System

Abstract

An object of a system according to an embodiment is to reduce man-hours required for creating and distributing a newsletter and to efficiently provide information.SOLUTION: A system includes a topic extraction unit, a newsletter creation unit, and a mail text creation unit. A topic extraction part analyzes the latest press release or collected articles and the exchange of in-house mails, and extracts topics. The newsletter creation unit creates a newsletter including a visual on the basis of the topics extracted by the topic extraction unit. The mail text creation unit creates a mail text associated with distribution of the newsletter created by the newsletter creation 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] With conventional technology, creating and distributing newsletters to provide regular information required a significant amount of man-hours, making it difficult to allocate resources.

[0005] The system according to the embodiment aims to reduce the number of steps required to create and distribute newsletters and to provide information efficiently. [Means for solving the problem]

[0006] The system according to the embodiment includes a topic extraction unit, a newsletter creation unit, and an email body creation unit. The topic extraction unit analyzes the most recent press releases or interview articles and internal email exchanges to extract topics. The newsletter creation unit creates a newsletter including visuals based on the topics extracted by the topic extraction unit. The email body creation unit creates the email body associated with the distribution of the newsletter created by the newsletter creation unit. [Effects of the Invention]

[0007] The system according to the embodiment can reduce the number of steps required to create and distribute newsletters, and can provide information efficiently. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention uses a generation AI to increase awareness of a company and its services and build relationships. This system analyzes recent press releases, interview articles, and internal email exchanges to extract topics, create a newsletter with visuals, and also creates the email body for distribution. This significantly reduces labor costs while enabling effective information provision. For example, the generation AI analyzes recent press releases, interview articles, and internal email exchanges to extract topics. The generation AI then creates a newsletter with visuals based on the extracted topics. The generation AI also creates the email body for the newsletter. The person in charge only needs to perform a final check and distribute the newsletter to stakeholders. This allows the generation AI to complete a monthly newsletter in just a few minutes, a task that previously took several hours. This streamlines information provision tasks, which typically require a high level of labor and have little immediate effect, and helps increase awareness of the company and its services and build relationships. For example, regular newsletter distribution makes it easier to build lasting relationships with the media, users, and business partners.

[0029] An information provision system according to an embodiment includes a topic extraction unit, a newsletter creation unit, and an email body creation unit. The topic extraction unit analyzes recent press releases, news articles, and internal email exchanges to extract topics. For example, the topic extraction unit can use natural language processing technology to analyze the contents of press releases, news articles, and internal emails to extract important keywords and phrases. The topic extraction unit can also use generation AI to analyze the contents of press releases, news articles, and internal emails to extract topics. The newsletter creation unit creates a newsletter including visuals based on the topics extracted by the topic extraction unit. For example, the newsletter creation unit can select appropriate images from an image database and automatically generate graphs and charts related to the topics. The newsletter creation unit can also use generation AI to create a newsletter including visuals related to the topics. The email body creation unit creates email bodies to accompany the newsletters created by the newsletter creation unit. For example, the email body creation unit can generate appropriate sentences according to the topics based on pre-set templates and context. The email body creation unit can also use the generation AI to create the email body for newsletter distribution. This enables the information provision system according to the embodiment to provide information effectively while significantly reducing the amount of work required. For example, the generation AI analyzes the most recent press releases, interview articles, and internal email exchanges, extracts topics, creates a newsletter including visuals, and also creates the email body for distribution. The person in charge only needs to perform a final check and distribute it to stakeholders. As a result, when creating a monthly newsletter, a task that previously took several hours can be completed in just a few minutes using the generation AI.

[0030] The topic extraction unit can use natural language processing technology to analyze the content of press releases, interview articles, and internal emails to extract important keywords or phrases. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. The topic extraction unit can, for example, use morphological analysis to analyze the content of press releases, interview articles, and internal emails to extract important keywords. The topic extraction unit can also use grammatical analysis to analyze the structure of sentences and extract important phrases. The topic extraction unit can also use semantic analysis to analyze the meaning of sentences and extract important keywords and phrases. This extraction of important keywords and phrases improves the accuracy of topics. Some or all of the above-mentioned processing in the topic extraction unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the topic extraction unit can input the content of press releases, interview articles, and internal emails into a generation AI and have the generation AI extract important keywords and phrases.

[0031] The newsletter creation unit can select images from an image database and automatically generate graphs and charts related to the topics. The image database includes, but is not limited to, images in JPEG format, PNG format, and the like. The newsletter creation unit, for example, selects appropriate images from the image database and inserts them into the newsletter. The newsletter creation unit can also automatically generate graphs and charts related to the topics. For example, the newsletter creation unit generates graphs and charts based on data related to the topics and inserts them into the newsletter. The newsletter creation unit can also use a generation AI to create a newsletter that includes visuals related to the topics. For example, the newsletter creation unit inputs data related to the topics into the generation AI and causes the generation AI to create a newsletter that includes visuals. This generates a visually appealing newsletter that more easily attracts the recipient's attention. Some or all of the above-described processing in the newsletter creation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

[0032] The email body creation unit can generate sentences according to topics based on a preset template or context. Pre-set templates include, but are not limited to, standard formats and writing styles. The email body creation unit can generate sentences according to topics based on, for example, a preset template. The email body creation unit can also generate appropriate sentences according to topics based on context. For example, the email body creation unit generates sentences with an appropriate writing style and length according to the content of the topic. The email body creation unit can also use a generation AI to create email bodies for newsletter distribution. For example, the email body creation unit can input topics and templates into the generation AI and have the generation AI create the email body. This can significantly reduce the time required to create emails. Some or all of the above-described processing in the email body creation unit can be performed using, for example, a generation AI, or without using a generation AI.

