System

Abstract

An object of a system according to an embodiment is to eliminate digital divide in a company and activate communication between employees.SOLUTION: A system according to an embodiment includes a conversation analysis unit, a topic extraction unit, a visualization unit, and a display unit. The conversation analysis unit analyzes a conversation of the communication tool in real time. The topic extraction unit extracts a hot topic from the conversation analyzed by the conversation analysis unit. The visualization part expresses the size of the subject of the topic extracted by the topic extraction part by the size of bubbles. The display unit displays the bubbles represented by the visualization unit in chronological order.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] With conventional technology, there was an information gap within the company, which led to issues such as smooth communication between employees.

[0005] The system according to the embodiment aims to eliminate information gaps within a company and stimulate communication between employees. [Means for solving the problem]

[0006] The system according to the embodiment includes a conversation analysis unit, a topic extraction unit, a visualization unit, and a display unit. The conversation analysis unit analyzes conversations on a communication tool in real time. The topic extraction unit extracts topics of interest from the conversation analyzed by the conversation analysis unit. The visualization unit represents the size of the topic extracted by the topic extraction unit as the size of a bubble. The display unit displays the bubbles represented by the visualization unit in chronological order. [Effects of the Invention]

[0007] The system according to the embodiment can eliminate information gaps within a company and stimulate communication between employees. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The digital divide bridging system according to an embodiment of the present invention is a system that analyzes conversations on communication tools in real time, uses a generation AI to extract trending topics, expresses the size of the topics as bubbles, and displays them in chronological order. As a result, the digital divide bridging system can eliminate the digital divide within a company, stimulate communication among employees, improve business efficiency, and promote corporate growth.

[0029] A system for bridging the digital divide according to an embodiment includes a conversation analysis unit, a topic extraction unit, a visualization unit, and a display unit. The conversation analysis unit analyzes conversations on a communication tool in real time. For example, the conversation analysis unit analyzes the content of the conversation using natural language processing technology. The conversation analysis unit can also convert audio data into text data using speech recognition technology. The conversation analysis unit can also understand the context of the conversation and extract important topics. For example, the conversation analysis unit analyzes the flow and context of the conversation and scores the importance of the topic. The topic extraction unit extracts topics that are being discussed from the conversation analyzed by the conversation analysis unit. For example, the topic extraction unit extracts topics using keyword frequency and co-occurrence network analysis. The topic extraction unit can also automatically recognize technical terms and industry-specific words to improve the accuracy of topic extraction. The visualization unit represents the size of the topic of the topic extracted by the topic extraction unit using the size of bubbles. For example, the visualization unit can also represent the size of the topic using the color and shape of the bubbles to add visual variety. The visualization unit can also visualize differences in interest within an organization by displaying the size of a topic using different colors for each employee's job title or department. The display unit displays the bubbles represented by the visualization unit in chronological order. For example, the display unit may make the chronological display interactive, allowing a user to select a specific period and view details. The display unit can also add trend lines to the chronological display to show how a specific topic developed. This allows the digital divide bridging system according to the embodiment to bridge the digital divide within a company, stimulate employee communication, improve business efficiency, and promote corporate growth. For example, the digital divide bridging system shares important internal information with all employees, supporting rapid decision-making. The digital divide bridging system also promotes communication between employees and improves teamwork. The digital divide bridging system also improves business efficiency and promotes corporate growth.

[0030] The conversation analysis unit understands the context of the conversation and can automatically rank the importance of topics. For example, the conversation analysis unit uses a generative AI to analyze the context of the conversation and score the importance of each topic. For example, conversations about project progress and problems may be ranked high. The conversation analysis unit also automatically ranks the importance of topics based on keywords and phrases that appear frequently in the conversation. For example, it may prioritize topics related to important meetings and deadlines. The conversation analysis unit also analyzes the flow and context of the conversation and dynamically ranks the importance of topics. For example, it may assign a high score to conversations about urgent issues or important decisions. This allows important information to be prioritized by automatically ranking the importance of topics.

[0031] The conversation analysis unit can automatically recognize technical terms and industry-specific words, improving the accuracy of topic extraction. For example, the conversation analysis unit uses a generative AI to automatically recognize technical terms and industry-specific words, improving the accuracy of topic extraction. For example, it accurately recognizes technical terms and marketing terms. The conversation analysis unit also compares the technical terms used in conversation with a dictionary database to improve the accuracy of topic extraction. For example, it accurately extracts medical and legal terms. The conversation analysis unit also automatically recognizes industry-specific words and abbreviations, improving the accuracy of topic extraction. For example, it accurately analyzes abbreviations in the IT industry and technical terms in the financial industry. This improves the accuracy of topic extraction by recognizing technical terms and industry-specific words.

