System

Abstract

An object of a system according to an embodiment is to extract useful information from a large amount of questionnaire data and propose an appropriate measure.SOLUTION: A system includes a questionnaire data collection part, a preprocessing part, a classification analysis part, a comment extraction part, and an improvement plan proposal part. The questionnaire data collection part collects questionnaire data. The preprocessing unit preprocesses the questionnaire data collected by the questionnaire data collection unit. The classification analysis unit classifies and analyzes the questionnaire data preprocessed by the preprocessing unit. The comment extraction unit extracts a useful comment from the data classified and analyzed by the classification analysis unit. The improvement plan proposal unit proposes an improvement plan based on the comment extracted by the comment extraction 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 an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

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

[0004] Conventional technology has had the problem of making it difficult to efficiently extract useful information from large amounts of survey data and derive appropriate measures.

[0005] The system according to the embodiment aims to extract useful information from a large amount of questionnaire data and propose appropriate measures. [Means for solving the problem]

[0006] The system according to the embodiment includes a questionnaire data collection unit, a preprocessing unit, a classification and analysis unit, a comment extraction unit, and an improvement plan proposal unit. The questionnaire data collection unit collects questionnaire data. The preprocessing unit preprocesses the questionnaire data collected by the questionnaire data collection unit. The classification and analysis unit classifies and analyzes the questionnaire data preprocessed by the preprocessing unit. The comment extraction unit extracts useful comments from the data classified and analyzed by the classification and analysis unit. The improvement plan proposal unit proposes an improvement plan based on the comments extracted by the comment extraction unit. [Effects of the Invention]

[0007] The system according to the embodiment can extract useful information from a large amount of questionnaire data and propose appropriate measures. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's 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 read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The survey analysis system according to the embodiment of the present invention is a system that efficiently analyzes survey data, understands what customers want, and proposes improvement measures that will lead to improved business performance. As a result, the survey analysis system can quickly implement improvement measures that meet the needs of customers.

[0029] A survey analysis system according to an embodiment includes a survey data collection unit, a preprocessing unit, a classification and analysis unit, a comment extraction unit, and an improvement plan proposal unit. The survey data collection unit collects survey data. For example, it collects free-form and multiple-choice responses from customers. The survey data collection unit can also collect data from online forms and paper documents. For example, data from online forms is automatically stored in a database. Paper documents are digitized using a scanner. The preprocessing unit preprocesses the collected survey data. For example, it removes noise and standardizes formats. The preprocessing unit can also unify different expressions with the same meaning. For example, it can unify "good" and "excellent." The classification and analysis unit classifies and analyzes the preprocessed survey data. For example, it can classify customer comments into "items that require improvement to improve business performance," "items that will damage the company's image if not improved," and "items that are merely opinions." The classification and analysis unit can also analyze the data using a clustering algorithm. For example, it uses K-means clustering. The comment extraction unit extracts useful comments from the data classified and analyzed by the classification and analysis unit. For example, the comment extraction unit extracts positive comments such as "This product is easy to use" and negative comments such as "This service needs improvement." The comment extraction unit can also extract comments using an emotion estimation function. For example, comments expressing positive emotions are preferentially extracted. The improvement plan proposal unit proposes an improvement plan based on the comments extracted by the comment extraction unit. For example, a specific action plan such as "Improve the user interface to further improve the usability of the product" is proposed. The improvement plan proposal unit can also propose an improvement plan using a generation AI. For example, the generation AI may make a proposal such as "Implement customer service training." This allows the survey analysis system according to the embodiment to efficiently analyze survey data, understand what customers want, and propose improvement measures that will lead to improved business performance. For example, this is expected to improve customer satisfaction and business performance.In addition, by responding quickly to negative feedback, you can prevent your company's image from being damaged.

[0030] The preprocessing unit can unify different expressions with the same meaning. For example, the preprocessing unit unifies different expressions with the same meaning. For example, the preprocessing unit unifies "good" and "great". The preprocessing unit can also unify synonyms. For example, the preprocessing unit can unify "quick" and "fast". The preprocessing unit can also unify abbreviations. For example, the preprocessing unit can unify "AI" and "artificial intelligence". This can improve the accuracy of the analysis.

[0031] The classification and analysis unit can classify customer comments into "items that need improvement to improve business performance," "items that will damage the company's image if not improved," and "items that are merely opinions." For example, the classification and analysis unit classifies customer comments into "items that need improvement to improve business performance," "items that will damage the company's image if not improved," and "items that are merely opinions." For example, a positive comment such as "This product is easy to use" is classified as "items that are merely opinions." A negative comment such as "This service needs improvement" is classified as "items that need improvement to improve business performance." The classification and analysis unit can also analyze data using a clustering algorithm. For example, K-means clustering is used. The classification and analysis unit can also analyze data using statistical analysis methods. For example, regression analysis is used. This allows for effective classification of customer comments.

