., using the generation AI.

[0063] (Example 2) The system according to the embodiment of the present invention uses a generation AI to analyze the word-of-mouth data of a product and extracts the reason why the product was not so good after use. This system operates when the user inputs an instruction to the generation AI, such as "Tell me the reason why people thought the product was not so good after use." The generation AI analyzes the input instruction and collects the word-of-mouth data of the product. For example, the generation AI collects word-of-mouth data from word-of-mouth sites and review sites on the Internet and stores it in a database. The generation AI then analyzes the collected word-of-mouth data and identifies the reason why the user thought the product was not so good. The generation AI extracts negative evaluations and dissatisfaction points from the word-of-mouth data and classifies and organizes them. For example, reasons such as "poor usability," "no effect felt," and "high price" are identified. Finally, the generation AI provides the identified "reason why the product was not so good" to the user. This allows the user to efficiently grasp the evaluation of the product without having to visually inspect each word-of-mouth. In addition, since the generation AI automatically analyzes the word-of-mouth data, it is possible to significantly reduce time and effort. This allows the system to efficiently allow the user to select products and consider improvements.

[0064] The system according to the embodiment includes a collection unit, an analysis unit, a classification unit, and a provision unit. The collection unit collects word-of-mouth data using a generation AI. The collection unit can collect word-of-mouth data from, for example, word-of-mouth sites and review sites on the Internet. The collection unit can use the generation AI to filter the word-of-mouth data based on, for example, specific keywords or phrases, and collect highly relevant data. The analysis unit analyzes the word-of-mouth data collected by the collection unit and extracts negative evaluations. The analysis unit can use the generation AI to analyze the word-of-mouth data using, for example, natural language processing technology, and extract negative evaluations and dissatisfaction points. The classification unit classifies and organizes the negative evaluations extracted by the analysis unit. The classification unit can use the generation AI to classify and organize the negative evaluations based on reasons such as "poor usability," "no effect felt," and "high price." The provision unit provides the user with the information organized by the classification unit. The provision unit can use the generation AI to provide information in, for example, text format, graphs, charts, etc. This allows the system to efficiently collect, analyze, classify, and provide word-of-mouth data.

[0065] The collection unit collects word-of-mouth data using the generation AI. Specifically, the collection unit can automatically collect word-of-mouth data from word-of-mouth and review sites on the Internet. The generation AI uses web scraping technology to extract text data from specified websites and store it in a database. In addition, the generation AI can filter word-of-mouth data based on specific keywords and phrases to collect only highly relevant data. For example, keywords such as "ease of use," "effectiveness," and "price" are set, and word-of-mouth data containing these keywords is preferentially collected. In addition, the generation AI also has a filtering function that removes irrelevant information such as spam and advertisements to eliminate duplication of collected data and maintain data quality. This allows the collection unit to collect word-of-mouth data efficiently and with high accuracy and provide it to the analysis unit. In addition, the collection unit can update the collected data in real time and always keep the latest word-of-mouth information. This can improve the freshness and reliability of data throughout the system.

[0066] The analysis unit analyzes the word-of-mouth data collected by the collection unit and extracts negative evaluations. Specifically, the analysis unit uses the generation AI to analyze the word-of-mouth data using natural language processing technology. The generation AI performs sentiment analysis of the text and can automatically classify evaluations into positive, negative, and neutral. For example, it extracts text containing negative expressions such as "difficult to use," "ineffective," and "too expensive" from the word-of-mouth data. In addition, the generation AI analyzes the co-occurrence of words and sentence structure to understand the context, achieving more accurate sentiment analysis. Furthermore, the analysis unit can analyze the extracted negative evaluations in detail and identify specific dissatisfaction and problems. For example, if there are many evaluations that are "difficult to use," it extracts detailed problems such as "complex interface" and "unintuitive operation" as specific reasons. This allows the analysis unit to efficiently extract useful information from the collected word-of-mouth data and provide it to the classification unit.

[0067] The classification unit classifies and organizes the negative evaluations extracted by the analysis unit. Specifically, the classification unit uses the generation AI to classify the negative evaluations based on reasons such as "poor usability," "no effect felt," and "high price." The generation AI can automatically assign each evaluation to an appropriate category using a text classification algorithm. For example, an evaluation that is "difficult to use" is classified as "poor usability," and an evaluation that is "ineffective" is classified as "no effect felt." In addition, even if multiple evaluations are included at the same time, the generation AI can appropriately divide each evaluation and classify them into multiple categories. Furthermore, the classification unit can organize the classified evaluations and perform statistical information and trend analysis. For example, the number of evaluations in each category during a specific period is tallied to determine which problems are most frequently pointed out. In addition, the classification unit can analyze fluctuations in evaluations over time and evaluate the effectiveness of improvements. This allows the classification unit to efficiently classify and organize negative evaluations and provide them to the provision unit.