[0032] The conversation analysis unit can expand the scope of conversation analysis to include not only text but also audio and video conference content, enabling multimodal analysis. For example, the conversation analysis unit can expand the scope of conversation analysis to audio data and extract topics using speech recognition technology. For example, it can analyze audio data from video conferences and extract important topics. The conversation analysis unit can also analyze video conference video data and extract topics based on the speaker's facial expressions and gestures. For example, it can analyze changes in the speaker's facial expression and extract emotionally important topics. The conversation analysis unit can also integrate text, audio, and video data to perform multimodal analysis. For example, it can extract topics by combining the content of the conversation with the speaker's facial expressions. This allows for the analysis of audio and video conference content, enabling a wider variety of information to be grasped.

[0033] The conversation analysis unit may have a multilingual function that translates conversations in different languages ​​in real time and extracts topics. The conversation analysis unit, for example, translates conversations in different languages ​​in real time and extracts topics. For example, it translates a conversation in English into Japanese and extracts topics. The conversation analysis unit also uses a multilingual translation function to analyze conversations in different languages ​​and extract topics. For example, it translates conversations in French or Chinese and extracts topics. The conversation analysis unit also uses a real-time translation function to analyze conversations in different languages ​​and extract topics. For example, it translates conversations at international conferences and extracts important topics. This makes it possible to share information globally by analyzing conversations in different languages.

[0034] The visualization unit can also express the size of a topic with the color and shape of the bubble, providing visual diversity. For example, the visualization unit expresses the size of a topic with the color of the bubble, making it easier to visually distinguish between topics. For example, important topics are displayed in red, and general topics in blue. The visualization unit also visually expresses the type and importance of a topic by changing the shape of the bubble. For example, important topics are displayed in a star shape, and general topics are displayed in a circle. The visualization unit also combines the color and shape of the bubble to express the size of a topic in a variety of visual ways. For example, important topics are displayed in a red star shape, and general topics are displayed in a blue circle. In this way, expressing the size of a topic with color and shape makes it easier to visually distinguish between topics.

[0035] The visualization unit displays the size of a topic in a different color for each employee's job title or department, making it possible to visualize differences in interest within an organization. For example, the visualization unit displays the size of a topic in a different color for each employee's job title, making it possible to visualize differences in interest within an organization. For example, topics for managers are displayed in red, and topics for regular employees are displayed in blue. The visualization unit also displays the size of a topic in a different color for each department, making it possible to visualize differences in interest within an organization. For example, topics for the sales department are displayed in green, and topics for the engineering department are displayed in yellow. The visualization unit also displays the size of a topic in a different color for each job title or department, making it possible to visually grasp differences in interest within an organization. For example, colors are set according to a combination of job title and department, and topics are displayed. In this way, by displaying different colors for each job title or department, it is possible to visually grasp differences in interest within an organization.

[0036] The visualization unit can represent the size of a topic using 3D graphics to enable a more intuitive understanding. For example, the visualization unit represents the size of a topic using 3D graphics to enable a user to intuitively understand the size visually. For example, important topics are displayed as large 3D objects. The visualization unit also uses 3D graphics to represent the size of a topic in three dimensions. For example, the size of the 3D object is changed depending on the importance of the topic. The visualization unit also represents the size of a topic using 3D graphics to enable a user to intuitively understand the size visually. For example, the 3D object can be rotated to grasp the overall picture. In this way, the size of a topic can be intuitively understood by representing it using 3D graphics.

[0037] The visualization unit can display the size of a topic in conjunction with other data (for example, project progress or sales data). For example, the visualization unit displays the size of a topic in conjunction with the progress of a project. For example, topics about projects that are behind schedule are displayed in a larger size. The visualization unit also displays the size of a topic in conjunction with sales data. For example, topics about products with high sales are displayed in a larger size. The visualization unit also displays the size of a topic in conjunction with other data (for example, customer satisfaction or market share). For example, topics about services with high customer satisfaction are displayed in a larger size. In this way, by displaying the size of a topic in conjunction with other data, the relevance can be visually grasped.