[0032] The comment extraction unit can extract positive comments and negative comments. The comment extraction unit extracts, for example, positive comments such as "This product is easy to use." It also extracts negative comments such as "This service needs improvement." The comment extraction unit can also extract comments using an emotion estimation function. For example, it can preferentially extract comments that show positive emotions. It can also preferentially extract comments that show negative emotions. This makes it possible to grasp important feedback.

[0033] The improvement plan proposal unit can propose a specific action plan based on the comments. The improvement plan proposal unit proposes a specific action plan based on the comments, for example. For example, it proposes a specific action plan such as "Improve the user interface to further improve the usability of the product." It also proposes a specific action plan such as "Implement customer service training to further improve the response of staff." The improvement plan proposal unit can also propose an improvement plan using a generation AI. For example, the generation AI makes a suggestion such as "Implement customer service training." This makes it possible to propose specific improvement measures.

[0034] The survey data collection unit can convert a customer's voice input into text. For example, the survey data collection unit converts a customer's voice input into text. For example, a customer uses a smartphone or tablet to input voice, and the voice data is converted into text data in real time. The survey data collection unit can also convert voice data into text data using voice recognition technology. For example, voice recognition software automatically analyzes the voice and saves it as text. The survey data collection unit can also build a system in which text is displayed on a screen simultaneously with voice input. This makes it easier to collect survey data by converting voice input into text.

[0035] The preprocessing unit can integrate a customer's past purchase history and behavioral data. For example, the preprocessing unit collects a customer's past purchase history and integrates it with survey data. For example, the preprocessing unit complements background information for survey responses based on data on products and services the customer has purchased in the past. The preprocessing unit can also collect a customer's behavioral data and integrate it with survey data. For example, the preprocessing unit collects a customer's website browsing history and click data to complement background information for survey responses. The preprocessing unit can also combine a customer's past purchase history with behavioral data to perform more accurate data analysis. This enables more accurate data analysis.

[0036] The survey data collection unit can permit the uploading of images and videos. For example, the survey data collection unit allows customers to upload photos of products and videos of their usage when answering a survey. For example, a customer uploads a photo of a product they purchased, and the image data is analyzed. The survey data collection unit can also allow customers to upload videos of their usage and analyze the video data. For example, the content of the video is analyzed and an evaluation is made based on visual information. The survey data collection unit can also permit the uploading of images and videos, and can include visual information in the preprocessing. This allows visual information to be included in the preprocessing.

[0037] The preprocessing unit can automatically translate survey responses in different languages. For example, if a customer responds to a survey in a different language, the preprocessing unit uses automatic translation technology to translate the responses into a specified language. For example, the preprocessing unit translates a survey completed in English into Japanese. The preprocessing unit can also build an automatic translation system that supports multiple languages. For example, it can support multiple languages ​​such as English, Japanese, and Spanish. The preprocessing unit can also perform translation that takes into account technical terms and industry jargon to improve translation accuracy. This enables preprocessing that supports multiple languages.

[0038] The classification analysis unit can refer to related social media posts and reviews when analyzing customer comments. For example, when analyzing customer comments, the classification analysis unit collects related social media posts and reflects them in the analysis. For example, it collects posts from Twitter and Facebook and compares them with customer comments. The classification analysis unit can also collect data from related review sites and reflect them in the analysis. For example, it can collect Amazon reviews and compare them with customer comments. The classification analysis unit can also build a system that reflects social media posts and reviews in the analysis. This allows analysis to be performed on a wider data set.

[0039] The classification and analysis unit can compare customer comments with feedback from different industries or fields. For example, when analyzing customer comments, the classification and analysis unit collects and compares feedback from different industries. For example, feedback from the manufacturing industry and the service industry can be compared to obtain common insights. The classification and analysis unit can also collect feedback from different fields and reflect this in the analysis. For example, feedback from the medical industry and the education industry can be compared to obtain common insights. The classification and analysis unit can also build a system that reflects feedback from different industries or fields in the analysis. This makes it possible to obtain cross-industry insights.

[0040] The classification analysis unit can convert customer comments into visual notes or mind maps. For example, the classification analysis unit can convert customer comments into visual notes and visually display them. For example, the main points of the comments can be shown using diagrams or icons. The classification analysis unit can also convert customer comments into mind maps and visually display them. For example, the classification analysis unit can set a central theme and add subthemes and related nodes. The classification analysis unit can also build a system for creating visual notes or mind maps. This allows customer comments to be classified in a format that is visually easy to understand.

[0041] The comment extraction unit can refer to related industry news and trend information when extracting customer comments. For example, when extracting customer comments, the comment extraction unit collects related industry news and reflects it in the analysis. For example, the comment extraction unit identifies current and useful comments based on the latest industry news. The comment extraction unit can also collect trend information and reflect it in the analysis. For example, it can collect trend information from Google Trends or social media and compare it with customer comments. The comment extraction unit can also build a system that reflects industry news and trend information in the analysis. This makes it possible to identify current and useful comments.