[0068] The providing unit provides the information organized by the classification unit to the user. Specifically, the providing unit can use the generating AI to provide information in text format, graphs, charts, etc. The generating AI can display information in the optimal format according to the needs of the user. For example, the statistical information of negative evaluations can be visually displayed in graphs and charts, allowing the user to grasp the trend of the problem at a glance. It can also generate detailed text reports to detail the evaluation contents and specific problems in each category. Furthermore, the providing unit has a filtering function that provides information limited to a specific category or period that the user is interested in. For example, it is possible to display only evaluations on a specific product or service, or to analyze fluctuations in evaluations over a specific period. This allows the providing unit to efficiently provide the information the user needs and assist in identifying problems and planning improvement measures. Furthermore, the providing unit can collect feedback from users and continuously improve the accuracy and usefulness of the information provided. This allows the providing unit to provide high-quality information to users and improve the value of the entire system.

[0069] The collection unit can collect word-of-mouth data from word-of-mouth sites or review sites on the Internet. The collection unit, for example, collects word-of-mouth data from word-of-mouth sites and review sites on the Internet. The collection unit can use the generation AI to filter the word-of-mouth data based on, for example, specific keywords or phrases, and collect highly relevant data. For example, in order to collect word-of-mouth data for a specific product, the collection unit inputs a prompt to the generation AI saying, "Please collect word-of-mouth data for this product." The generation AI collects related word-of-mouth data from word-of-mouth sites and review sites on the Internet, and stores it in a database. This allows the collection unit to obtain a wide range of word-of-mouth data.

[0070] The analysis unit can extract negative evaluations or points of dissatisfaction from the word-of-mouth data. The analysis unit, for example, extracts negative evaluations and points of dissatisfaction from the word-of-mouth data. The analysis unit can use the generation AI, for example, natural language processing technology, to analyze the word-of-mouth data and extract negative evaluations and points of dissatisfaction. For example, the analysis unit extracts negative evaluations such as "poor usability," "no effect felt," and "expensive" from the word-of-mouth data. The generation AI can detect specific keywords and phrases from the word-of-mouth data and extract negative evaluations based on them. This allows the analysis unit to clarify areas for improvement of the product.

[0071] The classification unit can classify and organize the extracted negative evaluations into at least one of the following reasons: "poor usability," "no effect felt," and "high price." The classification unit, for example, classifies and organizes the extracted negative evaluations into at least one of the following reasons: "poor usability," "no effect felt," and "high price." The classification unit can use the generation AI to classify and organize the negative evaluations, for example, based on specific keywords or phrases. For example, the classification unit classifies and organizes the negative evaluations from the word-of-mouth data based on reasons such as "poor usability," "no effect felt," and "high price." The generation AI can detect specific keywords or phrases from the word-of-mouth data and classify and organize the negative evaluations based on them. This allows the classification unit to make it easier for users to understand the content of the evaluations.

[0072] The providing unit can provide the classified and organized information to the user in a text format, graph, or chart. The providing unit, for example, provides the classified and organized information to the user in a text format, graph, chart, or the like. The providing unit can provide information based on a specific format, for example, using a generating AI. For example, the providing unit can provide the classified and organized information in a text format. The providing unit can also provide the classified and organized information in a graph or chart format. For example, the providing unit can display the percentage of negative evaluations in a bar graph or pie chart. This allows the providing unit to allow the user to intuitively understand the content of the evaluation.

[0073] The collection unit can estimate the user's emotion and adjust the collection timing of the word-of-mouth data based on the estimated user's emotion. The collection unit can estimate the user's emotion, for example, and adjust the collection timing of the word-of-mouth data based on the estimated user's emotion. The collection unit can estimate the user's emotion using a generation AI, for example, using techniques such as facial expression recognition, voice analysis, and text analysis. For example, when the user is stressed, the collection unit delays the collection timing and starts collection when the user is relaxed. In addition, when the user is excited, the collection unit can start collecting immediately and provide information quickly. Furthermore, when the user is tired, the collection unit can adjust the collection timing and collect after the user has taken a rest. This allows the collection unit to reduce the user's stress. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0074] The collection unit can analyze the user's past search history at the time of collection and select the optimal collection method. For example, the collection unit can analyze the user's past search history at the time of collection and select the optimal collection method. The collection unit can use the generation AI to preferentially collect related word-of-mouth data, for example, based on keywords or phrases that the user has searched in the past. For example, the collection unit can preferentially collect specific sites and reviews from the user's past search history. The collection unit can also preferentially collect word-of-mouth data of products that the user has given high ratings in the past. This enables the collection unit to collect data efficiently.

