System

Abstract

An object of a system according to an embodiment is to automatically create a newsletter that efficiently summarizes the efforts of a company.SOLUTION: A system includes an information collection part, a data analysis part, and a text generation part. The information collecting unit collects data from information sources such as a company's official website, news articles, and news records. The data analysis unit analyzes the data collected by the information collection unit and extracts important information. The text generation unit generates text of a newsletter based on the important information extracted by the data analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to efficiently create newsletters summarizing a company's efforts.

[0005] The system according to the embodiment aims to automatically create a newsletter that efficiently summarizes the efforts of a company. [Means for solving the problem]

[0006] The system according to the embodiment includes an information collection unit, a data analysis unit, and a text generation unit. The information collection unit collects data from information sources such as official company websites, news articles, and interview transcripts. The data analysis unit analyzes the data collected by the information collection unit and extracts important information. The text generation unit generates newsletter text based on the important information extracted by the data analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically create a newsletter that efficiently summarizes the efforts of a company. [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 automatic newsletter creation system according to an embodiment of the present invention collects data from information sources such as a company's official website, news articles, and interview records, summarizes the data using a generation AI, and automatically generates the text for a newsletter. As a result, the automatic newsletter creation system can automatically create a newsletter summarizing the company's efforts and periodically disseminate information.

[0029] An automatic newsletter creation system according to an embodiment includes an information collection unit, a data analysis unit, and a text generation unit. The information collection unit collects data from sources such as a company's official website, news articles, and interview transcripts. For example, the information collection unit uses web scraping technology to collect the latest news and press releases posted on a company's official website. The information collection unit can also collect the contents of news articles using an API. The information collection unit can also analyze interview transcripts and audio recordings to collect data for interview transcripts. The data analysis unit analyzes the collected data and extracts important information. For example, the data analysis unit can analyze text using natural language processing technology to identify important keywords and phrases. The data analysis unit can also use generative AI to extract important topics such as a company's new product announcement, performance report, or social contribution activities. The data analysis unit can also analyze data patterns using text mining technology to extract important information. The text generation unit generates newsletter text based on the extracted important information. For example, the text generation unit uses generative AI and natural language generation technology to construct text that is easy to read and conveys information accurately. The text generation unit can also set the format in accordance with a company's brand guidelines to create a visually appealing newsletter. Furthermore, the text generation unit can also automatically distribute the newsletter text using generative AI. As a result, the automatic newsletter creation system according to the embodiment can automatically create a newsletter that summarizes a company's initiatives and regularly disseminate information. For example, the company's latest initiatives and achievements can be communicated to reporters in a timely manner, thereby highlighting the company's presence. Furthermore, automatic newsletter generation reduces the burden on public relations staff, allowing them to focus on other important tasks.

[0030] The information collection unit can collect data, including unofficial information from social media sites and blogs. For example, the information collection unit uses a generation AI to collect information from social media sites and blogs, and combines this information with official information sources to collect data from a variety of perspectives. For example, it analyzes posts on Twitter and Facebook. The information collection unit also collects data from unofficial sources and builds a system that compares it with official information to evaluate its reliability. For example, it can analyze the content of blog articles and calculate a reliability score. The information collection unit also automatically classifies data collected from social media sites and blogs, integrates it with official information, and uses it as material for newsletters. For example, it can analyze user posts to identify trends. This makes it possible to collect data, including unofficial information from social media sites and blogs.

[0031] The information collection department can compare the collected data with the company's past newsletters and automatically eliminate duplicate or similar content. For example, the information collection department can compare the data collected by the generation AI with past newsletters and automatically eliminate duplicate content. For example, it can prevent the same topics from being repeated. The information collection department can also compare the collected data with past newsletters and build a system that automatically detects and eliminates similar content. For example, text mining technology can be used. The information collection department can also compare the collected data with past newsletters and develop an algorithm that filters out duplicate or similar content. For example, it can filter based on a similarity score. This makes it possible to automatically eliminate duplicate or similar content.