[0033] The topic extraction unit can improve the accuracy of extraction based on data from past press releases or news articles. Data from past press releases or news articles can be, for example, email, paper, or a specific format, but is not limited to these examples. The topic extraction unit, for example, extracts frequently occurring keywords from past press releases and reflects them in current topics. The topic extraction unit can also analyze the content of past news articles to extract related topics. The topic extraction unit can also evaluate the importance of topics based on past data and improve the accuracy of extraction. For example, the topic extraction unit can input data from past press releases or news articles into a generation AI and have the generation AI perform analysis to improve the accuracy of extraction. This improves the accuracy of topic extraction by referring to past data. Some or all of the above-described processing in the topic extraction unit can be performed, for example, using the generation AI, or without using the generation AI.

[0034] The topic extraction unit can extract important topics based on trends in a specific industry or market. Examples of specific industry or market trends include, but are not limited to, industry reports and market analysis data. The topic extraction unit, for example, analyzes current market trends and extracts relevant topics. The topic extraction unit can also refer to the latest news in a specific industry to extract important topics. The topic extraction unit can also evaluate the importance of topics based on the opinions of industry experts and extract them. For example, the topic extraction unit can input industry reports and market analysis data into the generation AI and have the generation AI extract important topics. This allows more relevant topics to be extracted by taking industry and market trends into consideration. Some or all of the above-described processing in the topic extraction unit can be performed, for example, using the generation AI, or without using the generation AI.

[0035] The topic extraction unit can improve the accuracy of extraction based on feedback from different departments within the company. Feedback from different departments within the company includes, but is not limited to, survey results and meeting minutes. For example, the topic extraction unit collects feedback from each department and reflects it in topic extraction. The topic extraction unit can also extract topics taking into account important matters for each department. The topic extraction unit can also adjust the priority of topics based on the feedback. For example, the topic extraction unit can input feedback from different departments within the company into the generation AI and have the generation AI perform analysis to improve extraction accuracy. This improves the accuracy of topic extraction by reflecting internal feedback. Some or all of the above-described processing in the topic extraction unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0036] The topic extraction unit can extract related topics based on internal project progress information. Internal project progress information includes, but is not limited to, progress reports and task management systems. The topic extraction unit extracts related topics based on, for example, the progress status of an ongoing project. The topic extraction unit can also extract topics taking into account important project milestones. The topic extraction unit can also adjust the priority of topics based on feedback from the project team. For example, the topic extraction unit can input internal project progress information into the generation AI and have the generation AI extract related topics. This allows more relevant topics to be extracted by taking project progress information into consideration. Some or all of the above-described processing in the topic extraction unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0037] The topic extraction unit can extract topics based on data from external news sources or social media. Examples of external news sources or social media data include, but are not limited to, news APIs and social media posting data. For example, the topic extraction unit collects the latest news from external news sites and extracts related topics. The topic extraction unit can also analyze social media trends and extract important topics. The topic extraction unit can also evaluate the importance of topics based on external data and extract them. For example, the topic extraction unit can input data from external news sources or social media into the generation AI and have the generation AI extract topics. By referencing external data, the accuracy of topic extraction can be improved. Some or all of the above-described processing in the topic extraction unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0038] The topic extraction unit can extract topics based on the frequency of occurrence of specific keywords or phrases. Examples of the frequency of occurrence of specific keywords or phrases include, but are not limited to, frequency thresholds and co-occurrence network analysis. For example, the topic extraction unit analyzes the frequency of occurrence of specific keywords and extracts related topics. The topic extraction unit can also extract important topics based on the frequency of occurrence of phrases. The topic extraction unit can also adjust the priority of topics based on the frequency of occurrence of keywords. For example, the topic extraction unit can input the frequency of occurrence of specific keywords or phrases into the generation AI and have the generation AI extract topics. By extracting topics based on the frequency of occurrence of keywords or phrases, important information is not overlooked. Some or all of the above-described processing in the topic extraction unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

[0039] The newsletter creation unit can improve the accuracy of creation based on the design or content of past newsletters. Examples of the design or content of past newsletters include, but are not limited to, design templates and content archives. The newsletter creation unit, for example, creates a current newsletter based on the design of a past newsletter. The newsletter creation unit can also analyze the content of past newsletters and extract related topics. The newsletter creation unit can also evaluate the importance of a newsletter based on past data and improve the accuracy of creation. For example, the newsletter creation unit can input the design and content of past newsletters into the generation AI and cause the generation AI to perform analysis to improve the accuracy of creation. This improves the accuracy of newsletter creation by referring to past data. Some or all of the above-described processing in the newsletter creation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

[0040] The newsletter creation unit can customize the newsletter based on a specific target audience. Examples of the specific target audience include, but are not limited to, age groups, occupations, and interests. The newsletter creation unit customizes the content of the newsletter based on the interests and concerns of the target audience. The newsletter creation unit can also adjust the design based on demographic information of the target audience. The newsletter creation unit can also optimize the content of the newsletter based on the target audience's past responses. For example, the newsletter creation unit can input the content of the newsletter into a generation AI based on the interests and concerns of the target audience and have the generation AI perform the customization. This enables more effective information provision by customizing the newsletter to the target audience. Some or all of the above-described processing in the newsletter creation unit can be performed, for example, using the generation AI or without the generation AI.