[0042] The comment extraction unit can automatically translate customer comments into different languages. For example, the comment extraction unit can automatically translate customer comments into different languages ​​and extract useful comments from an international perspective. For example, the comment extraction unit can translate into multiple languages ​​such as English, Japanese, and Chinese. The comment extraction unit can also build a system that translates comments using automatic translation technology. For example, it can perform highly accurate translation using a translation algorithm. The comment extraction unit can also extract useful comments based on the translated comments. This makes it possible to extract useful comments from an international perspective.

[0043] The comment extraction unit can convert customer comments into visual notes or mind maps. For example, the comment extraction unit can convert customer comments into visual notes and visually display them. For example, the main points of the comments can be shown using diagrams or icons. The comment extraction unit can also convert customer comments into mind maps and visually display them. For example, a central theme can be set and subthemes and related nodes can be added. The comment extraction unit can also build a system for creating visual notes or mind maps. This makes it possible to extract customer comments in a format that is visually easy to understand.

[0044] The improvement plan proposal unit can apply the improvement plan to different industries and applications. For example, the improvement plan proposal unit can apply the improvement plan to a different industry to discover new market needs. For example, an improvement plan for the manufacturing industry can be applied to the service industry to find new business opportunities. The improvement plan proposal unit can also apply the improvement plan to a different application to discover new market needs. For example, an improvement plan for a specific product can be applied to another product to find new business opportunities. The improvement plan proposal unit can also build a system that applies the improvement plan to different industries and applications. This makes it possible to discover new market needs.

[0045] The improvement plan proposal unit can implement the improvement plan as a prototype. For example, the improvement plan proposal unit can implement the improvement plan as a prototype and introduce an agile method of improving it based on user feedback. For example, a prototype can be developed in a short period of time and user opinions can be reflected. The improvement plan proposal unit can also implement the prototype and improve it through a testing process. For example, a prototype can be created and user tests can be conducted. The improvement plan proposal unit can also build a system to be implemented as a prototype. This makes it possible to introduce an agile method of improving it based on feedback.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The survey analysis system can further include a purchase intention estimation unit that estimates a customer's purchasing intention. The purchase intention estimation unit, for example, analyzes the customer's past purchase history and survey response content to estimate the products or services that the customer is likely to purchase next. The purchase intention estimation unit can also estimate purchasing intention based on the customer's website browsing history and click data. For example, a survey related to a particular product can be sent to customers who frequently view a specific product page. The purchase intention estimation unit can also analyze the content of the customer's social media posts to estimate purchasing intention. This makes it possible to understand the customer's purchasing intention and implement targeted marketing measures.

[0048] The preprocessing unit may further include a reliability evaluation unit that evaluates the reliability of customer responses. The reliability evaluation unit, for example, checks the consistency and inconsistencies of the responses and calculates a reliability score. The reliability evaluation unit may also evaluate reliability based on the time of response and background information of the respondent. For example, it may focus on evaluating questionnaires answered in a short time or responses from respondents with specific attributes. The reliability evaluation unit may also evaluate reliability by comparing with past response history. This allows analysis to be performed based on highly reliable data.

[0049] The classification analysis unit can further classify customer comments based on a topic model. For example, it uses LDA (Latent Dirichlet Allocation) to classify customer comments into multiple topics. The classification analysis unit can also use a topic model to identify areas of customer interest. For example, it can extract a customer group that has many comments related to a specific topic. The classification analysis unit can also discover new topics using a topic model. This allows for a detailed understanding of customer areas of interest and the implementation of targeted measures.

[0050] The comment extraction unit can also refer to related industry news and trend information when extracting customer comments. For example, when extracting customer comments, it can identify current and useful comments based on the latest industry news. The comment extraction unit can also collect trend information and reflect it in the analysis. For example, it can collect trend information from Google Trends and social media and compare it with customer comments. The comment extraction unit can also build a system that reflects industry news and trend information in the analysis. This makes it possible to identify current and useful comments.

[0051] The improvement plan proposal unit can further propose improvement plans applicable to different industries or applications based on customer comments. For example, an improvement plan for the manufacturing industry can be applied to the service industry to find new business opportunities. The improvement plan proposal unit can also apply an improvement plan for a specific product to other products to discover new market needs. For example, a user interface improvement plan for specific software can be applied to other software. The improvement plan proposal unit can also build systems applicable to different industries or applications, thereby discovering new market needs.

[0052] The processing flow of the first embodiment will be briefly explained below.

[0053] Step 1: The survey data collection department collects survey data. For example, it collects free-form and multiple-choice responses from customers. The survey data collection department can also collect data from online forms and paper documents. Data from online forms is automatically saved in a database, and paper documents are digitized using a scanner. Step 2: The preprocessing section preprocesses the collected survey data. For example, it removes noise and standardizes the format. The preprocessing section can also unify different expressions with the same meaning. For example, it can unify "good" and "great." Step 3: The classification and analysis unit classifies and analyzes the preprocessed survey data. For example, customer comments can be classified into "items that require improvement to improve business performance," "items that will damage the company's image if not improved," and "items that are merely opinions." The classification and analysis unit can also analyze the data using a clustering algorithm. For example, it uses K-means clustering. Step 4: The comment extraction unit extracts useful comments from the data classified and analyzed by the classification and analysis unit. For example, it extracts positive comments such as "This product is easy to use" and negative comments such as "This service needs improvement." The comment extraction unit can also extract comments using an emotion estimation function. For example, it prioritizes the extraction of comments that show positive emotions. Step 5: The improvement plan proposal unit proposes an improvement plan based on the comments extracted by the comment extraction unit. For example, it proposes a specific action plan such as "improving the user interface to further improve the usability of the product." The improvement plan proposal unit can also use a generation AI to propose an improvement plan. For example, the generation AI may suggest "conduct customer service training."