[0032] The information gathering department also collects information from competitors' official websites and press articles, allowing it to grasp trends across the industry. For example, the information gathering department uses generative AI to collect information from competitors' official websites and press articles to grasp trends across the industry. For example, it analyzes competitors' press releases. The information gathering department also builds a system to collect information about competitors and reflect it in the company's newsletter. For example, it can cover new product announcements by competitors. The information gathering department also collects information about competitors and integrates it into a database to grasp trends across the industry. For example, it can analyze competitors' performance reports. This allows it to grasp trends across the industry.

[0033] The information collection unit can automatically translate collected data into different languages ​​and collect information from an international perspective. For example, the information collection unit automatically translates data collected by the generation AI and integrates information from different languages ​​to collect information from an international perspective. For example, it translates articles in English and Chinese. The information collection unit also builds a system that automatically translates information in different languages ​​and creates newsletters from an international perspective. For example, it can generate newsletters in multiple languages. The information collection unit also uses the automatic translation function to collect information in different languages ​​and integrate data from an international perspective. For example, it can translate and analyze news articles from overseas. This makes it possible to collect information from an international perspective.

[0034] The data analysis unit can combine the data to be analyzed with a company's past performance and market data to generate more accurate summaries. For example, the data analysis unit combines a company's past performance data with the data to be analyzed by the generation AI to generate more accurate summaries. For example, it summarizes performance reports based on past sales data. The data analysis unit also combines market data with the analysis data to generate summaries that reflect the company's performance and market trends. For example, it can take into account market share and competitive conditions. The data analysis unit also integrates a company's past performance data with market data, and the generation AI automatically generates more accurate summaries. For example, it can create summaries based on past performance and market trends. This makes it possible to generate more accurate summaries.

[0035] The data analysis unit can combine data from different industries and fields with the data to be analyzed to gain new insights. For example, the data analysis unit can combine data from different industries with the data to be analyzed by the generation AI to gain new insights. For example, data from the technology field and the consumer market can be integrated. The data analysis unit can also combine data from different fields with the analysis data to gain cross-industry insights. For example, data from the medical field and the IT field can be integrated. The data analysis unit can also analyze data from different industries and fields with the generation AI to automatically generate new insights. For example, trends from different industries can be integrated to create summaries. This can yield new insights.

[0036] The data analysis unit can convert the data to be analyzed into visual notes or mind maps to make it easier to understand visually. For example, the data analysis unit can convert data analyzed by the generation AI into visual notes to make it easier to understand visually. For example, it can show important points with diagrams or icons. The data analysis unit can also convert the analyzed data into a mind map format to visually organize related keywords and concepts. This makes it possible to understand the overall picture of the data at a glance. The data analysis unit can also develop tools that automatically generate visual notes and mind maps to enable users to easily visually display data summaries. For example, it can provide a function to visualize summary text with drag and drop. This makes it easier to understand visually.

[0037] The text generation unit can take into account not only the company's brand guidelines but also the preferences and interests of the target audience when generating text. For example, when the generation AI generates text, the text generation unit takes into account the company's brand guidelines and the preferences and interests of the target audience. For example, it uses language that reflects the target audience's age group and interests. The text generation unit can also analyze the preferences and interests of the target audience and build a system that customizes text based on that. For example, it can select appropriate topics for groups with specific interests. The text generation unit can also integrate the company's brand guidelines and target audience data, allowing the generation AI to automatically generate optimal text. For example, it can use language that resonates with the target audience while maintaining the brand image. This makes it possible to generate text that takes into account the preferences and interests of the target audience.

[0038] The text generation unit can analyze the effectiveness of past newsletters when generating text and incorporate the most effective expressions and structures. For example, the text generation unit uses a generation AI to analyze the effectiveness of past newsletters and incorporate the most effective expressions and structures. For example, it prioritizes the use of expressions with high open rates and click rates. The text generation unit also analyzes data from past newsletters and builds a system to identify effective expressions and structures. For example, it can extract elements of successful newsletters and reflect them in new text. The text generation unit also uses a generation AI to learn the effectiveness of past newsletters and automatically generate the most effective expressions and structures. For example, it can create optimal text based on past data. This makes it possible to generate text that incorporates the most effective expressions and structures.