[0041] The newsletter creation unit can adjust the layout or content placement based on the importance of the topic. The importance of the topic includes, but is not limited to, for example, an evaluation of influence and setting of priorities. For example, the newsletter creation unit places important topics in prominent positions. The newsletter creation unit can also adjust the placement of content according to the importance of the topic. The newsletter creation unit can also optimize the layout based on the priority of the topic. For example, the newsletter creation unit can input the importance of the topic into the generation AI and cause the generation AI to adjust the layout and content placement. This allows for adjusting the layout based on the importance of the topic, thereby providing a more effective newsletter. Some or all of the above-described processing in the newsletter creation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0042] The newsletter creation unit can adjust the design based on internal brand guidelines. Internal brand guidelines include, but are not limited to, logo usage regulations and color palettes. The newsletter creation unit can adjust the newsletter design, for example, in accordance with the internal brand guidelines. The newsletter creation unit can also provide a unified design using brand colors and fonts. The newsletter creation unit can also optimize the newsletter layout based on the brand guidelines. For example, the newsletter creation unit can input the internal brand guidelines into a generation AI and have the generation AI adjust the design. This allows a unified design to be provided by taking the brand guidelines into consideration. Some or all of the above-mentioned processing in the newsletter creation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0043] The newsletter creation unit can enhance the visuals based on an external design template. Examples of external design templates include, but are not limited to, template types and usage conditions. The newsletter creation unit can enhance the design of a newsletter based on, for example, an external design template. The newsletter creation unit can also select appropriate visual elements from the design template and incorporate them into the newsletter. The newsletter creation unit can also optimize the layout of the newsletter by referring to the external design template. For example, the newsletter creation unit can input the external design template into the generation AI and have the generation AI enhance the visuals. This improves the visual quality by referring to the external design template. Some or all of the above-described processing in the newsletter creation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0044] The newsletter creation unit can create a special edition based on a specific event or campaign. Examples of a specific event or campaign include, but are not limited to, the date and time of the event, its purpose, and its target audience. The newsletter creation unit can, for example, create a special edition of a newsletter tailored to a specific event. The newsletter creation unit can also create a special edition that covers topics related to the campaign. The newsletter creation unit can also adjust the design of the newsletter based on the theme of the event or campaign. For example, the newsletter creation unit can input information about a specific event or campaign into the generation AI and have the generation AI create a special edition. This allows for more effective information provision by creating a special edition tailored to a specific event or campaign. Some or all of the above-described processing in the newsletter creation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0045] The email body creation unit can improve the accuracy of creation based on data of past email bodies. Data of past email bodies includes, but is not limited to, email archives and content analysis. The email body creation unit creates the current email body based on, for example, data of past email bodies. The email body creation unit can also analyze the content of past email bodies and extract related topics. The email body creation unit can also evaluate the importance of the email body based on past data and improve the accuracy of creation. For example, the email body creation unit can input data of past email bodies into a generation AI and cause the generation AI to perform analysis to improve the accuracy of creation. This improves the accuracy of email body creation by referring to past data. Some or all of the above-mentioned processing in the email body creation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

[0046] The email body creation unit can customize the email body based on a specific target audience. Examples of the specific target audience include, but are not limited to, age groups, occupations, and interests. The email body creation unit customizes the content of the email body based on the interests and concerns of the target audience. The email body creation unit can also adjust the tone based on demographic information of the target audience. The email body creation unit can also optimize the content of the email body based on the target audience's past responses. For example, the email body creation unit can input the content of the email body into a generation AI based on the interests and concerns of the target audience and have the generation AI perform the customization. This enables more effective information provision by customizing the email to the target audience. Some or all of the above-described processing in the email body creation unit can be performed, for example, using the generation AI or without using the generation AI.

[0047] The email body creation unit can adjust the content of the email body based on the importance of the topic. The importance of the topic includes, but is not limited to, for example, an evaluation of influence and setting of priority. For example, the email body creation unit creates an email body that emphasizes important topics. The email body creation unit can also adjust the content of the email body according to the importance of the topic. The email body creation unit can also optimize the composition of the email body based on the priority of the topic. For example, the email body creation unit can input the importance of the topic to the generation AI and have the generation AI adjust the content of the email body. By adjusting the content of the email body based on the importance of the topic, more effective information can be provided. Some or all of the above-described processing in the email body creation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0048] The email body creation unit can adjust the content based on internal communication guidelines. Internal communication guidelines include, but are not limited to, language specifications and formatting standards. The email body creation unit adjusts the content of the email body, for example, in accordance with the internal communication guidelines. The email body creation unit can also use an appropriate tone and language based on the guidelines. The email body creation unit can also optimize the composition of the email body based on the guidelines. For example, the email body creation unit can input the internal communication guidelines into a generation AI and have the generation AI adjust the content. This makes it possible to provide email bodies with a consistent feel by taking the communication guidelines into consideration. Some or all of the above-mentioned processing in the email body creation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

[0049] The email body creation unit can incorporate effective expressions based on an external email marketing tool. Examples of external email marketing tools include, but are not limited to, the type of tool, how to use it, and effectiveness measurement. For example, the email body creation unit extracts effective expressions from the external email marketing tool and incorporates them into the email body. The email body creation unit can also optimize the content of the email body based on data from the marketing tool. The email body creation unit can also use effective expressions to improve the response rate of the email body. For example, the email body creation unit can input data from the external email marketing tool into the generation AI and cause the generation AI to incorporate effective expressions. This improves the quality of the email body by referring to the external tool. Some or all of the above-described processing in the email body creation unit can be performed, for example, using the generation AI, or without using the generation AI.