[0038] The display unit may make the time series display interactive and include a function that allows the user to select a specific period to view details. The display unit, for example, makes the time series display interactive and adds a function that allows the user to select a specific period to view details. For example, a specific period may be selected using a slider. The display unit may also use an interactive time series display to allow the user to view details of topics within a specific period. For example, detailed information may be displayed by clicking. The display unit may also make the time series display interactive and add a function that allows the user to select a specific period to view details. For example, a zoom-in / zoom-out function may be used to enlarge a specific period. This allows the user to select a specific period to view details, enabling the user to quickly grasp information of interest.

[0039] The display unit can add trend lines to the time series display to show how a particular topic has developed. For example, the display unit adds trend lines to the time series display to visually show how a particular topic has developed. For example, it displays changes in the importance of a topic in a line graph. The display unit also adds trend lines to the time series display to show the development of a topic, allowing a user to grasp the evolution of the topic at a glance. For example, it displays the frequency of appearance of a topic in a line graph. The display unit also adds trend lines to the time series display to show how a particular topic has developed. For example, it displays changes in the sentiment score of a topic in a line graph. In this way, by adding trend lines, the development of a particular topic can be visually grasped.

[0040] The display unit may have a function that allows the time series display to be filtered by different departments or projects. For example, the display unit adds a function that allows the time series display to be filtered by different departments. For example, a filter that displays only topics related to the sales department is provided. The display unit also adds a function that allows the time series display to be filtered by project. For example, only topics related to a specific project are displayed. The display unit also adds a function that allows the time series display to be filtered by department or project, allowing the user to narrow down topics of interest. For example, a combination of multiple filters can be displayed. This allows the user to quickly grasp information of interest by filtering by different departments or projects.

[0041] The display unit can display the time series display in conjunction with other business indicators (e.g., sales or customer satisfaction). For example, the display unit displays the time series display in conjunction with sales data. For example, it displays the fluctuations in sales and the size of the buzz simultaneously. The display unit also displays the time series display in conjunction with customer satisfaction data. For example, it displays the fluctuations in customer satisfaction and the size of the buzz simultaneously. The display unit also displays the time series display in conjunction with other business indicators (e.g., employee productivity or market share). For example, it displays the fluctuations in employee productivity and the size of the buzz simultaneously. In this way, by linking the time series display with other business indicators, the correlation can be visually grasped.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The system for bridging the digital divide can further collect user behavioral data and include a behavioral analysis unit. The behavioral analysis unit, for example, analyzes the user's click and scroll patterns to identify topics in which the user is interested. For example, the user's level of interest can be evaluated based on the number of clicks and time spent on a particular topic. The behavioral analysis unit can also dynamically adjust the importance of topics based on the user's behavioral data. For example, topics that the user accesses frequently can be ranked with a high score. This makes it possible to utilize user behavioral data to extract topics with greater accuracy.

[0044] The system for bridging the digital divide can further collect user feedback and include a feedback analysis unit. The feedback analysis unit, for example, analyzes comments and ratings provided by users and adjusts the importance of topics. For example, it may preferentially display topics that users have given high ratings. The feedback analysis unit can also improve the accuracy of topic extraction based on user feedback. For example, it may correct errors pointed out by users and improve the topic extraction algorithm. This makes it possible to utilize user feedback to provide more useful information to users.

[0045] The digital divide bridging system can further integrate external data sources and include an external data analysis unit. The external data analysis unit, for example, analyzes news articles and social media posts and associates them with internal company topics. For example, it can compare the latest industry news with internal company topics and extract highly relevant information. The external data analysis unit can also adjust the importance of topics based on external data. For example, it can prioritize the display of topics that are trending externally. This allows the system to utilize external data to provide a wider range of information.

[0046] The digital divide bridging system can further integrate user schedule data and include a schedule analysis unit. The schedule analysis unit, for example, analyzes the user's calendar information and extracts topics related to important meetings and events. For example, it extracts topics based on the meeting agenda and provides related information in advance. The schedule analysis unit can also adjust the timing of topic display based on the user's schedule. For example, it can display related topics just before a meeting. This makes it possible to provide information tailored to the user's schedule.