[0054] (Example 2) The survey analysis system according to the embodiment of the present invention is a system that efficiently analyzes survey data, understands what customers want, and proposes improvement measures that will lead to improved business performance. As a result, the survey analysis system can quickly implement improvement measures that meet the needs of customers.

[0055] A survey analysis system according to an embodiment includes a survey data collection unit, a preprocessing unit, a classification and analysis unit, a comment extraction unit, and an improvement plan proposal unit. The survey data collection unit collects survey data. For example, it collects free-form and multiple-choice responses from customers. The survey data collection unit can also collect data from online forms and paper documents. For example, data from online forms is automatically stored in a database. Paper documents are digitized using a scanner. The preprocessing unit preprocesses the collected survey data. For example, it removes noise and standardizes formats. The preprocessing unit can also unify different expressions with the same meaning. For example, it can unify "good" and "excellent." The classification and analysis unit classifies and analyzes the preprocessed survey data. For example, it can classify customer comments into "items that require improvement to improve business performance," "items that will damage the company's image if not improved," and "items that are merely opinions." The classification and analysis unit can also analyze the data using a clustering algorithm. For example, it uses K-means clustering. The comment extraction unit extracts useful comments from the data classified and analyzed by the classification and analysis unit. For example, the comment extraction unit extracts positive comments such as "This product is easy to use" and negative comments such as "This service needs improvement." The comment extraction unit can also extract comments using an emotion estimation function. For example, comments expressing positive emotions are preferentially extracted. The improvement plan proposal unit proposes an improvement plan based on the comments extracted by the comment extraction unit. For example, a specific action plan such as "Improve the user interface to further improve the usability of the product" is proposed. The improvement plan proposal unit can also propose an improvement plan using a generation AI. For example, the generation AI may make a proposal such as "Implement customer service training." This allows the survey analysis system according to the embodiment to efficiently analyze survey data, understand what customers want, and propose improvement measures that will lead to improved business performance. For example, this is expected to improve customer satisfaction and business performance.In addition, by responding quickly to negative feedback, you can prevent your company's image from being damaged.

[0056] The preprocessing unit can unify different expressions with the same meaning. For example, the preprocessing unit unifies different expressions with the same meaning. For example, the preprocessing unit unifies "good" and "great". The preprocessing unit can also unify synonyms. For example, the preprocessing unit can unify "quick" and "fast". The preprocessing unit can also unify abbreviations. For example, the preprocessing unit can unify "AI" and "artificial intelligence". This can improve the accuracy of the analysis.

[0057] The classification and analysis unit can classify customer comments into "items that need improvement to improve business performance," "items that will damage the company's image if not improved," and "items that are merely opinions." For example, the classification and analysis unit classifies customer comments into "items that need improvement to improve business performance," "items that will damage the company's image if not improved," and "items that are merely opinions." For example, a positive comment such as "This product is easy to use" is classified as "items that are merely opinions." A negative comment such as "This service needs improvement" is classified as "items that need improvement to improve business performance." The classification and analysis unit can also analyze data using a clustering algorithm. For example, K-means clustering is used. The classification and analysis unit can also analyze data using statistical analysis methods. For example, regression analysis is used. This allows for effective classification of customer comments.

[0058] The comment extraction unit can extract positive comments and negative comments. The comment extraction unit extracts, for example, positive comments such as "This product is easy to use." It also extracts negative comments such as "This service needs improvement." The comment extraction unit can also extract comments using an emotion estimation function. For example, it can preferentially extract comments that show positive emotions. It can also preferentially extract comments that show negative emotions. This makes it possible to grasp important feedback.

[0059] The improvement plan proposal unit can propose a specific action plan based on the comments. The improvement plan proposal unit proposes a specific action plan based on the comments, for example. For example, it proposes a specific action plan such as "Improve the user interface to further improve the usability of the product." It also proposes a specific action plan such as "Implement customer service training to further improve the response of staff." The improvement plan proposal unit can also propose an improvement plan using a generation AI. For example, the generation AI makes a suggestion such as "Implement customer service training." This makes it possible to propose specific improvement measures.

[0060] The survey data collection unit can convert a customer's voice input into text. For example, the survey data collection unit converts a customer's voice input into text. For example, a customer uses a smartphone or tablet to input voice, and the voice data is converted into text data in real time. The survey data collection unit can also convert voice data into text data using voice recognition technology. For example, voice recognition software automatically analyzes the voice and saves it as text. The survey data collection unit can also build a system in which text is displayed on a screen simultaneously with voice input. This makes it easier to collect survey data by converting voice input into text.