[0039] When generating text, the text generation unit automatically generates versions that are compatible with different languages ​​and cultures, allowing information to be provided from an international perspective. For example, when a generation AI generates text, the text generation unit automatically generates versions that are compatible with different languages ​​and cultures. For example, it translates into multiple languages ​​such as English, French, and Chinese. The text generation unit also automatically generates text that is compatible with different cultures, building a system that provides information from an international perspective. For example, it can use expressions that take cultural nuances into consideration. The text generation unit also uses an automatic translation function to generate newsletters that are compatible with different languages ​​and cultures, allowing information to be provided from an international perspective. For example, it can create text that reflects the characteristics of each region. This allows information to be provided from an international perspective.

[0040] The text generation unit automatically incorporates visual content (images and videos) when generating text, making it possible to create visually appealing newsletters. For example, the text generation unit automatically incorporates visual content when the generation AI generates text. For example, it automatically inserts related images and videos. The text generation unit also builds a system that automatically generates visual content and incorporates it into newsletters. For example, it can select appropriate visuals using image recognition technology. The text generation unit also integrates text and visual content with the generation AI to automatically generate visually appealing newsletters. For example, it can automatically adjust the layout to effectively position visuals. This makes it possible to create visually appealing newsletters.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The automatic newsletter creation system can further include a feedback collection unit that collects user feedback and reflects it in the next newsletter. For example, a survey can be sent to newsletter recipients to collect satisfaction with the content and areas for improvement. The feedback collection unit can also analyze data such as recipient click rates and open rates to identify which content attracted the most interest. Furthermore, the feedback collection unit can improve the content and structure of the newsletter based on the collected feedback and reflect it in the next distribution. This makes it possible to create a newsletter that is more suited to the needs of recipients.

[0043] The data collection unit can also collect data from a company's social media accounts to enhance the company's online presence. For example, it can analyze Twitter and Instagram posts to gather information about the company's latest activities and campaigns. The data collection unit can also analyze social media engagement data to identify which posts generated the most interest. Furthermore, the data collection unit can tailor the content of newsletters based on social media data to provide more relevant information to recipients. This can enhance the company's online presence and create newsletters that attract recipients' attention.

[0044] The information gathering department can further collect feedback from company employees and create a newsletter that reflects internal perspectives. For example, the information gathering department can conduct an employee survey to collect opinions and impressions on company initiatives and projects. The information gathering department can also interview employees to collect internal information about the company. Furthermore, the information gathering department can adjust the content of the newsletter based on feedback from employees to provide information that reflects the company's internal perspective. In this way, a newsletter containing internal company information can be created, increasing the company's transparency to recipients.

[0045] The information gathering department can also collect feedback from the company's customers and create newsletters that reflect their opinions. For example, it can conduct customer surveys to collect opinions and impressions about products and services. The information gathering department can also analyze customer reviews and ratings to understand customer needs and expectations. Furthermore, the information gathering department can adjust the content of the newsletter based on customer feedback and provide information that reflects customer opinions. This makes it possible to create newsletters that meet customer needs and improve customer satisfaction.

[0046] The information gathering department can further collect opinions from industry experts and influencers to create newsletters that reflect their expert perspectives. For example, the information gathering department can analyze blogs and articles from industry experts and influencers to gather the latest trends and insights. The information gathering department can also conduct interviews with experts and influencers to gather first-hand opinions and advice. Furthermore, the information gathering department can adjust the content of the newsletter based on the collected expert opinions to provide valuable information to recipients. This allows the newsletter to be created to reflect an expert perspective and gain the trust of recipients.

[0047] The processing flow of the first embodiment will be briefly explained below.

[0048] Step 1: The information collection department collects data from sources such as the company's official website, press articles, and interview transcripts. For example, the information collection department uses web scraping technology to collect the latest news and press releases posted on the company's official website. The information collection department can also use APIs to collect the content of press articles. In addition, the information collection department can analyze interview transcripts and audio recordings to collect interview transcript data. Step 2: The data analysis unit analyzes the collected data and extracts important information. For example, the data analysis unit uses natural language processing technology to analyze text and identify important keywords and phrases. The data analysis unit can also use generative AI to extract important topics such as a company's new product announcements, performance reports, and social contribution activities. Furthermore, the data analysis unit can use text mining technology to analyze data patterns and extract important information. Step 3: The text generator generates the newsletter text based on the extracted key information. For example, the text generator uses generative AI and natural language generation technology to construct text that is easy to read and accurately conveys information. The text generator can also format the newsletter according to the company's brand guidelines to create a visually appealing newsletter. Furthermore, the text generator can use generative AI to automatically distribute the newsletter text.