[0075] The collection unit can filter based on the user's current field of interest at the time of collection. For example, the collection unit can filter based on the user's current field of interest at the time of collection. The collection unit can use the generation AI to preferentially collect, for example, word-of-mouth data of products in which the user is currently interested. For example, the collection unit can filter and collect word-of-mouth data related to products in a category recently searched by the user. The collection unit can also preferentially collect word-of-mouth data of a specific brand or manufacturer in which the user is interested. This allows the collection unit to collect highly relevant data.

[0076] The collection unit can estimate the user's emotion and determine the priority of the word-of-mouth data to be collected based on the estimated user's emotion. The collection unit can estimate the user's emotion, for example, and determine the priority of the word-of-mouth data to be collected based on the estimated user's emotion. The collection unit can estimate the user's emotion using the generation AI, for example, using techniques such as facial expression recognition, voice analysis, and text analysis. For example, when the user feels anxious, the collection unit can preferentially collect reliable word-of-mouth data. In addition, when the user is excited, the collection unit can preferentially collect the latest word-of-mouth data. Furthermore, when the user is relaxed, the collection unit can preferentially collect detailed word-of-mouth data. This allows the collection unit to preferentially collect information that is important to the user. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0077] The collection unit can preferentially collect highly relevant word-of-mouth data in consideration of the geographical location information of the user at the time of collection. For example, the collection unit preferentially collects highly relevant word-of-mouth data in consideration of the geographical location information of the user at the time of collection. The collection unit can preferentially collect, for example, word-of-mouth data of stores and services close to the user's current location using the generation AI. For example, the collection unit can preferentially collect word-of-mouth data related to places the user has visited in the past. The collection unit can also preferentially collect word-of-mouth data related to places the user plans to visit in the future. This allows the collection unit to efficiently collect word-of-mouth data related to the area.

[0078] The collection unit can analyze the user's social media activities at the time of collection and collect related word-of-mouth data. For example, the collection unit can analyze the user's social media activities at the time of collection and collect related word-of-mouth data. The collection unit can use the generation AI to preferentially collect word-of-mouth data of products and services mentioned by the user on social media, for example. For example, the collection unit can preferentially collect word-of-mouth data posted by the user's followers and friends. The collection unit can also preferentially collect word-of-mouth data of products that are hot topics in groups and communities in which the user participates. This allows the collection unit to collect highly relevant word-of-mouth data.

[0079] The analysis unit can estimate the user's emotion and adjust the method of extracting negative evaluations based on the estimated user's emotion. The analysis unit can estimate the user's emotion, for example, and adjust the method of extracting negative evaluations based on the estimated user's emotion. The analysis unit can estimate the user's emotion using a generation AI, for example, using techniques such as facial expression recognition, voice analysis, and text analysis. For example, the analysis unit can quickly extract negative evaluations when the user is stressed. In addition, the analysis unit can extract detailed negative evaluations when the user is relaxed. Furthermore, the analysis unit can extract negative evaluations in a visually easy-to-understand format when the user is excited. This allows the analysis unit to quickly extract negative evaluations that are important to the user. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0080] The analysis unit can adjust the level of detail of the analysis based on the importance of the word-of-mouth data during analysis. The analysis unit, for example, adjusts the level of detail of the analysis based on the importance of the word-of-mouth data during analysis. The analysis unit can use the generation AI to evaluate the importance based on, for example, the number of stars in the evaluation of the word-of-mouth data or the content of the comments, and adjust the level of detail of the analysis based on that. For example, the analysis unit performs a detailed analysis on word-of-mouth data with high importance. In addition, the analysis unit can perform a simplified analysis on word-of-mouth data with low importance. Furthermore, the analysis unit can perform an analysis at an appropriate level of detail on word-of-mouth data with medium importance. This enables the analysis unit to perform efficient analysis.

[0081] The analysis unit can apply different analysis algorithms depending on the category of the word-of-mouth data during analysis. The analysis unit can, for example, apply different analysis algorithms depending on the category of the word-of-mouth data during analysis. The analysis unit can use the generation AI to apply, for example, an optimal analysis algorithm for each product category. For example, the analysis unit can apply different analysis algorithms for each service category. The analysis unit can also apply different analysis algorithms for each region. This allows the analysis unit to apply the optimal analysis algorithm depending on the category of the word-of-mouth data, thereby improving the analysis accuracy.