[0061] The preprocessing unit can integrate a customer's past purchase history and behavioral data. For example, the preprocessing unit collects a customer's past purchase history and integrates it with survey data. For example, the preprocessing unit complements background information for survey responses based on data on products and services the customer has purchased in the past. The preprocessing unit can also collect a customer's behavioral data and integrate it with survey data. For example, the preprocessing unit collects a customer's website browsing history and click data to complement background information for survey responses. The preprocessing unit can also combine a customer's past purchase history with behavioral data to perform more accurate data analysis. This enables more accurate data analysis.

[0062] The preprocessing unit can analyze the emotions of customers when they answer questions. For example, the preprocessing unit captures the facial expressions of customers when they answer a questionnaire using a camera and analyzes their emotions from the facial expressions using emotion estimation technology. For example, if a customer answers with a smile, the positive emotion is reflected in the data. The preprocessing unit can also record the customer's voice and analyze their emotions using voice analysis technology. For example, it can analyze the tone and speed of the voice and calculate an emotion score. The preprocessing unit can also collect the customer's biometric data (heart rate and electrodermal activity) using a sensor and analyze their emotions using emotion estimation technology. For example, it can calculate an emotion score based on heart rate fluctuations. This makes it possible to preprocess data based on the customer's emotions.

[0063] The survey data collection unit can permit the uploading of images and videos. For example, the survey data collection unit allows customers to upload photos of products and videos of their usage when answering a survey. For example, a customer uploads a photo of a product they purchased, and the image data is analyzed. The survey data collection unit can also allow customers to upload videos of their usage and analyze the video data. For example, the content of the video is analyzed and an evaluation is made based on visual information. The survey data collection unit can also permit the uploading of images and videos, and can include visual information in the preprocessing. This allows visual information to be included in the preprocessing.

[0064] The preprocessing unit can automatically translate survey responses in different languages. For example, if a customer responds to a survey in a different language, the preprocessing unit uses automatic translation technology to translate the responses into a specified language. For example, the preprocessing unit translates a survey completed in English into Japanese. The preprocessing unit can also build an automatic translation system that supports multiple languages. For example, it can support multiple languages ​​such as English, Japanese, and Spanish. The preprocessing unit can also perform translation that takes into account technical terms and industry jargon to improve translation accuracy. This enables preprocessing that supports multiple languages.

[0065] The classification analysis unit can use the generation AI to classify customer comments based on the intensity and type of emotion. For example, the classification analysis unit uses the generation AI to classify customer comments based on the intensity of emotion. For example, it classifies comments into very positive comments, moderately positive comments, and negative comments. The classification analysis unit can also classify comments based on the type of emotion. For example, it can classify comments based on emotions such as joy, sadness, and anger. The classification analysis unit can also use the generation AI to analyze the intensity and type of emotion and build a system that classifies comments. This makes it possible to classify customer comments based on the intensity and type of emotion.

[0066] The classification analysis unit can refer to related social media posts and reviews when analyzing customer comments. For example, when analyzing customer comments, the classification analysis unit collects related social media posts and reflects them in the analysis. For example, it collects posts from Twitter and Facebook and compares them with customer comments. The classification analysis unit can also collect data from related review sites and reflect them in the analysis. For example, it can collect Amazon reviews and compare them with customer comments. The classification analysis unit can also build a system that reflects social media posts and reviews in the analysis. This allows analysis to be performed on a wider data set.

[0067] The classification and analysis unit can analyze the emotional nuances of customer comments using the emotion estimation function. The classification and analysis unit, for example, analyzes the emotional nuances of customer comments using the emotion estimation function. For example, it analyzes the subtle emotions expressed by customers in their comments and classifies them based on those emotions. The classification and analysis unit can also analyze the emotional nuances of comments using an emotion estimation algorithm. For example, it calculates an emotion score for customer comments and classifies them based on that score. The classification and analysis unit can also build a system that analyzes the emotional nuances of comments using the emotion estimation function. This makes it possible to analyze the emotional nuances of customer comments.

[0068] The classification and analysis unit can compare customer comments with feedback from different industries or fields. For example, when analyzing customer comments, the classification and analysis unit collects and compares feedback from different industries. For example, feedback from the manufacturing industry and the service industry can be compared to obtain common insights. The classification and analysis unit can also collect feedback from different fields and reflect this in the analysis. For example, feedback from the medical industry and the education industry can be compared to obtain common insights. The classification and analysis unit can also build a system that reflects feedback from different industries or fields in the analysis. This makes it possible to obtain cross-industry insights.

[0069] The classification analysis unit can convert customer comments into visual notes or mind maps. For example, the classification analysis unit can convert customer comments into visual notes and visually display them. For example, the main points of the comments can be shown using diagrams or icons. The classification analysis unit can also convert customer comments into mind maps and visually display them. For example, the classification analysis unit can set a central theme and add subthemes and related nodes. The classification analysis unit can also build a system for creating visual notes or mind maps. This allows customer comments to be classified in a format that is visually easy to understand.