[0047] The system for bridging the digital divide can further integrate user profile data and include a profile analysis unit. The profile analysis unit extracts highly relevant topics based on the user's job role or field of expertise, for example. For example, it may prioritize displaying technology-related topics to an engineer. The profile analysis unit can also provide topics tailored to the user's individual interests based on the user's past behavioral data. For example, it may prioritize displaying topics that the user has frequently accessed in the past. This makes it possible to provide personalized information based on the user's profile.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The conversation analysis unit analyzes conversations in communication tools in real time. For example, it uses natural language processing technology to analyze the content of the conversation and speech recognition technology to convert the voice data into text data. It can also understand the context of the conversation and extract important topics. For example, it analyzes the flow and context of the conversation and scores the importance of the topic. Step 2: The topic extraction unit extracts popular topics from the conversations analyzed by the conversation analysis unit. For example, it extracts topics using keyword frequency and co-occurrence network analysis, and automatically recognizes technical terms and industry-specific words to improve the accuracy of topic extraction. Step 3: The visualization unit expresses the size of the topics extracted by the topic extraction unit as bubbles. For example, the size of the topic can be expressed by the color and shape of the bubbles, providing visual diversity. It is also possible to visualize differences in interest within an organization by displaying different colors according to employee position or department. Step 4: The display unit displays the bubbles represented by the visualization unit in a chronological order. For example, the timeline display can be made interactive, allowing users to select a specific period for more detailed information. Trendlines can also be added to show how a particular topic has developed.

[0050] (Example 2) The digital divide bridging system according to an embodiment of the present invention is a system that analyzes conversations on communication tools in real time, uses a generation AI to extract trending topics, expresses the size of the topics as bubbles, and displays them in chronological order. As a result, the digital divide bridging system can eliminate the digital divide within a company, stimulate communication among employees, improve business efficiency, and promote corporate growth.

[0051] A system for bridging the digital divide according to an embodiment includes a conversation analysis unit, a topic extraction unit, a visualization unit, and a display unit. The conversation analysis unit analyzes conversations on a communication tool in real time. For example, the conversation analysis unit analyzes the content of the conversation using natural language processing technology. The conversation analysis unit can also convert audio data into text data using speech recognition technology. The conversation analysis unit can also understand the context of the conversation and extract important topics. For example, the conversation analysis unit analyzes the flow and context of the conversation and scores the importance of the topic. The topic extraction unit extracts topics that are being discussed from the conversation analyzed by the conversation analysis unit. For example, the topic extraction unit extracts topics using keyword frequency and co-occurrence network analysis. The topic extraction unit can also automatically recognize technical terms and industry-specific words to improve the accuracy of topic extraction. The visualization unit represents the size of the topic of the topic extracted by the topic extraction unit using the size of bubbles. For example, the visualization unit can also represent the size of the topic using the color and shape of the bubbles to add visual variety. The visualization unit can also visualize differences in interest within an organization by displaying the size of a topic using different colors for each employee's job title or department. The display unit displays the bubbles represented by the visualization unit in chronological order. For example, the display unit may make the chronological display interactive, allowing a user to select a specific period and view details. The display unit can also add trend lines to the chronological display to show how a specific topic developed. This allows the digital divide bridging system according to the embodiment to bridge the digital divide within a company, stimulate employee communication, improve business efficiency, and promote corporate growth. For example, the digital divide bridging system shares important internal information with all employees, supporting rapid decision-making. The digital divide bridging system also promotes communication between employees and improves teamwork. The digital divide bridging system also improves business efficiency and promotes corporate growth.

[0052] The conversation analysis unit understands the context of the conversation and can automatically rank the importance of topics. For example, the conversation analysis unit uses a generative AI to analyze the context of the conversation and score the importance of each topic. For example, conversations about project progress and problems may be ranked high. The conversation analysis unit also automatically ranks the importance of topics based on keywords and phrases that appear frequently in the conversation. For example, it may prioritize topics related to important meetings and deadlines. The conversation analysis unit also analyzes the flow and context of the conversation and dynamically ranks the importance of topics. For example, it may assign a high score to conversations about urgent issues or important decisions. This allows important information to be prioritized by automatically ranking the importance of topics.

[0053] The conversation analysis unit can automatically recognize technical terms and industry-specific words, improving the accuracy of topic extraction. For example, the conversation analysis unit uses a generative AI to automatically recognize technical terms and industry-specific words, improving the accuracy of topic extraction. For example, it accurately recognizes technical terms and marketing terms. The conversation analysis unit also compares the technical terms used in conversation with a dictionary database to improve the accuracy of topic extraction. For example, it accurately extracts medical and legal terms. The conversation analysis unit also automatically recognizes industry-specific words and abbreviations, improving the accuracy of topic extraction. For example, it accurately analyzes abbreviations in the IT industry and technical terms in the financial industry. This improves the accuracy of topic extraction by recognizing technical terms and industry-specific words.