[0082] The analysis unit can estimate the user's emotion and determine the priority of extraction of negative evaluations based on the estimated user's emotion. The analysis unit can estimate the user's emotion, for example, and determine the priority of extraction of negative evaluations based on the estimated user's emotion. The analysis unit can estimate the user's emotion using a generation AI, for example, using techniques such as facial expression recognition, voice analysis, and text analysis. For example, when the user feels anxious, the analysis unit can preferentially extract highly reliable negative evaluations. In addition, when the user is excited, the analysis unit can preferentially extract the latest negative evaluations. Furthermore, when the user is relaxed, the analysis unit can preferentially extract detailed negative evaluations. This allows the analysis unit to preferentially extract negative evaluations that are important to the user. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0083] The analysis unit can determine the priority of analysis based on the time of submission of the review data during analysis. The analysis unit, for example, determines the priority of analysis based on the time of submission of the review data during analysis. The analysis unit can use the generation AI to evaluate the time of submission based on, for example, the posting date and time or the latest data, and determine the priority of analysis based on that. For example, the analysis unit prioritizes analysis of the latest review data. In addition, the analysis unit can appropriately analyze past review data. Furthermore, the analysis unit can prioritize analysis of review data that was submitted in a concentrated manner during a specific period. This allows the analysis unit to prioritize analysis of the latest data.

[0084] The analysis unit can adjust the order of analysis based on the relevance of the word-of-mouth data during analysis. The analysis unit can adjust the order of analysis based on the relevance of the word-of-mouth data during analysis, for example. The analysis unit can use the generation AI to evaluate the relevance based on, for example, common keywords or related topics, and adjust the order of analysis based on the evaluation. For example, the analysis unit preferentially analyzes word-of-mouth data with high relevance. Also, the analysis unit can analyze word-of-mouth data with medium relevance next. Furthermore, the analysis unit can analyze word-of-mouth data with low relevance last. This enables the analysis unit to perform efficient analysis.

[0085] The classification unit can estimate the user's emotion and adjust the classification method of the negative evaluation based on the estimated user's emotion. The classification unit can estimate the user's emotion, for example, and adjust the classification method of the negative evaluation based on the estimated user's emotion. The classification unit can estimate the user's emotion using a generation AI, for example, using techniques such as facial expression recognition, voice analysis, and text analysis. For example, the classification unit applies a simple classification method when the user is stressed. Also, the classification unit can apply a detailed classification method when the user is relaxed. Furthermore, the classification unit can apply a visually easy-to-understand classification method when the user is excited. This enables the classification unit to perform classification that is easy for the user to understand. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0086] The classification unit can improve the accuracy of classification by taking into account the interrelationships of the word-of-mouth data during classification. The classification unit can improve the accuracy of classification by taking into account the interrelationships of the word-of-mouth data during classification, for example. The classification unit can use a generation AI to, for example, extract commonalities in the word-of-mouth data and classify it by taking into account the interrelationships. For example, the classification unit can analyze the correlations of the word-of-mouth data and perform classification with high accuracy. The classification unit can also evaluate the relevance of the word-of-mouth data and perform optimal classification. This enables the classification unit to perform classification with high accuracy.

[0087] The classification unit can perform classification taking into consideration attribute information of the submitter of the word-of-mouth data when classifying. For example, the classification unit performs classification taking into consideration attribute information of the submitter of the word-of-mouth data when classifying. The classification unit can use the generation AI to classify the word-of-mouth data based on, for example, the age or gender of the submitter. For example, the classification unit can classify the word-of-mouth data based on the region or nationality of the submitter. The classification unit can also classify the word-of-mouth data based on the purchase history or usage history of the submitter. This enables the classification unit to perform more detailed classification.

[0088] The classification unit can estimate the user's emotion and adjust the display method of the classification result based on the estimated user's emotion. The classification unit can estimate the user's emotion, for example, and adjust the display method of the classification result based on the estimated user's emotion. The classification unit can estimate the user's emotion using a generation AI, for example, using techniques such as facial expression recognition, voice analysis, and text analysis. For example, the classification unit can provide a display method that is simple and highly visible when the user is nervous. In addition, the classification unit can provide a display method that includes detailed information when the user is relaxed. Furthermore, the classification unit can provide a display method that focuses on the main points when the user is in a hurry. This enables the classification unit to display in a way that is easy for the user to understand. The estimation of emotion is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0089] The classification unit can perform classification taking into consideration the geographical distribution of the word-of-mouth data when classifying. For example, the classification unit performs classification taking into consideration the geographical distribution of the word-of-mouth data when classifying. The classification unit can use the generation AI to classify the word-of-mouth data by region, for example, and extract region-specific evaluations. For example, the classification unit can classify the word-of-mouth data by country, and extract country-specific evaluations. The classification unit can also classify the word-of-mouth data by city, and extract city-specific evaluations. This allows the classification unit to extract region-specific evaluations.