[0070] The classification and analysis unit can collect other customers' emotional reactions to the customer's comments using the emotion estimation function. The classification and analysis unit, for example, uses the emotion estimation function to collect other customers' emotional reactions to the customer's comments. For example, it analyzes positive and negative reactions to the comments. The classification and analysis unit can also collect other customers' emotional reactions using an emotion estimation algorithm. For example, it analyzes the degree of empathy for the customer's comments and classifies them based on the results. The classification and analysis unit can also build a system that collects other customers' emotional reactions using the emotion estimation function. This makes it possible to perform classification based on the emotional reactions of other customers to the customer's comments.

[0071] The comment extraction unit can use generation AI to extract comments from customers that show particularly strong emotional reactions. For example, the comment extraction unit uses generation AI to extract comments from customers that show particularly strong emotional reactions. For example, it may preferentially extract very positive comments or very negative comments. The comment extraction unit can also extract comments based on emotional intensity. For example, it may preferentially extract comments with a high emotional score. The comment extraction unit can also build a system that uses generation AI to extract comments that show particularly strong emotional reactions. This makes it possible to extract comments with a strong emotional impact.

[0072] The comment extraction unit can refer to related industry news and trend information when extracting customer comments. For example, when extracting customer comments, the comment extraction unit collects related industry news and reflects it in the analysis. For example, the comment extraction unit identifies current and useful comments based on the latest industry news. The comment extraction unit can also collect trend information and reflect it in the analysis. For example, it can collect trend information from Google Trends or social media and compare it with customer comments. The comment extraction unit can also build a system that reflects industry news and trend information in the analysis. This makes it possible to identify current and useful comments.

[0073] The comment extraction unit can evaluate the emotional value of customer comments using the emotion estimation function. The comment extraction unit, for example, evaluates the emotional value of customer comments using the emotion estimation function. For example, comments with high emotional value can be identified based on the emotion score of the comment. The comment extraction unit can also evaluate the value of comments based on the intensity or type of emotion. For example, very positive comments or very negative comments can be preferentially evaluated. The comment extraction unit can also build a system that evaluates the emotional value of comments using the emotion estimation function. This makes it possible to extract useful comments based on emotion.

[0074] The comment extraction unit can automatically translate customer comments into different languages. For example, the comment extraction unit can automatically translate customer comments into different languages ​​and extract useful comments from an international perspective. For example, the comment extraction unit can translate into multiple languages ​​such as English, Japanese, and Chinese. The comment extraction unit can also build a system that translates comments using automatic translation technology. For example, it can perform highly accurate translation using a translation algorithm. The comment extraction unit can also extract useful comments based on the translated comments. This makes it possible to extract useful comments from an international perspective.

[0075] The comment extraction unit can convert customer comments into visual notes or mind maps. For example, the comment extraction unit can convert customer comments into visual notes and visually display them. For example, the main points of the comments can be shown using diagrams or icons. The comment extraction unit can also convert customer comments into mind maps and visually display them. For example, a central theme can be set and subthemes and related nodes can be added. The comment extraction unit can also build a system for creating visual notes or mind maps. This makes it possible to extract customer comments in a format that is visually easy to understand.

[0076] The comment extraction unit can use the emotion estimation function to collect other customers' emotional reactions to the customer's comments. The comment extraction unit, for example, uses the emotion estimation function to collect other customers' emotional reactions to the customer's comments. For example, it analyzes positive and negative reactions to the comments. The comment extraction unit can also collect other customers' emotional reactions using an emotion estimation algorithm. For example, it analyzes the degree of empathy for the customer's comments and extracts comments based on the results. The comment extraction unit can also build a system that uses the emotion estimation function to collect other customers' emotional reactions. This makes it possible to extract comments that are likely to be emotionally relatable.

[0077] The improvement plan proposal unit can use the generation AI to propose an improvement plan based on emotional insights into customer comments. The improvement plan proposal unit, for example, uses the generation AI to propose an improvement plan based on emotional insights into customer comments. For example, based on comments that show positive emotions, it proposes specific actions to improve customer satisfaction. The improvement plan proposal unit can also propose specific actions to resolve issues based on comments that show negative emotions. For example, it proposes specific improvement measures to resolve customer dissatisfaction. The improvement plan proposal unit can also build a system that uses the generation AI to propose an improvement plan based on emotional insights. This makes it possible to propose improvement plans based on emotions.

[0078] The improvement plan proposal unit can predict the emotional response of a customer using the emotion estimation function. The improvement plan proposal unit, for example, uses the emotion estimation function to predict the emotional response of a customer and proposes an improvement plan based on the result. For example, it proposes specific actions to elicit positive emotions. The improvement plan proposal unit can also propose specific actions to avoid negative emotions. For example, it proposes specific improvement measures to resolve customer dissatisfaction. The improvement plan proposal unit can also build a system that predicts the emotional response of a customer using the emotion estimation function. This makes it possible to propose an improvement plan based on emotions.