[0050] The email body creation unit can create a special version based on a specific event or campaign. A specific event or campaign may include, but is not limited to, the date and time of the event, its purpose, and its target audience. The email body creation unit can create, for example, a special version of the email body tailored to a specific event. The email body creation unit can also create a special version that covers topics related to the campaign. The email body creation unit can also adjust the content of the email body based on the theme of the event or campaign. For example, the email body creation unit can input information about a specific event or campaign into the generation AI and have the generation AI create a special version. This allows for more effective information provision by creating a special version tailored to a specific event or campaign. Some or all of the above-described processing in the email body creation unit can be performed, for example, using the generation AI, or without using the generation AI.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The topic extraction unit can also determine the priority of topics based on the user's past behavioral history. For example, it analyzes data on links the user has clicked and pages they have viewed in the past to prioritize topics that are likely to be of interest. It can also prioritize topics related to events the user has previously attended or products they have purchased. It can also extract related topics based on content that the user has previously rated highly. This makes it possible to provide more personalized information by taking the user's past behavioral history into consideration.

[0053] The topic extraction unit can also evaluate the importance of topics based on the opinions of external experts. For example, it can analyze blogs and articles written by industry experts to extract important topics. It can also extract related topics based on the content of interviews and lectures by experts. It can also analyze social media posts by experts to evaluate the importance of topics. This allows the provision of more reliable information by incorporating the opinions of external experts.

[0054] The topic extraction unit can also extract topics based on news and events in a specific region. For example, it can analyze local news sites and event calendars to extract related topics. It can also analyze local social media posts to extract important topics. It can also evaluate the importance of topics based on the opinions of local experts and influencers. This allows for more targeted information provision by providing information related to a specific region.

[0055] The topic extraction unit can also monitor the frequency of specific keywords in real time and extract topics. For example, it can analyze news sites and social media posts in real time to extract frequently occurring keywords. Also, if the frequency of a specific keyword increases sharply, it can prioritize the extraction of topics related to that keyword. Furthermore, it can evaluate the importance of topics based on the results of real-time monitoring. This makes it possible to provide the latest information quickly.

[0056] The topic extraction unit can also extract topics based on user behavior data during a specific time period. For example, it can analyze content that a user frequently accesses during a specific time period and extract related topics. It can also determine the priority of topics based on the user's activities during a specific time period. It can also analyze the user's behavior patterns during a specific time period and evaluate the importance of topics. This makes it possible to provide more personalized information by taking user behavior data into consideration.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The topic extraction unit analyzes recent press releases, interview articles, and internal email correspondence to extract topics. For example, it uses natural language processing technology or generative AI to extract important keywords and phrases. Step 2: The newsletter creation unit creates a newsletter, including visuals, based on the topics extracted by the topic extraction unit. For example, it selects appropriate images from an image database and automatically generates graphs and charts related to the topics. It is also possible to create a newsletter using generative AI. Step 3: The email body creation unit creates the email body for the newsletter created by the newsletter creation unit. For example, it generates appropriate sentences based on the topic based on pre-set templates and context. It is also possible to create the email body using generative AI.

[0059] (Example 2) A system according to an embodiment of the present invention uses a generation AI to increase awareness of a company and its services and build relationships. This system analyzes recent press releases, interview articles, and internal email exchanges to extract topics, create a newsletter with visuals, and also creates the email body for distribution. This significantly reduces labor costs while enabling effective information provision. For example, the generation AI analyzes recent press releases, interview articles, and internal email exchanges to extract topics. The generation AI then creates a newsletter with visuals based on the extracted topics. The generation AI also creates the email body for the newsletter. The person in charge only needs to perform a final check and distribute the newsletter to stakeholders. This allows the generation AI to complete a monthly newsletter in just a few minutes, a task that previously took several hours. This streamlines information provision tasks, which typically require a high level of labor and have little immediate effect, and helps increase awareness of the company and its services and build relationships. For example, regular newsletter distribution makes it easier to build lasting relationships with the media, users, and business partners.

[0060] An information provision system according to an embodiment includes a topic extraction unit, a newsletter creation unit, and an email body creation unit. The topic extraction unit analyzes recent press releases, news articles, and internal email exchanges to extract topics. For example, the topic extraction unit can use natural language processing technology to analyze the contents of press releases, news articles, and internal emails to extract important keywords and phrases. The topic extraction unit can also use generation AI to analyze the contents of press releases, news articles, and internal emails to extract topics. The newsletter creation unit creates a newsletter including visuals based on the topics extracted by the topic extraction unit. For example, the newsletter creation unit can select appropriate images from an image database and automatically generate graphs and charts related to the topics. The newsletter creation unit can also use generation AI to create a newsletter including visuals related to the topics. The email body creation unit creates email bodies to accompany the newsletters created by the newsletter creation unit. For example, the email body creation unit can generate appropriate sentences according to the topics based on pre-set templates and context. The email body creation unit can also use the generation AI to create the email body for newsletter distribution. This enables the information provision system according to the embodiment to provide information effectively while significantly reducing the amount of work required. For example, the generation AI analyzes the most recent press releases, interview articles, and internal email exchanges, extracts topics, creates a newsletter including visuals, and also creates the email body for distribution. The person in charge only needs to perform a final check and distribute it to stakeholders. As a result, when creating a monthly newsletter, a task that previously took several hours can be completed in just a few minutes using the generation AI.

[0061] The topic extraction unit can use natural language processing technology to analyze the content of press releases, interview articles, and internal emails to extract important keywords or phrases. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. The topic extraction unit can, for example, use morphological analysis to analyze the content of press releases, interview articles, and internal emails to extract important keywords. The topic extraction unit can also use grammatical analysis to analyze the structure of sentences and extract important phrases. The topic extraction unit can also use semantic analysis to analyze the meaning of sentences and extract important keywords and phrases. This extraction of important keywords and phrases improves the accuracy of topics. Some or all of the above-mentioned processing in the topic extraction unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the topic extraction unit can input the content of press releases, interview articles, and internal emails into a generation AI and have the generation AI extract important keywords and phrases.