[0054] The conversation analysis unit can use the emotion estimation function to analyze changes in emotions during a conversation and prioritize extract emotionally important topics. The conversation analysis unit, for example, uses the emotion estimation function to analyze changes in emotions during a conversation in real time and extract emotionally important topics. For example, topics with strong emotions such as anger or joy are preferentially displayed. The conversation analysis unit also automatically extracts emotionally important topics based on the emotion score of the conversation. For example, conversation content with a high emotion score is preferentially analyzed. The conversation analysis unit also analyzes changes in emotions during a conversation based on emotion estimation data and extracts emotionally important topics. For example, topics that were discussed at the peak of emotions are preferentially displayed. In this way, emotional issues can be quickly identified by preferentially extracting emotionally important topics.

[0055] The conversation analysis unit can expand the scope of conversation analysis to include not only text but also audio and video conference content, enabling multimodal analysis. For example, the conversation analysis unit can expand the scope of conversation analysis to audio data and extract topics using speech recognition technology. For example, it can analyze audio data from video conferences and extract important topics. The conversation analysis unit can also analyze video conference video data and extract topics based on the speaker's facial expressions and gestures. For example, it can analyze changes in the speaker's facial expression and extract emotionally important topics. The conversation analysis unit can also integrate text, audio, and video data to perform multimodal analysis. For example, it can extract topics by combining the content of the conversation with the speaker's facial expressions. This allows for the analysis of audio and video conference content, enabling a wider variety of information to be grasped.

[0056] The conversation analysis unit may have a multilingual function that translates conversations in different languages ​​in real time and extracts topics. The conversation analysis unit, for example, translates conversations in different languages ​​in real time and extracts topics. For example, it translates a conversation in English into Japanese and extracts topics. The conversation analysis unit also uses a multilingual translation function to analyze conversations in different languages ​​and extract topics. For example, it translates conversations in French or Chinese and extracts topics. The conversation analysis unit also uses a real-time translation function to analyze conversations in different languages ​​and extract topics. For example, it translates conversations at international conferences and extracts important topics. This makes it possible to share information globally by analyzing conversations in different languages.

[0057] The conversation analysis unit can use the emotion estimation function to visualize the intensity of emotions during a conversation and display emotionally important topics in real time. The conversation analysis unit, for example, uses the emotion estimation function to visualize the intensity of emotions during a conversation in real time. For example, it displays emotion scores in a graph and highlights emotionally important topics. The conversation analysis unit also visualizes the intensity of emotions during a conversation using colors and icons and displays emotionally important topics in real time. For example, it displays topics with high emotion scores in red. The conversation analysis unit also visualizes the intensity of emotions during a conversation based on emotion estimation data and displays emotionally important topics in real time. For example, it highlights topics that were discussed at the peak of emotions. In this way, emotional issues can be quickly identified by displaying emotionally important topics in real time.

[0058] The visualization unit can also express the size of a topic with the color and shape of the bubble, providing visual diversity. For example, the visualization unit expresses the size of a topic with the color of the bubble, making it easier to visually distinguish between topics. For example, important topics are displayed in red, and general topics in blue. The visualization unit also visually expresses the type and importance of a topic by changing the shape of the bubble. For example, important topics are displayed in a star shape, and general topics are displayed in a circle. The visualization unit also combines the color and shape of the bubble to express the size of a topic in a variety of visual ways. For example, important topics are displayed in a red star shape, and general topics are displayed in a blue circle. In this way, expressing the size of a topic with color and shape makes it easier to visually distinguish between topics.

[0059] The visualization unit displays the size of a topic in a different color for each employee's job title or department, making it possible to visualize differences in interest within an organization. For example, the visualization unit displays the size of a topic in a different color for each employee's job title, making it possible to visualize differences in interest within an organization. For example, topics for managers are displayed in red, and topics for regular employees are displayed in blue. The visualization unit also displays the size of a topic in a different color for each department, making it possible to visualize differences in interest within an organization. For example, topics for the sales department are displayed in green, and topics for the engineering department are displayed in yellow. The visualization unit also displays the size of a topic in a different color for each job title or department, making it possible to visually grasp differences in interest within an organization. For example, colors are set according to a combination of job title and department, and topics are displayed. In this way, by displaying different colors for each job title or department, it is possible to visually grasp differences in interest within an organization.