[0049] (Example 2) The automatic newsletter creation system according to an embodiment of the present invention collects data from information sources such as a company's official website, news articles, and interview records, summarizes the data using a generation AI, and automatically generates the text for a newsletter. As a result, the automatic newsletter creation system can automatically create a newsletter summarizing the company's efforts and periodically disseminate information.

[0050] An automatic newsletter creation system according to an embodiment includes an information collection unit, a data analysis unit, and a text generation unit. The information collection unit collects data from sources such as a company's official website, news articles, and interview transcripts. For example, the information collection unit uses web scraping technology to collect the latest news and press releases posted on a company's official website. The information collection unit can also collect the contents of news articles using an API. The information collection unit can also analyze interview transcripts and audio recordings to collect data for interview transcripts. The data analysis unit analyzes the collected data and extracts important information. For example, the data analysis unit can analyze text using natural language processing technology to identify important keywords and phrases. The data analysis unit can also use generative AI to extract important topics such as a company's new product announcement, performance report, or social contribution activities. The data analysis unit can also analyze data patterns using text mining technology to extract important information. The text generation unit generates newsletter text based on the extracted important information. For example, the text generation unit uses generative AI and natural language generation technology to construct text that is easy to read and conveys information accurately. The text generation unit can also set the format in accordance with a company's brand guidelines to create a visually appealing newsletter. Furthermore, the text generation unit can also automatically distribute the newsletter text using generative AI. As a result, the automatic newsletter creation system according to the embodiment can automatically create a newsletter that summarizes a company's initiatives and regularly disseminate information. For example, the company's latest initiatives and achievements can be communicated to reporters in a timely manner, thereby highlighting the company's presence. Furthermore, automatic newsletter generation reduces the burden on public relations staff, allowing them to focus on other important tasks.

[0051] The information collection unit can use the emotion estimation function to preferentially collect articles with positive emotions. For example, the information collection unit performs emotion analysis on data collected by the generation AI and preferentially collects articles with high positive emotion scores. For example, it preferentially selects articles with emotions of joy or surprise. The information collection unit also uses the emotion estimation function to filter articles that evoke positive emotions from the collected data. For example, it can preferentially collect articles with emotion scores above a certain level. The information collection unit also performs emotion analysis on the collected data, automatically tags articles with positive emotions, and preferentially stores them in the database. This makes it possible to preferentially collect articles with positive emotions.

[0052] The information collection unit can collect data, including unofficial information from social media sites and blogs. For example, the information collection unit uses a generation AI to collect information from social media sites and blogs, and combines this information with official information sources to collect data from a variety of perspectives. For example, it analyzes posts on Twitter and Facebook. The information collection unit also collects data from unofficial sources and builds a system that compares it with official information to evaluate its reliability. For example, it can analyze the content of blog articles and calculate a reliability score. The information collection unit also automatically classifies data collected from social media sites and blogs, integrates it with official information, and uses it as material for newsletters. For example, it can analyze user posts to identify trends. This makes it possible to collect data, including unofficial information from social media sites and blogs.

[0053] The information collection department can compare the collected data with the company's past newsletters and automatically eliminate duplicate or similar content. For example, the information collection department can compare the data collected by the generation AI with past newsletters and automatically eliminate duplicate content. For example, it can prevent the same topics from being repeated. The information collection department can also compare the collected data with past newsletters and build a system that automatically detects and eliminates similar content. For example, text mining technology can be used. The information collection department can also compare the collected data with past newsletters and develop an algorithm that filters out duplicate or similar content. For example, it can filter based on a similarity score. This makes it possible to automatically eliminate duplicate or similar content.