[0062] The newsletter creation unit can select images from an image database and automatically generate graphs and charts related to the topics. The image database includes, but is not limited to, images in JPEG format, PNG format, and the like. The newsletter creation unit, for example, selects appropriate images from the image database and inserts them into the newsletter. The newsletter creation unit can also automatically generate graphs and charts related to the topics. For example, the newsletter creation unit generates graphs and charts based on data related to the topics and inserts them into the newsletter. The newsletter creation unit can also use a generation AI to create a newsletter that includes visuals related to the topics. For example, the newsletter creation unit inputs data related to the topics into the generation AI and causes the generation AI to create a newsletter that includes visuals. This generates a visually appealing newsletter that more easily attracts the recipient's attention. Some or all of the above-described processing in the newsletter creation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

[0063] The email body creation unit can generate sentences according to topics based on a preset template or context. Pre-set templates include, but are not limited to, standard formats and writing styles. The email body creation unit can generate sentences according to topics based on, for example, a preset template. The email body creation unit can also generate appropriate sentences according to topics based on context. For example, the email body creation unit generates sentences with an appropriate writing style and length according to the content of the topic. The email body creation unit can also use a generation AI to create email bodies for newsletter distribution. For example, the email body creation unit can input topics and templates into the generation AI and have the generation AI create the email body. This can significantly reduce the time required to create emails. Some or all of the above-described processing in the email body creation unit can be performed using, for example, a generation AI, or without using a generation AI.

[0064] The topic extraction unit can estimate a user's emotions and prioritize topics to be extracted based on the estimated user emotions. To estimate a user's emotions, for example, a sentiment analysis algorithm can be used. Sentiment analysis algorithms include, but are not limited to, text analysis, voice analysis, and facial expression analysis. The topic extraction unit can estimate a user's emotions using text analysis and prioritize topics based on the estimated emotions. The topic extraction unit can also estimate a user's emotions using voice analysis and prioritize topics. The topic extraction unit can also estimate a user's emotions using facial expression analysis and prioritize topics. For example, if a user is excited, positive news and success stories can be prioritized. If a user is stressed, relaxing topics can be prioritized. If a user is neutral, balanced topics can be extracted. This allows for more appropriate information to be provided by adjusting the priority of topics according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the topic extraction unit may be performed using, or without, the generation AI.

[0065] The topic extraction unit can improve the accuracy of extraction based on data from past press releases or news articles. Data from past press releases or news articles can be, for example, email, paper, or a specific format, but is not limited to these examples. The topic extraction unit, for example, extracts frequently occurring keywords from past press releases and reflects them in current topics. The topic extraction unit can also analyze the content of past news articles to extract related topics. The topic extraction unit can also evaluate the importance of topics based on past data and improve the accuracy of extraction. For example, the topic extraction unit can input data from past press releases or news articles into a generation AI and have the generation AI perform analysis to improve the accuracy of extraction. This improves the accuracy of topic extraction by referring to past data. Some or all of the above-described processing in the topic extraction unit can be performed, for example, using the generation AI, or without using the generation AI.

[0066] The topic extraction unit can extract important topics based on trends in a specific industry or market. Examples of specific industry or market trends include, but are not limited to, industry reports and market analysis data. The topic extraction unit, for example, analyzes current market trends and extracts relevant topics. The topic extraction unit can also refer to the latest news in a specific industry to extract important topics. The topic extraction unit can also evaluate the importance of topics based on the opinions of industry experts and extract them. For example, the topic extraction unit can input industry reports and market analysis data into the generation AI and have the generation AI extract important topics. This allows more relevant topics to be extracted by taking industry and market trends into consideration. Some or all of the above-described processing in the topic extraction unit can be performed, for example, using the generation AI, or without using the generation AI.

[0067] The topic extraction unit can improve the accuracy of extraction based on feedback from different departments within the company. Feedback from different departments within the company includes, but is not limited to, survey results and meeting minutes. For example, the topic extraction unit collects feedback from each department and reflects it in topic extraction. The topic extraction unit can also extract topics taking into account important matters for each department. The topic extraction unit can also adjust the priority of topics based on the feedback. For example, the topic extraction unit can input feedback from different departments within the company into the generation AI and have the generation AI perform analysis to improve extraction accuracy. This improves the accuracy of topic extraction by reflecting internal feedback. Some or all of the above-described processing in the topic extraction unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0068] The topic extraction unit can estimate a user's emotions and adjust the display method of the extracted topics based on the estimated user emotions. To estimate a user's emotions, for example, an emotion analysis algorithm can be used. Emotion analysis algorithms include, but are not limited to, text analysis, voice analysis, and facial expression analysis. For example, the topic extraction unit can estimate a user's emotions using text analysis and adjust the display method of the topics based on the estimated emotions. The topic extraction unit can also estimate a user's emotions using voice analysis and adjust the display method of the topics. The topic extraction unit can also estimate a user's emotions using facial expression analysis and adjust the display method of the topics. For example, if a user is relaxed, a visually appealing display method can be provided. If a user is in a hurry, a concise and to-the-point display method can be provided. If a user is excited, a display method with dynamic effects can be provided. This allows for more appropriate information provision by adjusting the display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the topic extraction unit may be performed using, or without, the generation AI.