[0090] The classification unit can improve the accuracy of classification by referring to related literature of the word-of-mouth data during classification. The classification unit can, for example, improve the accuracy of classification by referring to related literature of the word-of-mouth data during classification. The classification unit can use the generation AI to, for example, refer to related literature and set classification criteria for the word-of-mouth data. For example, the classification unit can optimize the classification method for the word-of-mouth data based on the related literature. The classification unit can also improve the classification accuracy of the word-of-mouth data by referring to the related literature. This improves the classification accuracy of the classification unit.

[0091] The providing unit can estimate the user's emotion and adjust the method of providing information based on the estimated user's emotion. The providing unit can, for example, estimate the user's emotion and adjust the method of providing information based on the estimated user's emotion. The providing unit can estimate the user's emotion using a generation AI, for example, using techniques such as facial expression recognition, voice analysis, and text analysis. For example, when the user is nervous, the providing unit can provide information in a simple and highly visible format. Also, when the user is relaxed, the providing unit can provide information in a format including detailed information. Furthermore, when the user is in a hurry, the providing unit can provide information in a format that focuses on the main points. This enables the providing unit to provide information that is easy for the user to understand. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0092] The providing unit can select the optimal information providing method by referring to the user's past usage history at the time of information provision. For example, the providing unit can select the optimal information providing method by referring to the user's past usage history at the time of information provision. The providing unit can use the generation AI to, for example, preferentially select an information providing method that the user has used in the past. For example, the providing unit can select the most effective information providing method from the user's past usage history. The providing unit can also preferentially select an information providing method that the user has given a high rating in the past. This enables the providing unit to provide information efficiently.

[0093] The providing unit can customize the information based on the user's current field of interest at the time of providing. For example, the providing unit customizes the information based on the user's current field of interest at the time of providing. The providing unit can use the generating AI to, for example, preferentially provide information related to a field in which the user is currently interested. For example, the providing unit can customize the information based on keywords recently searched by the user. The providing unit can also provide information related to a specific topic in which the user is interested. This allows the providing unit to provide highly relevant information.

[0094] The providing unit can estimate the user's emotion and determine the priority of information based on the estimated user's emotion. The providing unit can estimate the user's emotion, for example, and determine the priority of information based on the estimated user's emotion. The providing unit can estimate the user's emotion using a generation AI, for example, using techniques such as facial expression recognition, voice analysis, and text analysis. For example, when the user feels anxious, the providing unit can provide highly reliable information preferentially. In addition, when the user is excited, the providing unit can provide the latest information preferentially. Furthermore, when the user is relaxed, the providing unit can provide detailed information preferentially. This allows the providing unit to provide information that is important to the user preferentially. The estimation of emotion is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0095] The providing unit can select the optimal information providing method in consideration of the device information of the user at the time of providing. For example, the providing unit selects the optimal information providing method in consideration of the device information of the user at the time of providing. The providing unit can use the generation AI to select an information providing method that matches the screen size, for example, when the user is using a smartphone. For example, the providing unit can select an information providing method that is optimized for a large screen, when the user is using a tablet. In addition, the providing unit can also select an information providing method that is concise and has high visibility, when the user is using a smartwatch. This allows the providing unit to provide information in an optimal format.

[0096] The providing unit can adjust the way information is provided by analyzing the user's social media activity at the time of providing the information. For example, the providing unit can adjust the way information is provided by analyzing the user's social media activity at the time of providing the information. The providing unit can use the generation AI to preferentially provide information related to topics mentioned by the user on social media, for example. For example, the providing unit can preferentially provide information shared by the user's followers or friends. The providing unit can also provide information related to topics that are trending in groups or communities in which the user participates. This allows the providing unit to provide highly relevant information.

[0097] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0098] The collection unit can analyze the user's past purchase history and preferentially collect related word-of-mouth data. For example, the collection unit can provide information that matches the user's interests by collecting word-of-mouth data related to products that the user has purchased in the past. The collection unit can also preferentially collect word-of-mouth data on products that the user has given high ratings in the past. Furthermore, the collection unit can collect related word-of-mouth data based on the categories of products that the user has purchased in the past. This allows the collection unit to efficiently collect information that is useful to the user.