[0054] The information gathering department also collects information from competitors' official websites and press articles, allowing it to grasp trends across the industry. For example, the information gathering department uses generative AI to collect information from competitors' official websites and press articles to grasp trends across the industry. For example, it analyzes competitors' press releases. The information gathering department also builds a system to collect information about competitors and reflect it in the company's newsletter. For example, it can cover new product announcements by competitors. The information gathering department also collects information about competitors and integrates it into a database to grasp trends across the industry. For example, it can analyze competitors' performance reports. This allows it to grasp trends across the industry.

[0055] The information collection unit can automatically translate collected data into different languages ​​and collect information from an international perspective. For example, the information collection unit automatically translates data collected by the generation AI and integrates information from different languages ​​to collect information from an international perspective. For example, it translates articles in English and Chinese. The information collection unit also builds a system that automatically translates information in different languages ​​and creates newsletters from an international perspective. For example, it can generate newsletters in multiple languages. The information collection unit also uses the automatic translation function to collect information in different languages ​​and integrate data from an international perspective. For example, it can translate and analyze news articles from overseas. This makes it possible to collect information from an international perspective.

[0056] The information collection unit uses an emotion estimation function on the collected data to analyze users' emotional responses in real time and prioritize the collection of information that elicits positive responses. For example, the information collection unit performs emotion analysis on data collected by the generation AI and prioritizes the collection of information that elicits positive emotional responses. For example, it selects articles with high emotion scores. The information collection unit also uses the emotion estimation function to filter information that elicits positive responses from the collected data. For example, it can prioritize the collection of information with an emotion score above a certain level. The information collection unit also performs emotion analysis on the collected data, automatically tags information that elicits positive emotional responses, and prioritizes storing it in a database. This makes it possible to prioritize the collection of information that elicits positive responses.

[0057] The data analysis unit can use the emotion estimation function on the data to be analyzed to preferentially extract keywords and phrases that evoke positive emotions. For example, the data analysis unit performs emotion analysis on the data to be analyzed by the generation AI, and preferentially extracts keywords and phrases that evoke positive emotions. For example, it selects phrases that evoke emotions such as joy and surprise. The data analysis unit also uses the emotion estimation function to filter keywords and phrases that evoke positive emotions from the analyzed data. For example, it can preferentially extract those with high emotion scores. The data analysis unit also performs emotion analysis on the analyzed data, automatically tags keywords and phrases that evoke positive emotions, and preferentially reflects these in the summary. This allows keywords and phrases that evoke positive emotions to be preferentially extracted.

[0058] The data analysis unit can combine the data to be analyzed with a company's past performance and market data to generate more accurate summaries. For example, the data analysis unit combines a company's past performance data with the data to be analyzed by the generation AI to generate more accurate summaries. For example, it summarizes performance reports based on past sales data. The data analysis unit also combines market data with the analysis data to generate summaries that reflect the company's performance and market trends. For example, it can take into account market share and competitive conditions. The data analysis unit also integrates a company's past performance data with market data, and the generation AI automatically generates more accurate summaries. For example, it can create summaries based on past performance and market trends. This makes it possible to generate more accurate summaries.

[0059] The data analysis unit can combine data from different industries and fields with the data to be analyzed to gain new insights. For example, the data analysis unit can combine data from different industries with the data to be analyzed by the generation AI to gain new insights. For example, data from the technology field and the consumer market can be integrated. The data analysis unit can also combine data from different fields with the analysis data to gain cross-industry insights. For example, data from the medical field and the IT field can be integrated. The data analysis unit can also analyze data from different industries and fields with the generation AI to automatically generate new insights. For example, trends from different industries can be integrated to create summaries. This can yield new insights.

[0060] The data analysis unit can convert the data to be analyzed into visual notes or mind maps to make it easier to understand visually. For example, the data analysis unit can convert data analyzed by the generation AI into visual notes to make it easier to understand visually. For example, it can show important points with diagrams or icons. The data analysis unit can also convert the analyzed data into a mind map format to visually organize related keywords and concepts. This makes it possible to understand the overall picture of the data at a glance. The data analysis unit can also develop tools that automatically generate visual notes and mind maps to enable users to easily visually display data summaries. For example, it can provide a function to visualize summary text with drag and drop. This makes it easier to understand visually.