[0069] The topic extraction unit can extract related topics based on internal project progress information. Internal project progress information includes, but is not limited to, progress reports and task management systems. The topic extraction unit extracts related topics based on, for example, the progress status of an ongoing project. The topic extraction unit can also extract topics taking into account important project milestones. The topic extraction unit can also adjust the priority of topics based on feedback from the project team. For example, the topic extraction unit can input internal project progress information into the generation AI and have the generation AI extract related topics. This allows more relevant topics to be extracted by taking project progress information into consideration. Some or all of the above-described processing in the topic extraction unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0070] The topic extraction unit can extract topics based on data from external news sources or social media. Examples of external news sources or social media data include, but are not limited to, news APIs and social media posting data. For example, the topic extraction unit collects the latest news from external news sites and extracts related topics. The topic extraction unit can also analyze social media trends and extract important topics. The topic extraction unit can also evaluate the importance of topics based on external data and extract them. For example, the topic extraction unit can input data from external news sources or social media into the generation AI and have the generation AI extract topics. By referencing external data, the accuracy of topic extraction can be improved. Some or all of the above-described processing in the topic extraction unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0071] The topic extraction unit can extract topics based on the frequency of occurrence of specific keywords or phrases. Examples of the frequency of occurrence of specific keywords or phrases include, but are not limited to, frequency thresholds and co-occurrence network analysis. For example, the topic extraction unit analyzes the frequency of occurrence of specific keywords and extracts related topics. The topic extraction unit can also extract important topics based on the frequency of occurrence of phrases. The topic extraction unit can also adjust the priority of topics based on the frequency of occurrence of keywords. For example, the topic extraction unit can input the frequency of occurrence of specific keywords or phrases into the generation AI and have the generation AI extract topics. By extracting topics based on the frequency of occurrence of keywords or phrases, important information is not overlooked. Some or all of the above-described processing in the topic extraction unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

[0072] The newsletter creation unit can estimate a user's emotions and adjust the newsletter design based on the estimated user emotions. To estimate a user's emotions, for example, an emotion analysis algorithm can be used. Examples of emotion analysis algorithms include, but are not limited to, text analysis, voice analysis, and facial expression analysis. For example, the newsletter creation unit can estimate a user's emotions using text analysis and adjust the newsletter design based on the estimated emotions. The newsletter creation unit can also estimate a user's emotions using voice analysis and adjust the newsletter design. The newsletter creation unit can also estimate a user's emotions using facial expression analysis and adjust the newsletter design. For example, if a user is relaxed, a design with soft colors can be provided. If a user is excited, a design with vibrant colors can be provided. If a user is stressed, a simple and calm design can be provided. This allows for a more effective newsletter by adjusting the design according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the newsletter creation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI.

[0073] The newsletter creation unit can improve the accuracy of creation based on the design or content of past newsletters. Examples of the design or content of past newsletters include, but are not limited to, design templates and content archives. The newsletter creation unit, for example, creates a current newsletter based on the design of a past newsletter. The newsletter creation unit can also analyze the content of past newsletters and extract related topics. The newsletter creation unit can also evaluate the importance of a newsletter based on past data and improve the accuracy of creation. For example, the newsletter creation unit can input the design and content of past newsletters into the generation AI and cause the generation AI to perform analysis to improve the accuracy of creation. This improves the accuracy of newsletter creation by referring to past data. Some or all of the above-described processing in the newsletter creation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

[0074] The newsletter creation unit can customize the newsletter based on a specific target audience. Examples of the specific target audience include, but are not limited to, age groups, occupations, and interests. The newsletter creation unit customizes the content of the newsletter based on the interests and concerns of the target audience. The newsletter creation unit can also adjust the design based on demographic information of the target audience. The newsletter creation unit can also optimize the content of the newsletter based on the target audience's past responses. For example, the newsletter creation unit can input the content of the newsletter into a generation AI based on the interests and concerns of the target audience and have the generation AI perform the customization. This enables more effective information provision by customizing the newsletter to the target audience. Some or all of the above-described processing in the newsletter creation unit can be performed, for example, using the generation AI or without the generation AI.

[0075] The newsletter creation unit can adjust the layout or content placement based on the importance of the topic. The importance of the topic includes, but is not limited to, for example, an evaluation of influence and setting of priorities. For example, the newsletter creation unit places important topics in prominent positions. The newsletter creation unit can also adjust the placement of content according to the importance of the topic. The newsletter creation unit can also optimize the layout based on the priority of the topic. For example, the newsletter creation unit can input the importance of the topic into the generation AI and cause the generation AI to adjust the layout and content placement. This allows for adjusting the layout based on the importance of the topic, thereby providing a more effective newsletter. Some or all of the above-described processing in the newsletter creation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0076] The newsletter creation unit can estimate a user's emotion and adjust the color scheme of the newsletter based on the estimated user's emotion. To estimate the user's emotion, for example, an emotion analysis algorithm can be used. Emotion analysis algorithms include, but are not limited to, text analysis, voice analysis, and facial expression analysis. For example, the newsletter creation unit can estimate the user's emotion using text analysis and adjust the color scheme of the newsletter based on the estimated emotion. The newsletter creation unit can also estimate the user's emotion using voice analysis and adjust the color scheme of the newsletter. The newsletter creation unit can also estimate the user's emotion using facial expression analysis and adjust the color scheme of the newsletter. For example, if the user is relaxed, a soft color scheme can be provided. If the user is excited, a vibrant color scheme can be provided. If the user is stressed, a simple, calm color scheme can be provided. By adjusting the color scheme according to the user's emotion, a more effective newsletter can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the newsletter creation unit may be performed using, or without, the generation AI.