[0060] The visualization unit uses the emotion estimation function to represent the emotional importance of a topic with a shade of color, thereby emphasizing emotionally important topics. The visualization unit, for example, uses the emotion estimation function to represent the emotional importance of a topic with a shade of color. For example, topics with high emotion scores are displayed in dark colors. The visualization unit also represents the emotional importance of a topic with a shade of color, thereby emphasizing emotionally important topics. For example, topics with low emotion scores are displayed in light colors. The visualization unit also represents the emotional importance of a topic with a shade of color, based on emotion estimation data, thereby emphasizing emotionally important topics. For example, topics that were talked about at the peak of emotion are displayed in dark colors. In this way, emotionally important topics can be emphasized by representing emotional importance with a shade of color.

[0061] The visualization unit can represent the size of a topic using 3D graphics to enable a more intuitive understanding. For example, the visualization unit represents the size of a topic using 3D graphics to enable a user to intuitively understand the size visually. For example, important topics are displayed as large 3D objects. The visualization unit also uses 3D graphics to represent the size of a topic in three dimensions. For example, the size of the 3D object is changed depending on the importance of the topic. The visualization unit also represents the size of a topic using 3D graphics to enable a user to intuitively understand the size visually. For example, the 3D object can be rotated to grasp the overall picture. In this way, the size of a topic can be intuitively understood by representing it using 3D graphics.

[0062] The visualization unit can display the size of a topic in conjunction with other data (for example, project progress or sales data). For example, the visualization unit displays the size of a topic in conjunction with the progress of a project. For example, topics about projects that are behind schedule are displayed in a larger size. The visualization unit also displays the size of a topic in conjunction with sales data. For example, topics about products with high sales are displayed in a larger size. The visualization unit also displays the size of a topic in conjunction with other data (for example, customer satisfaction or market share). For example, topics about services with high customer satisfaction are displayed in a larger size. In this way, by displaying the size of a topic in conjunction with other data, the relevance can be visually grasped.

[0063] The visualization unit uses the emotion estimation function to display the emotional reactions to topics in real time, thereby enabling emotional trends to be grasped. The visualization unit, for example, uses the emotion estimation function to display the emotional reactions to topics in real time. For example, the visualization unit displays emotion scores in a graph to grasp emotional trends. The visualization unit also displays the emotional reactions to topics in real time using colors and icons to grasp emotional trends. For example, topics with high emotion scores are displayed in red. The visualization unit also displays the emotional reactions to topics in real time based on the emotion estimation data to grasp emotional trends. For example, topics that became popular at the peak of emotion are highlighted. In this way, emotional trends can be grasped by displaying emotional reactions in real time.

[0064] The display unit may make the time series display interactive and include a function that allows the user to select a specific period to view details. The display unit, for example, makes the time series display interactive and adds a function that allows the user to select a specific period to view details. For example, a specific period may be selected using a slider. The display unit may also use an interactive time series display to allow the user to view details of topics within a specific period. For example, detailed information may be displayed by clicking. The display unit may also make the time series display interactive and add a function that allows the user to select a specific period to view details. For example, a zoom-in / zoom-out function may be used to enlarge a specific period. This allows the user to select a specific period to view details, enabling the user to quickly grasp information of interest.

[0065] The display unit can add trend lines to the time series display to show how a particular topic has developed. For example, the display unit adds trend lines to the time series display to visually show how a particular topic has developed. For example, it displays changes in the importance of a topic in a line graph. The display unit also adds trend lines to the time series display to show the development of a topic, allowing a user to grasp the evolution of the topic at a glance. For example, it displays the frequency of appearance of a topic in a line graph. The display unit also adds trend lines to the time series display to show how a particular topic has developed. For example, it displays changes in the sentiment score of a topic in a line graph. In this way, by adding trend lines, the development of a particular topic can be visually grasped.

[0066] The display unit can use the emotion estimation function to superimpose changes in emotion on the time-series display to visualize emotional trends. The display unit, for example, uses the emotion estimation function to superimpose changes in emotion on the time-series display. For example, it displays changes in emotion scores using shades of color. The display unit also superimposes changes in emotion on the time-series display to visualize emotional trends. For example, it displays fluctuations in emotion scores using a line graph. The display unit also superimposes changes in emotion on the time-series display based on emotion estimation data to visualize emotional trends. For example, it highlights topics that became popular at the peak of emotions. In this way, emotional trends can be visually grasped by superimposing changes in emotion.