[0061] The data analysis unit can use the emotion estimation function to collect users' emotional reactions to summarized ideas and improve the accuracy of summaries based on the collected data. For example, the data analysis unit can collect users' emotional reactions to summarized ideas in real time and improve the accuracy of summaries based on the collected data. For example, the data analysis unit can prioritize summaries with a high number of positive reactions. The data analysis unit can also use the emotion estimation function to collect feedback on summarized ideas and regenerate summaries if there are a high number of negative reactions. The data analysis unit can also analyze users' emotional reaction data and identify areas for improvement in the summaries based on the results. For example, the data analysis unit can suggest correcting parts with low emotion scores. This can improve the accuracy of summaries.

[0062] The text generation unit uses an emotion estimation function when generating text, allowing it to prioritize the use of expressions that elicit positive emotions. For example, the text generation unit performs emotion analysis when the generation AI generates text, and prioritizes the use of expressions that elicit positive emotions. For example, it selects phrases that convey emotions of joy or surprise. The text generation unit also uses the emotion estimation function to filter expressions that elicit positive emotions from the text. For example, it prioritizes the use of expressions with high emotion scores. The text generation unit also performs emotion analysis when generating text, automatically tags expressions that elicit positive emotions, and prioritizes their reflection in the text. This allows the use of expressions that elicit positive emotions to be prioritized.

[0063] The text generation unit can take into account not only the company's brand guidelines but also the preferences and interests of the target audience when generating text. For example, when the generation AI generates text, the text generation unit takes into account the company's brand guidelines and the preferences and interests of the target audience. For example, it uses language that reflects the target audience's age group and interests. The text generation unit can also analyze the preferences and interests of the target audience and build a system that customizes text based on that. For example, it can select appropriate topics for groups with specific interests. The text generation unit can also integrate the company's brand guidelines and target audience data, allowing the generation AI to automatically generate optimal text. For example, it can use language that resonates with the target audience while maintaining the brand image. This makes it possible to generate text that takes into account the preferences and interests of the target audience.

[0064] The text generation unit can analyze the effectiveness of past newsletters when generating text and incorporate the most effective expressions and structures. For example, the text generation unit uses a generation AI to analyze the effectiveness of past newsletters and incorporate the most effective expressions and structures. For example, it prioritizes the use of expressions with high open rates and click rates. The text generation unit also analyzes data from past newsletters and builds a system to identify effective expressions and structures. For example, it can extract elements of successful newsletters and reflect them in new text. The text generation unit also uses a generation AI to learn the effectiveness of past newsletters and automatically generate the most effective expressions and structures. For example, it can create optimal text based on past data. This makes it possible to generate text that incorporates the most effective expressions and structures.

[0065] When generating text, the text generation unit automatically generates versions that are compatible with different languages ​​and cultures, allowing information to be provided from an international perspective. For example, when a generation AI generates text, the text generation unit automatically generates versions that are compatible with different languages ​​and cultures. For example, it translates into multiple languages ​​such as English, French, and Chinese. The text generation unit also automatically generates text that is compatible with different cultures, building a system that provides information from an international perspective. For example, it can use expressions that take cultural nuances into consideration. The text generation unit also uses an automatic translation function to generate newsletters that are compatible with different languages ​​and cultures, allowing information to be provided from an international perspective. For example, it can create text that reflects the characteristics of each region. This allows information to be provided from an international perspective.

[0066] The text generation unit automatically incorporates visual content (images and videos) when generating text, making it possible to create visually appealing newsletters. For example, the text generation unit automatically incorporates visual content when the generation AI generates text. For example, it automatically inserts related images and videos. The text generation unit also builds a system that automatically generates visual content and incorporates it into newsletters. For example, it can select appropriate visuals using image recognition technology. The text generation unit also integrates text and visual content with the generation AI to automatically generate visually appealing newsletters. For example, it can automatically adjust the layout to effectively position visuals. This makes it possible to create visually appealing newsletters.