[0099] The analysis unit can extract positive evaluations from the word-of-mouth data and provide them to the user. For example, the analysis unit can extract positive evaluations such as "easy to use," "feel effective," and "reasonable price" from the word-of-mouth data. The analysis unit can also classify the positive evaluations by category and provide them to the user. Furthermore, the analysis unit can display the percentage of positive evaluations in a graph or chart and provide it to the user in a format that is visually easy to understand. This allows the analysis unit to make it easier for the user to understand the good points of the product.

[0100] The classification unit can estimate emotions from the word-of-mouth data and classify the data based on positive emotions and negative emotions. For example, the classification unit can extract and classify evaluations with positive emotions such as "satisfaction," "joy," and "gratitude" from the word-of-mouth data. The classification unit can also extract and classify evaluations with negative emotions such as "dissatisfaction," "anger," and "disappointment." Furthermore, the classification unit can classify the evaluations based on the intensity of the emotions and provide them to the user. In this way, the classification unit can make it easier for the user to understand the emotional aspects of the word-of-mouth data.

[0101] The providing unit can estimate the user's emotions and customize the method of providing information based on the estimated emotions. For example, when the user is feeling stressed, the providing unit can provide information in a simple and highly visible format. When the user is relaxed, the providing unit can also provide information in a format including detailed information. Furthermore, when the user is in a hurry, the providing unit can provide information in a format that focuses on the main points. This enables the providing unit to provide optimal information according to the user's emotions.

[0102] The collection unit can preferentially collect word-of-mouth data specific to a region, taking into consideration the geographical location information of the user. For example, the collection unit can provide information highly relevant to the user by collecting word-of-mouth data of stores and services close to the user's current location. The collection unit can also collect word-of-mouth data related to places the user has visited in the past. Furthermore, the collection unit can collect word-of-mouth data related to places the user plans to visit in the future. This allows the collection unit to efficiently collect word-of-mouth data related to a region.

[0103] The analysis unit can extract evaluations related to specific topics from the word-of-mouth data and provide them to the user. For example, the analysis unit can extract evaluations related to specific topics such as "ease of use," "effectiveness," and "price" from the word-of-mouth data. The analysis unit can also classify the evaluations related to the specific topic by category and provide them to the user. Furthermore, the analysis unit can display the percentage of evaluations related to the specific topic in a graph or chart and provide it to the user in a format that is visually easy to understand. In this way, the analysis unit can make it easier for the user to understand the evaluations related to the specific topic.

[0104] The classification unit can estimate emotions from the word-of-mouth data and classify the data based on positive emotions and negative emotions. For example, the classification unit can extract and classify evaluations with positive emotions such as "satisfaction," "joy," and "gratitude" from the word-of-mouth data. The classification unit can also extract and classify evaluations with negative emotions such as "dissatisfaction," "anger," and "disappointment." Furthermore, the classification unit can classify the evaluations based on the intensity of the emotions and provide them to the user. In this way, the classification unit can make it easier for the user to understand the emotional aspects of the word-of-mouth data.

[0105] The providing unit can estimate the user's emotions and customize the method of providing information based on the estimated emotions. For example, when the user is feeling stressed, the providing unit can provide information in a simple and highly visible format. When the user is relaxed, the providing unit can also provide information in a format including detailed information. Furthermore, when the user is in a hurry, the providing unit can provide information in a format that focuses on the main points. This enables the providing unit to provide optimal information according to the user's emotions.

[0106] The collection unit can analyze the user's social media activities and preferentially collect related word-of-mouth data. For example, the collection unit can provide information that matches the user's interests by collecting word-of-mouth data on products and services mentioned by the user on social media. The collection unit can also preferentially collect word-of-mouth data posted by the user's followers and friends. Furthermore, the collection unit can collect word-of-mouth data on products that are hot topics in groups and communities in which the user participates. This allows the collection unit to efficiently collect highly relevant word-of-mouth data.

[0107] The analysis unit can extract evaluations related to specific topics from the word-of-mouth data and provide them to the user. For example, the analysis unit can extract evaluations related to specific topics such as "ease of use," "effectiveness," and "price" from the word-of-mouth data. The analysis unit can also classify the evaluations related to the specific topic by category and provide them to the user. Furthermore, the analysis unit can display the percentage of evaluations related to the specific topic in a graph or chart and provide it to the user in a format that is visually easy to understand. In this way, the analysis unit can make it easier for the user to understand the evaluations related to the specific topic.

[0108] The process flow of the second embodiment will be briefly described below.