[0079] The improvement plan proposal unit can apply the improvement plan to different industries and applications. For example, the improvement plan proposal unit can apply the improvement plan to a different industry to discover new market needs. For example, an improvement plan for the manufacturing industry can be applied to the service industry to find new business opportunities. The improvement plan proposal unit can also apply the improvement plan to a different application to discover new market needs. For example, an improvement plan for a specific product can be applied to another product to find new business opportunities. The improvement plan proposal unit can also build a system that applies the improvement plan to different industries and applications. This makes it possible to discover new market needs.

[0080] The improvement plan proposal unit can implement the improvement plan as a prototype. For example, the improvement plan proposal unit can implement the improvement plan as a prototype and introduce an agile method of improving it based on user feedback. For example, a prototype can be developed in a short period of time and user opinions can be reflected. The improvement plan proposal unit can also implement the prototype and improve it through a testing process. For example, a prototype can be created and user tests can be conducted. The improvement plan proposal unit can also build a system to be implemented as a prototype. This makes it possible to introduce an agile method of improving it based on feedback.

[0081] The improvement plan proposal unit can use the emotion estimation function to monitor the customer's emotional response to the improvement plan in real time. The improvement plan proposal unit, for example, develops a system that uses the emotion estimation function to monitor the customer's emotional response to the improvement plan in real time. For example, the improvement plan proposal unit analyzes the customer's facial expressions and voice and calculates an emotion score. The improvement plan proposal unit can also monitor the customer's emotional response in real time and continuously search for an optimal plan. For example, the improvement plan proposal unit adjusts the improvement plan based on the customer's emotional response. The improvement plan proposal unit can also build a system that uses the emotion estimation function to monitor the customer's emotional response in real time. This makes it possible to continuously search for an optimal plan.

[0082] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0083] The survey analysis system can further include a purchase intention estimation unit that estimates a customer's purchasing intention. The purchase intention estimation unit, for example, analyzes the customer's past purchase history and survey response content to estimate the products or services that the customer is likely to purchase next. The purchase intention estimation unit can also estimate purchasing intention based on the customer's website browsing history and click data. For example, a survey related to a particular product can be sent to customers who frequently view a specific product page. The purchase intention estimation unit can also analyze the content of the customer's social media posts to estimate purchasing intention. This makes it possible to understand the customer's purchasing intention and implement targeted marketing measures.

[0084] The preprocessing unit may further include a reliability evaluation unit that evaluates the reliability of customer responses. The reliability evaluation unit, for example, checks the consistency and inconsistencies of the responses and calculates a reliability score. The reliability evaluation unit may also evaluate reliability based on the time of response and background information of the respondent. For example, it may focus on evaluating questionnaires answered in a short time or responses from respondents with specific attributes. The reliability evaluation unit may also evaluate reliability by comparing with past response history. This allows analysis to be performed based on highly reliable data.

[0085] The classification analysis unit can further classify customer comments based on a topic model. For example, it uses LDA (Latent Dirichlet Allocation) to classify customer comments into multiple topics. The classification analysis unit can also use a topic model to identify areas of customer interest. For example, it can extract a customer group that has many comments related to a specific topic. The classification analysis unit can also discover new topics using a topic model. This allows for a detailed understanding of customer areas of interest and the implementation of targeted measures.

[0086] The comment extraction unit can also refer to related industry news and trend information when extracting customer comments. For example, when extracting customer comments, it can identify current and useful comments based on the latest industry news. The comment extraction unit can also collect trend information and reflect it in the analysis. For example, it can collect trend information from Google Trends and social media and compare it with customer comments. The comment extraction unit can also build a system that reflects industry news and trend information in the analysis. This makes it possible to identify current and useful comments.

[0087] The improvement plan proposal unit can further propose improvement plans applicable to different industries or applications based on customer comments. For example, an improvement plan for the manufacturing industry can be applied to the service industry to find new business opportunities. The improvement plan proposal unit can also apply an improvement plan for a specific product to other products to discover new market needs. For example, a user interface improvement plan for specific software can be applied to other software. The improvement plan proposal unit can also build systems applicable to different industries or applications, thereby discovering new market needs.

[0088] The survey analysis system may further include a dynamic question change unit that estimates the customer's emotions and dynamically changes the content of the survey questions based on the estimated emotions. For example, if a customer expresses negative emotions, a follow-up question corresponding to that emotion may be added. The dynamic question change unit may also change the order of questions based on the customer's emotions. For example, if a customer expresses positive emotions, a question requesting more detailed feedback may be added. The dynamic question change unit may also adjust the difficulty of the questions based on the customer's emotions. This allows for flexible surveys to be conducted according to the customer's emotions.