[0067] The text generation unit uses the emotion estimation function when generating text to monitor the user's emotional reactions in real time and continuously search for optimal expressions. For example, the text generation unit uses the emotion estimation function when the generation AI generates text to monitor the user's emotional reactions in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The text generation unit also builds a system that continuously optimizes text expressions based on the user's emotional reaction data. For example, it can prioritize the use of expressions that evoke a high number of positive emotional reactions. The text generation unit also collects emotion estimation data in real time and develops a system that dynamically adjusts text expressions. For example, it can modify text in response to changes in the user's emotions. This makes it possible to monitor the user's emotional reactions in real time and continuously search for optimal expressions.

[0068] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0069] The automatic newsletter creation system can further include a feedback collection unit that collects user feedback and reflects it in the next newsletter. For example, a survey can be sent to newsletter recipients to collect satisfaction with the content and areas for improvement. The feedback collection unit can also analyze data such as recipient click rates and open rates to identify which content attracted the most interest. Furthermore, the feedback collection unit can improve the content and structure of the newsletter based on the collected feedback and reflect it in the next distribution. This makes it possible to create a newsletter that is more suited to the needs of recipients.

[0070] The data collection unit can also collect data from a company's social media accounts to enhance the company's online presence. For example, it can analyze Twitter and Instagram posts to gather information about the company's latest activities and campaigns. The data collection unit can also analyze social media engagement data to identify which posts generated the most interest. Furthermore, the data collection unit can tailor the content of newsletters based on social media data to provide more relevant information to recipients. This can enhance the company's online presence and create newsletters that attract recipients' attention.

[0071] The information gathering department can further collect feedback from company employees and create a newsletter that reflects internal perspectives. For example, the information gathering department can conduct an employee survey to collect opinions and impressions on company initiatives and projects. The information gathering department can also interview employees to collect internal information about the company. Furthermore, the information gathering department can adjust the content of the newsletter based on feedback from employees to provide information that reflects the company's internal perspective. In this way, a newsletter containing internal company information can be created, increasing the company's transparency to recipients.

[0072] The information gathering department can also collect feedback from the company's customers and create newsletters that reflect their opinions. For example, it can conduct customer surveys to collect opinions and impressions about products and services. The information gathering department can also analyze customer reviews and ratings to understand customer needs and expectations. Furthermore, the information gathering department can adjust the content of the newsletter based on customer feedback and provide information that reflects customer opinions. This makes it possible to create newsletters that meet customer needs and improve customer satisfaction.

[0073] The information gathering department can further collect opinions from industry experts and influencers to create newsletters that reflect their expert perspectives. For example, the information gathering department can analyze blogs and articles from industry experts and influencers to gather the latest trends and insights. The information gathering department can also conduct interviews with experts and influencers to gather first-hand opinions and advice. Furthermore, the information gathering department can adjust the content of the newsletter based on the collected expert opinions to provide valuable information to recipients. This allows the newsletter to be created to reflect an expert perspective and gain the trust of recipients.

[0074] The information collection unit can use the emotion estimation function on the collected data to eliminate articles with negative sentiment. For example, it performs emotion analysis on the data collected by the generation AI and eliminates articles with high negative sentiment scores. The information collection unit also uses the emotion estimation function to filter out articles that evoke negative sentiment from the collected data. For example, it can eliminate articles with emotion scores below a certain level. Furthermore, the information collection unit performs emotion analysis on the collected data and automatically tags articles with negative sentiment and excludes them from the database. This makes it possible to eliminate articles with negative sentiment.

[0075] The data analysis unit can use the emotion estimation function on the data to be analyzed to eliminate keywords and phrases that evoke negative emotions. For example, it performs emotion analysis on the data to be analyzed by the generation AI to eliminate keywords and phrases that evoke negative emotions. The data analysis unit also uses the emotion estimation function to filter out keywords and phrases that evoke negative emotions from the analyzed data. For example, it can eliminate keywords and phrases with an emotion score below a certain level. Furthermore, the data analysis unit performs emotion analysis on the analyzed data to automatically tag keywords and phrases that evoke negative emotions and exclude them from the summary. This makes it possible to eliminate keywords and phrases that evoke negative emotions.