[0109] Step 1: The collection unit collects word-of-mouth data using the generation AI. The collection unit can collect word-of-mouth data, for example, from word-of-mouth sites and review sites on the Internet. The collection unit can use the generation AI to filter the word-of-mouth data, for example, based on specific keywords or phrases, and collect highly relevant data. Step 2: The analysis unit analyzes the word-of-mouth data collected by the collection unit and extracts negative evaluations. The analysis unit can use the generative AI, for example, natural language processing technology, to analyze the word-of-mouth data and extract negative evaluations and complaints. Step 3: The classification unit classifies and organizes the negative reviews extracted by the analysis unit. Using a generative AI, the classification unit can classify and organize negative reviews based on reasons such as "poor usability," "no visible effect," and "high price." Step 4: The providing unit provides the information organized by the classification unit to the user. The providing unit can provide the information in text format, graphs, charts, etc., using the generation AI.

[0110] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0111] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0112] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0113] For example, the collecting unit can collect word-of-mouth data using the camera 42 or microphone 38B of the smart device 14. The collecting unit is also realized by the specific processing unit 290 of the data processing device 12, and collects data from word-of-mouth sites and review sites on the Internet. The analyzing unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and analyzes the collected word-of-mouth data and extracts negative evaluations. The classifying unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and classifies and organizes the extracted negative evaluations. The providing unit is realized by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12, and provides the classified information to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] 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, the RAM 30, and the 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.

[0117] 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.

[0118] 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 the voice according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0120] 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 performed in a secure state.

[0121] Fig. 4 shows an example of 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.

[0122] 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.

[0123] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0125] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0126] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0127] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0128] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0129] For example, the collecting unit can collect word-of-mouth data using the camera 42 and microphone 238 of the smart glasses 214. The collecting unit is also realized by the specific processing unit 290 of the data processing device 12, and collects data from word-of-mouth sites and review sites on the Internet. The analyzing unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and analyzes the collected word-of-mouth data and extracts negative evaluations. The classifying unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and classifies and organizes the extracted negative evaluations. The providing unit is realized by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and provides the classified information to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0132] 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, the RAM 30, and the 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.

[0133] 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.

[0134] 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 the voice according to instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0136] 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 performed in a secure state.

[0137] 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.

[0138] 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.

[0139] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0140] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 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.

[0141] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0142] 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 voice indicating a user input for 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.

[0143] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0144] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0145] For example, the collecting unit can collect word-of-mouth data using the camera 42 or microphone 238 of the headset type terminal 314. The collecting unit is also realized by the specific processing unit 290 of the data processing device 12, and collects data from word-of-mouth sites and review sites on the Internet. The analyzing unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and analyzes the collected word-of-mouth data and extracts negative evaluations. The classifying unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and classifies and organizes the extracted negative evaluations. The providing unit is realized by the display 343 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and provides the classified information to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] 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, the RAM 30, and the 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.

[0149] 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.

[0150] 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 the voice according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0152] 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 performed in a secure state.

[0153] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0154] 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.

[0155] 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.

[0156] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0157] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0158] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0159] 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 a voice indicating a user input for 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.

[0160] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0161] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0162] For example, the collecting unit can collect word-of-mouth data using the camera 42 or microphone 238 of the robot 414. The collecting unit is also realized by the specific processing unit 290 of the data processing device 12, and collects data from word-of-mouth sites and review sites on the Internet. The analyzing unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and analyzes the collected word-of-mouth data and extracts negative evaluations. The classifying unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and classifies and organizes the extracted negative evaluations. The providing unit is realized by the speaker 240 of the robot 414 or the specific processing unit 290 of the data processing device 12, and provides the classified information to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0163] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0164] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0165] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0166] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0167] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0168] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0170] 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.

[0171] 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 Universal Serial Bus (USB) 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.

[0172] In addition, 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 upon request from the data processing device 12.

[0173] 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.