[0089] The preprocessing unit can further analyze the emotions of the customer when answering a question and evaluate the reliability of the answer based on those emotions. For example, if the customer shows positive emotions, the reliability of the answer can be highly evaluated. The preprocessing unit can also evaluate the reliability of the answer based on the customer's emotion score. For example, it can focus on analyzing answers with high emotion scores. The preprocessing unit can also build a system that evaluates the reliability of the answer based on the customer's emotions. This makes it possible to evaluate reliability based on emotions.

[0090] The classification analysis unit can further classify customer comments based on the intensity and type of emotion. For example, it can classify comments into very positive comments, moderately positive comments, and negative comments. The classification analysis unit can also classify comments based on the type of emotion. For example, it can classify comments based on emotions such as joy, sadness, and anger. The classification analysis unit can also analyze the intensity and type of emotion and build a system for classifying comments. This makes it possible to classify customer comments based on the intensity and type of emotion.

[0091] The comment extraction unit can further evaluate the emotional value of customer comments and extract comments based on that value. For example, comments with high emotional value can be identified based on the emotional score of the comments. The comment extraction unit can also evaluate the value of comments based on the intensity or type of emotion. For example, very positive comments or very negative comments can be prioritized. The comment extraction unit can also build a system for evaluating emotional value. This makes it possible to extract useful comments based on emotion.

[0092] The improvement plan proposal unit can further predict the emotional response of the customer and propose an improvement plan based on that response. For example, it can propose specific actions to elicit positive emotions. The improvement plan proposal unit can also propose specific actions to avoid negative emotions. For example, it can propose specific improvement measures to resolve customer dissatisfaction. The improvement plan proposal unit can also build a system to predict emotional responses. This makes it possible to propose an improvement plan based on emotions.

[0093] The processing flow of the second embodiment will be briefly explained below.

[0094] Step 1: The survey data collection department collects survey data. For example, it collects free-form and multiple-choice responses from customers. The survey data collection department can also collect data from online forms and paper documents. Data from online forms is automatically saved in a database, and paper documents are digitized using a scanner. Step 2: The preprocessing section preprocesses the collected survey data. For example, it removes noise and standardizes the format. The preprocessing section can also unify different expressions with the same meaning. For example, it can unify "good" and "great." Step 3: The classification and analysis unit classifies and analyzes the preprocessed survey data. For example, customer comments can be classified into "items that require improvement to improve business performance," "items that will damage the company's image if not improved," and "items that are merely opinions." The classification and analysis unit can also analyze the data using a clustering algorithm. For example, it uses K-means clustering. Step 4: The comment extraction unit extracts useful comments from the data classified and analyzed by the classification and analysis unit. For example, it extracts positive comments such as "This product is easy to use" and negative comments such as "This service needs improvement." The comment extraction unit can also extract comments using an emotion estimation function. For example, it prioritizes the extraction of comments that show positive emotions. Step 5: The improvement plan proposal unit proposes an improvement plan based on the comments extracted by the comment extraction unit. For example, it proposes a specific action plan such as "improving the user interface to further improve the usability of the product." The improvement plan proposal unit can also use a generation AI to propose an improvement plan. For example, the generation AI may suggest "conduct customer service training."

[0095] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0096] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0097] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0098] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0099] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0100] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0101] 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.

[0102] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0103] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0104] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0105] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0106] 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.

[0107] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0108] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0109] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0111] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0112] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0113] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0114] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0115] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0116] 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.

[0117] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0119] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0120] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0121] 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.

[0122] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0123] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0124] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0125] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0127] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0128] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0129] 7, the 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.

[0130] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0131] 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.

[0132] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0134] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0135] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0136] 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.

[0137] 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.

[0138] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0139] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0140] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0141] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0143] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0144] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0145] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0146] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0147] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0148] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0149] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0150] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0151] 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.

[0152] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0153] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0154] 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.

[0155] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0156] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0157] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0158] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0159] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0160] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0161] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0162] 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 survey data collection unit that collects survey data; a preprocessing unit that preprocesses the questionnaire data collected by the questionnaire data collection unit; a classification and analysis unit that classifies and analyzes the questionnaire data preprocessed by the preprocessing unit; a comment extraction unit that extracts useful comments from the data classified and analyzed by the classification analysis unit; an improvement plan proposal unit that proposes an improvement plan based on the comments extracted by the comment extraction unit. A system characterized by:

2. The questionnaire data collection unit Convert customer voice input to text 2. The system of claim 1.

3. The classification analysis unit Classify customer comments into "things that need improvement to improve business performance," "things that will damage the company's image if not improved," and "things that are just opinions" 2. The system of claim 1.

4. The comment extraction unit Extracting positive and negative comments 2. The system of claim 1.

5. The pre-treatment unit Automatically translate survey responses in said different languages 2. The system of claim 1.

6. The classification analysis unit Use generative AI to categorize customer comments based on intensity and type of sentiment 2. The system of claim 1.

7. The comment extraction unit Using generative AI to extract customer comments that elicit particularly strong emotional responses 2. The system of claim 1.

8. The improvement plan proposal unit Use generative AI to suggest improvement plans based on emotional insights from customer comments 2. The system of claim 1.

Images