[0076] The data analysis unit uses an emotion estimation function on the data being analyzed to predict the user's emotional response and generate summaries that elicit positive responses. For example, it performs emotion analysis on the data being analyzed by the generation AI and generates summaries that elicit positive emotions. The data analysis unit also uses the emotion estimation function to filter summaries that elicit positive emotions from the analyzed data. For example, it can prioritize the generation of summaries with high emotion scores. Furthermore, the data analysis unit performs emotion analysis on the analyzed data, automatically tags summaries that elicit positive emotions, and prioritizes their inclusion in the newsletter. This makes it possible to generate summaries that elicit positive emotions.

[0077] The text generation unit can use the emotion estimation function when generating text to eliminate expressions that evoke negative emotions. For example, the generation AI performs emotion analysis when generating text to eliminate expressions that evoke negative emotions. The text generation unit also uses the emotion estimation function to filter expressions that evoke negative emotions from the text. For example, it can eliminate expressions with an emotion score below a certain level. Furthermore, the text generation unit performs emotion analysis when generating text to automatically tag and exclude expressions that evoke negative emotions from the text. This makes it possible to eliminate expressions that evoke negative emotions.

[0078] The text generation unit uses an emotion estimation function when generating text to predict the user's emotional response and prioritize the use of expressions that elicit positive responses. For example, when the generation AI generates text, it performs emotion analysis and prioritizes the use of expressions that elicit positive emotions. The text generation unit also uses the emotion estimation function to filter expressions that elicit positive emotions from the text. For example, it prioritizes the use of expressions with high emotion scores. Furthermore, the text generation unit performs emotion analysis when generating text, automatically tags expressions that elicit positive emotions, and prioritizes their reflection in the text. This allows the use of expressions that elicit positive emotions to be prioritized.

[0079] The processing flow of the second embodiment will be briefly explained below.

[0080] Step 1: The information collection department collects data from sources such as the company's official website, press articles, and interview transcripts. For example, the information collection department uses web scraping technology to collect the latest news and press releases posted on the company's official website. The information collection department can also use APIs to collect the content of press articles. In addition, the information collection department can analyze interview transcripts and audio recordings to collect interview transcript data. Step 2: The data analysis unit analyzes the collected data and extracts important information. For example, the data analysis unit uses natural language processing technology to analyze text and identify important keywords and phrases. The data analysis unit can also use generative AI to extract important topics such as a company's new product announcements, performance reports, and social contribution activities. Furthermore, the data analysis unit can use text mining technology to analyze data patterns and extract important information. Step 3: The text generator generates the newsletter text based on the extracted key information. For example, the text generator uses generative AI and natural language generation technology to construct text that is easy to read and accurately conveys information. The text generator can also format the newsletter according to the company's brand guidelines to create a visually appealing newsletter. Furthermore, the text generator can use generative AI to automatically distribute the newsletter text.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0085] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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).

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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).

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0115] 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.

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, 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.

[0117] 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.

[0118] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0119] 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).

[0120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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."

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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]

[0148] 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. The information gathering department collects data from sources such as official company websites, press articles, and interview records. a data analysis unit that analyzes the data collected by the information collection unit and extracts important information; a text generation unit that generates a newsletter text based on the important information extracted by the data analysis unit. A system characterized by:

2. The information collecting unit Prioritize collection of articles with positive sentiment 2. The system of claim 1.

3. The information collecting unit Collect data including unofficial information such as social media and blogs 2. The system of claim 1.

4. The information collecting unit Compare the collected data with the company's past newsletters and automatically eliminate duplicates and similar content 2. The system of claim 1.

5. The information collecting unit Gather information from competitors' official websites and press articles to understand industry-wide trends 2. The system of claim 1.

6. The information collecting unit Automatically translate collected data into different languages ​​to gather information from an international perspective 2. The system of claim 1.

7. The information collecting unit Analyze users' emotional reactions to collected data in real time and prioritize information that elicits positive reactions.

2. The system of claim 1.

8. The data analysis unit Prioritize the extraction of keywords and phrases that have positive sentiment toward the data being analyzed.

2. The system of claim 1.

Images