[0174] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0175] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0176] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0177] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0178] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0179] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0180] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0181] (Appendix 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 and extracts negative evaluations; A classification unit that classifies and organizes the negative evaluations extracted by the analysis unit; a providing unit that provides the information organized by the classification unit to a user. A system characterized by: (Appendix 2) The collecting unit includes: Collect word-of-mouth data from online word-of-mouth or review sites 2. The system of claim 1, (Appendix 3) The analysis unit is Extracting negative reviews or complaints from review data 2. The system of claim 1, (Appendix 4) The classification unit is Classify and organize the extracted negative evaluations into at least one of the following reasons: "poor usability," "no sense of effectiveness," or "high price." 2. The system of claim 1, (Appendix 5) The providing unit is Provide users with categorized and organized information in text format or in graphs and charts 2. The system of claim 1, (Appendix 6) The collecting unit includes: To estimate user sentiment and adjust the timing of collecting word-of-mouth data based on the estimated user sentiment. 2. The system of claim 1, (Appendix 7) The collecting unit includes: When collecting data, the system analyzes the user's past search history and selects the optimal collection method. 2. The system of claim 1, (Appendix 8) The collecting unit includes: At the time of collection, filtering is performed based on the user's current interests 2. The system of claim 1, (Appendix 9) The collecting unit includes: Estimate user sentiment and prioritize the review data to be collected based on the estimated user sentiment. 2. The system of claim 1, (Appendix 10) The collecting unit includes: When collecting data, the geographic location of the user is taken into consideration to prioritize collection of relevant review data. 2. The system of claim 1, (Appendix 11) The collecting unit includes: At the time of collection, analyze users' social media activity to gather pertinent review data 2. The system of claim 1, (Appendix 12) The analysis unit is Infer user sentiment and adjust the method of extracting negative ratings based on the estimated user sentiment 2. The system of claim 1, (Appendix 13) The analysis unit is During analysis, adjust the level of detail based on the importance of review data 2. The system of claim 1, (Appendix 14) The analysis unit is During analysis, different analysis algorithms are applied depending on the category of review data. 2. The system of claim 1, (Appendix 15) The analysis unit is Estimate user sentiment and prioritize extraction of negative reviews based on the estimated user sentiment. 2. The system of claim 1, (Appendix 16) The analysis unit is During analysis, we prioritize analysis based on when review data was submitted 2. The system of claim 1, (Appendix 17) The analysis unit is During analysis, adjust the order of analysis based on the relevance of review data 2. The system of claim 1, (Appendix 18) The classification unit is Infer user sentiment and adjust the classification of negative reviews based on the inferred user sentiment 2. The system of claim 1, (Appendix 19) The classification unit is When classifying, the accuracy of classification is improved by taking into account the correlations between review data. 2. The system of claim 1, (Appendix 20) The classification unit is When classifying reviews, the attribute information of the person submitting the review data is taken into consideration. 2. The system of claim 1, (Appendix 21) The classification unit is Inferring user emotion and adjusting the way classification results are displayed based on the inferred user emotion 2. The system of claim 1, (Appendix 22) The classification unit is When classifying, the geographic distribution of review data is taken into account. 2. The system of claim 1, (Appendix 23) The classification unit is When classifying, the accuracy of classification is improved by referring to related literature on review data. 2. The system of claim 1, (Appendix 24) The providing unit is To estimate a user's emotion and adjust a method of providing information based on the estimated user's emotion. 2. The system of claim 1, (Appendix 25) The providing unit is When providing the service, the optimal method of providing the service is selected by referring to the user's past usage history. 2. The system of claim 1, (Appendix 26) The providing unit is When provided, to customize information based on your current interests 2. The system of claim 1, (Appendix 27) The providing unit is Estimate user emotions and prioritize information based on the estimated user emotions 2. The system of claim 1, (Appendix 28) The providing unit is When providing information, the optimal method of providing the information is selected taking into account the user's device information. 2. The system of claim 1, (Appendix 29) The providing unit is When providing information, analyze your social media activity to tailor how information is provided to you 2. The system of claim 1, [Explanation of symbols]

[0182] 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 and extracts negative evaluations; A classification unit that classifies and organizes the negative evaluations extracted by the analysis unit; a providing unit that provides the information organized by the classification unit to a user. A system characterized by:

2. The collecting unit includes: Collect word-of-mouth data from online word-of-mouth or review sites 2. The system of claim 1 .

3. The analysis unit is Extracting negative reviews or complaints from review data 2. The system of claim 1 .

4. The providing unit is Provide users with classified and organized information in text format or in graphs and charts 2. The system of claim 1 .

5. The collecting unit includes: To estimate user sentiment and adjust the timing of collecting word-of-mouth data based on the estimated user sentiment.

2. The system of claim 1 .

6. The collecting unit includes: When collecting data, the system analyzes the user's past search history and selects the optimal collection method.

2. The system of claim 1 .

7. The collecting unit includes: At the time of collection, filtering is performed based on the user's current interests 2. The system of claim 1 .

8. The collecting unit includes: Estimate user sentiment and prioritize the review data to be collected based on the estimated user sentiment.

2. The system of claim 1 .

9. The collecting unit includes: When collecting data, the geographic location of the user is taken into consideration to prioritize collection of relevant review data.

2. The system of claim 1 .

Images