[0077] The newsletter creation unit can adjust the design based on internal brand guidelines. Internal brand guidelines include, but are not limited to, logo usage regulations and color palettes. The newsletter creation unit can adjust the newsletter design, for example, in accordance with the internal brand guidelines. The newsletter creation unit can also provide a unified design using brand colors and fonts. The newsletter creation unit can also optimize the newsletter layout based on the brand guidelines. For example, the newsletter creation unit can input the internal brand guidelines into a generation AI and have the generation AI adjust the design. This allows a unified design to be provided by taking the brand guidelines into consideration. Some or all of the above-mentioned processing in the newsletter creation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0078] The newsletter creation unit can enhance the visuals based on an external design template. Examples of external design templates include, but are not limited to, template types and usage conditions. The newsletter creation unit can enhance the design of a newsletter based on, for example, an external design template. The newsletter creation unit can also select appropriate visual elements from the design template and incorporate them into the newsletter. The newsletter creation unit can also optimize the layout of the newsletter by referring to the external design template. For example, the newsletter creation unit can input the external design template into the generation AI and have the generation AI enhance the visuals. This improves the visual quality by referring to the external design template. Some or all of the above-described processing in the newsletter creation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0079] The newsletter creation unit can create a special edition based on a specific event or campaign. Examples of a specific event or campaign include, but are not limited to, the date and time of the event, its purpose, and its target audience. The newsletter creation unit can, for example, create a special edition of a newsletter tailored to a specific event. The newsletter creation unit can also create a special edition that covers topics related to the campaign. The newsletter creation unit can also adjust the design of the newsletter based on the theme of the event or campaign. For example, the newsletter creation unit can input information about a specific event or campaign into the generation AI and have the generation AI create a special edition. This allows for more effective information provision by creating a special edition tailored to a specific event or campaign. Some or all of the above-described processing in the newsletter creation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0080] The email body creation unit can estimate the user's emotion and adjust the tone of the email body based on the estimated user emotion. To estimate the user's emotion, for example, an emotion analysis algorithm can be used. Emotion analysis algorithms include, but are not limited to, text analysis, voice analysis, and facial expression analysis. The email body creation unit can estimate the user's emotion using text analysis and adjust the tone of the email body based on the estimated emotion. The email body creation unit can also estimate the user's emotion using voice analysis and adjust the tone of the email body. The email body creation unit can also estimate the user's emotion using facial expression analysis and adjust the tone of the email body. For example, if the user is relaxed, the email body can be provided with a soft tone. If the user is excited, the email body can be provided with an energetic tone. If the user is stressed, the email body can be provided with a calm tone. Adjusting the tone of the email body according to the user's emotion enables more effective communication. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the email body creation unit may be performed using, or without, the generation AI.

[0081] The email body creation unit can improve the accuracy of creation based on data of past email bodies. Data of past email bodies includes, but is not limited to, email archives and content analysis. The email body creation unit creates the current email body based on, for example, data of past email bodies. The email body creation unit can also analyze the content of past email bodies and extract related topics. The email body creation unit can also evaluate the importance of the email body based on past data and improve the accuracy of creation. For example, the email body creation unit can input data of past email bodies into a generation AI and cause the generation AI to perform analysis to improve the accuracy of creation. This improves the accuracy of email body creation by referring to past data. Some or all of the above-mentioned processing in the email body creation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

[0082] The email body creation unit can customize the email body based on a specific target audience. Examples of the specific target audience include, but are not limited to, age groups, occupations, and interests. The email body creation unit customizes the content of the email body based on the interests and concerns of the target audience. The email body creation unit can also adjust the tone based on demographic information of the target audience. The email body creation unit can also optimize the content of the email body based on the target audience's past responses. For example, the email body creation unit can input the content of the email body into a generation AI based on the interests and concerns of the target audience and have the generation AI perform the customization. This enables more effective information provision by customizing the email to the target audience. Some or all of the above-described processing in the email body creation unit can be performed, for example, using the generation AI or without using the generation AI.

[0083] The email body creation unit can adjust the content of the email body based on the importance of the topic. The importance of the topic includes, but is not limited to, for example, an evaluation of influence and setting of priority. For example, the email body creation unit creates an email body that emphasizes important topics. The email body creation unit can also adjust the content of the email body according to the importance of the topic. The email body creation unit can also optimize the composition of the email body based on the priority of the topic. For example, the email body creation unit can input the importance of the topic to the generation AI and have the generation AI adjust the content of the email body. By adjusting the content of the email body based on the importance of the topic, more effective information can be provided. Some or all of the above-described processing in the email body creation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI.

[0084] The email body creation unit can estimate the user's emotion and adjust the length of the email body based on the estimated user emotion. To estimate the user's emotion, for example, an emotion analysis algorithm can be used. Emotion analysis algorithms include, but are not limited to, text analysis, voice analysis, and facial expression analysis. The email body creation unit can estimate the user's emotion using text analysis and adjust the length of the email body based on the estimated emotion. The email body creation unit can also estimate the user's emotion using voice analysis and adjust the length of the email body. The email body creation unit can also estimate the user's emotion using facial expression analysis and adjust the length of the email body. For example, if the user is in a hurry, a short and to-the-point email body can be provided. If the user is relaxed, a longer email body with detailed explanations can be provided. If the user is excited, a visually stimulating email body can be provided. This allows for more effective communication by adjusting the length of the email body according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the email body creation unit may be performed using, or without, the generation AI.

[0085] The email body creation unit can adjust the content based on internal communication guidelines. Internal communication guidelines include, but are not limited to, language specifications and formatting standards. The email body creation unit adjusts the content of the email body, for example, in accordance with the internal communication guidelines. The email body creation unit can also use an appropriate tone and language based on the guidelines. The email body creation unit can also optimize the composition of the email body based on the guidelines. For example, the email body creation unit can input the internal communication guidelines into a generation AI and have the generation AI adjust the content. This makes it possible to provide email bodies with a consistent feel by taking the communication guidelines into consideration. Some or all of the above-mentioned processing in the email body creation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI.