[0067] The display unit may have a function that allows the time series display to be filtered by different departments or projects. For example, the display unit adds a function that allows the time series display to be filtered by different departments. For example, a filter that displays only topics related to the sales department is provided. The display unit also adds a function that allows the time series display to be filtered by project. For example, only topics related to a specific project are displayed. The display unit also adds a function that allows the time series display to be filtered by department or project, allowing the user to narrow down topics of interest. For example, a combination of multiple filters can be displayed. This allows the user to quickly grasp information of interest by filtering by different departments or projects.

[0068] The display unit can display the time series display in conjunction with other business indicators (e.g., sales or customer satisfaction). For example, the display unit displays the time series display in conjunction with sales data. For example, it displays the fluctuations in sales and the size of the buzz simultaneously. The display unit also displays the time series display in conjunction with customer satisfaction data. For example, it displays the fluctuations in customer satisfaction and the size of the buzz simultaneously. The display unit also displays the time series display in conjunction with other business indicators (e.g., employee productivity or market share). For example, it displays the fluctuations in employee productivity and the size of the buzz simultaneously. In this way, by linking the time series display with other business indicators, the correlation can be visually grasped.

[0069] The display unit can use the emotion estimation function to highlight emotional peaks in the time series display and identify emotionally important points. The display unit, for example, uses the emotion estimation function to highlight emotional peaks in the time series display. For example, the point with the highest emotion score is displayed in red. The display unit also highlights emotional peaks in the time series display and identifies emotionally important points. For example, the display unit displays fluctuations in the emotion score in a graph and highlights the peaks. The display unit also highlights emotional peaks in the time series display based on the emotion estimation data and identifies emotionally important points. For example, it highlights topics that were talked about at the time of the emotion peaks. In this way, by highlighting emotional peaks, emotionally important points can be quickly identified.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The system for bridging the digital divide can further collect user behavioral data and include a behavioral analysis unit. The behavioral analysis unit, for example, analyzes the user's click and scroll patterns to identify topics in which the user is interested. For example, the user's level of interest can be evaluated based on the number of clicks and time spent on a particular topic. The behavioral analysis unit can also dynamically adjust the importance of topics based on the user's behavioral data. For example, topics that the user accesses frequently can be ranked with a high score. This makes it possible to utilize user behavioral data to extract topics with greater accuracy.

[0072] The system for bridging the digital divide can further collect user feedback and include a feedback analysis unit. The feedback analysis unit, for example, analyzes comments and ratings provided by users and adjusts the importance of topics. For example, it may preferentially display topics that users have given high ratings. The feedback analysis unit can also improve the accuracy of topic extraction based on user feedback. For example, it may correct errors pointed out by users and improve the topic extraction algorithm. This makes it possible to utilize user feedback to provide more useful information to users.

[0073] The digital divide bridging system can further integrate external data sources and include an external data analysis unit. The external data analysis unit, for example, analyzes news articles and social media posts and associates them with internal company topics. For example, it can compare the latest industry news with internal company topics and extract highly relevant information. The external data analysis unit can also adjust the importance of topics based on external data. For example, it can prioritize the display of topics that are trending externally. This allows the system to utilize external data to provide a wider range of information.

[0074] The digital divide bridging system can further integrate user schedule data and include a schedule analysis unit. The schedule analysis unit, for example, analyzes the user's calendar information and extracts topics related to important meetings and events. For example, it extracts topics based on the meeting agenda and provides related information in advance. The schedule analysis unit can also adjust the timing of topic display based on the user's schedule. For example, it can display related topics just before a meeting. This makes it possible to provide information tailored to the user's schedule.

[0075] The system for bridging the digital divide can further integrate user profile data and include a profile analysis unit. The profile analysis unit extracts highly relevant topics based on the user's job role or field of expertise, for example. For example, it may prioritize displaying technology-related topics to an engineer. The profile analysis unit can also provide topics tailored to the user's individual interests based on the user's past behavioral data. For example, it may prioritize displaying topics that the user has frequently accessed in the past. This makes it possible to provide personalized information based on the user's profile.

[0076] The digital divide bridging system can also use an emotion estimation function to adjust the priority of topics based on the user's emotions. For example, if a user is feeling stressed, topics that will help them relax can be displayed preferentially. If a user is excited, topics that will help them improve their concentration can also be provided. Furthermore, the emotion estimation function can be used to dynamically adjust the order in which topics are displayed according to changes in the user's emotions. This makes it possible to provide information tailored to the user's emotional state.

[0077] The digital divide bridging system can also use an emotion estimation function to collect feedback based on the user's emotions and adjust the importance of topics. For example, topics for which the user expressed positive emotions can be ranked with a high score. Topics for which the user expressed negative emotions can also be re-evaluated and, if necessary, suppressed from display. Furthermore, the emotion estimation function can also be used to collect feedback based on the user's emotions in real time and dynamically adjust the display order of topics. This enables flexible information provision based on the user's emotions.

[0078] The digital divide bridging system can further use an emotion estimation function to provide a notification function based on the user's emotions. For example, if the user is feeling stressed, it can notify the user of content that will help them relax. Or, if the user is excited, it can notify the user of content that will help them improve their concentration. Furthermore, the emotion estimation function can be used to adjust the timing of notifications according to changes in the user's emotions. This makes it possible to provide information at appropriate times that match the user's emotional state.

[0079] The digital divide bridging system can further use its emotion estimation function to customize the interface based on the user's emotions. For example, if the user is relaxed, it can provide an interface with calm colors. Alternatively, if the user is concentrating, it can provide a simple and intuitive interface. Furthermore, the emotion estimation function can dynamically adjust the interface design according to changes in the user's emotions. This makes it possible to provide a comfortable operating environment that matches the user's emotional state.

[0080] The digital divide bridging system can also use an emotion estimation function to recommend content based on the user's emotions. For example, if the user is expressing positive emotions, it can recommend enjoyable content. If the user is expressing negative emotions, it can recommend encouraging messages or relaxing content. Furthermore, the emotion estimation function can also be used to dynamically adjust the recommended content according to changes in the user's emotions. This allows it to provide appropriate content that matches the user's emotional state.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The conversation analysis unit analyzes conversations in communication tools in real time. For example, it uses natural language processing technology to analyze the content of the conversation and speech recognition technology to convert the voice data into text data. It can also understand the context of the conversation and extract important topics. For example, it analyzes the flow and context of the conversation and scores the importance of the topic. Step 2: The topic extraction unit extracts popular topics from the conversations analyzed by the conversation analysis unit. For example, it extracts topics using keyword frequency and co-occurrence network analysis, and automatically recognizes technical terms and industry-specific words to improve the accuracy of topic extraction. Step 3: The visualization unit expresses the size of the topics extracted by the topic extraction unit as bubbles. For example, the size of the topic can be expressed by the color and shape of the bubbles, providing visual diversity. It is also possible to visualize differences in interest within an organization by displaying different colors according to employee position or department. Step 4: The display unit displays the bubbles represented by the visualization unit in a chronological order. For example, the timeline display can be made interactive, allowing users to select a specific period for more detailed information. Trendlines can also be added to show how a particular topic has developed.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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).

[0092] 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.

[0093] 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.

[0094] 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.

[0095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0096] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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).

[0107] 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.

[0108] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] 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.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0111] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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."

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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]

[0150] 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 conversation analysis unit that analyzes conversations in communication tools in real time, a topic extraction unit that extracts topics of conversation from the conversation analyzed by the conversation analysis unit; a visualization unit that expresses the size of the topic extracted by the topic extraction unit as the size of bubbles; a display unit that displays the bubbles visualized by the visualization unit in chronological order. A system characterized by:

2. The conversation analysis unit Understand the context of the conversation and automatically rank the importance of said topics 2. The system of claim 1.

3. The conversation analysis unit Automatically recognize technical terms and industry-specific words used in conversations, improving the accuracy of topic extraction by the topic extraction unit.

2. The system of claim 1.

4. The conversation analysis unit Analyzes emotional changes during conversations and prioritizes extraction of emotionally significant topics 2. The system of claim 1.

5. The conversation analysis unit Expanding the scope of conversation analysis beyond text to include audio and video conferencing content, and conducting multimodal analysis 2. The system of claim 1.

6. The conversation analysis unit It has a multilingual function that translates conversations in different languages ​​in real time and extracts topics using the topic extraction unit.

2. The system of claim 1.

Images