[0086] The email body creation unit can incorporate effective expressions based on an external email marketing tool. Examples of external email marketing tools include, but are not limited to, the type of tool, how to use it, and effectiveness measurement. For example, the email body creation unit extracts effective expressions from the external email marketing tool and incorporates them into the email body. The email body creation unit can also optimize the content of the email body based on data from the marketing tool. The email body creation unit can also use effective expressions to improve the response rate of the email body. For example, the email body creation unit can input data from the external email marketing tool into the generation AI and cause the generation AI to incorporate effective expressions. This improves the quality of the email body by referring to the external tool. Some or all of the above-described processing in the email body creation unit can be performed, for example, using the generation AI, or without using the generation AI.

[0087] The email body creation unit can create a special version based on a specific event or campaign. A specific event or campaign may include, but is not limited to, the date and time of the event, its purpose, and its target audience. The email body creation unit can create, for example, a special version of the email body tailored to a specific event. The email body creation unit can also create a special version that covers topics related to the campaign. The email body creation unit can also adjust the content of the email body based on the theme of the event or campaign. For example, the email body creation unit can input information about a specific event or campaign into the generation AI and have the generation AI create a special version. This allows for more effective information provision by creating a special version tailored to a specific event or campaign. Some or all of the above-described processing in the email body creation unit can be performed, for example, using the generation AI, or without using the generation AI. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned topic extraction unit, newsletter creation unit, and email body creation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the topic extraction unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the newsletter creation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the email body creation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned topic extraction unit, newsletter creation unit, and email body creation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the topic extraction unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the newsletter creation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the email body creation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned topic extraction unit, newsletter creation unit, and email body creation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the topic extraction unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the newsletter creation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the email body creation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned topic extraction unit, newsletter creation unit, and email body creation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the topic extraction unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the newsletter creation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the email body creation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The topic extraction unit can also determine the priority of topics based on the user's past behavioral history. For example, it analyzes data on links the user has clicked and pages they have viewed in the past to prioritize topics that are likely to be of interest. It can also prioritize topics related to events the user has previously attended or products they have purchased. It can also extract related topics based on content that the user has previously rated highly. This makes it possible to provide more personalized information by taking the user's past behavioral history into consideration.

[0090] The newsletter creation unit can also estimate the user's emotions and adjust the content of the newsletter based on the estimated user's emotions. For example, if the user has positive emotions, success stories and positive news can be emphasized. If the user has negative emotions, information about encouragement and support can be provided. Furthermore, if the user has neutral emotions, balanced information can be provided. This makes it possible to provide information more effectively by adjusting the content of the newsletter according to the user's emotions.

[0091] The email body creation unit can also estimate the user's emotions and adjust the format of the email body based on the estimated user's emotions. For example, if the user is relaxed, a casual format can be used. If the user is in a hurry, a concise and to-the-point format can be used. Furthermore, if the user is excited, a visually stimulating format can be used. This allows for more effective communication by adjusting the format of the email body according to the user's emotions.

[0092] The topic extraction unit can also evaluate the importance of topics based on the opinions of external experts. For example, it can analyze blogs and articles written by industry experts to extract important topics. It can also extract related topics based on the content of interviews and lectures by experts. It can also analyze social media posts by experts to evaluate the importance of topics. This allows the provision of more reliable information by incorporating the opinions of external experts.

[0093] The newsletter creation unit can also estimate the user's emotions and adjust the timing of newsletter distribution based on the estimated user's emotions. For example, the newsletter can be distributed during times when the user is relaxed. It can also be distributed during times when the user is busy. Furthermore, a higher response rate can be expected by distributing the newsletter during times when the user is excited. This makes it possible to provide information more effectively by adjusting the distribution timing according to the user's emotions.

[0094] The topic extraction unit can also extract topics based on news and events in a specific region. For example, it can analyze local news sites and event calendars to extract related topics. It can also analyze local social media posts to extract important topics. It can also evaluate the importance of topics based on the opinions of local experts and influencers. This allows for more targeted information provision by providing information related to a specific region.

[0095] The newsletter creation unit can also estimate the user's emotions and adjust the length of the newsletter based on the estimated user's emotions. For example, if the user is relaxed, a longer newsletter containing detailed information can be provided. If the user is in a hurry, a shorter newsletter that is concise and to the point can be provided. Furthermore, if the user is excited, a newsletter with visually stimulating effects can be provided. In this way, by adjusting the length of the newsletter according to the user's emotions, more effective information provision can be achieved.

[0096] The topic extraction unit can also monitor the frequency of specific keywords in real time and extract topics. For example, it can analyze news sites and social media posts in real time to extract frequently occurring keywords. Also, if the frequency of a specific keyword increases sharply, it can prioritize the extraction of topics related to that keyword. Furthermore, it can evaluate the importance of topics based on the results of real-time monitoring. This makes it possible to provide the latest information quickly.

[0097] The newsletter creation unit can also estimate the user's emotions and adjust the font style of the newsletter based on the estimated user's emotions. For example, if the user is relaxed, an easy-to-read font style can be used. If the user is excited, a visually stimulating font style can be used. Furthermore, if the user is stressed, a simple and calm font style can be used. In this way, by adjusting the font style according to the user's emotions, more effective information provision can be achieved.

[0098] The topic extraction unit can also extract topics based on user behavior data during a specific time period. For example, it can analyze content that a user frequently accesses during a specific time period and extract related topics. It can also determine the priority of topics based on the user's activities during a specific time period. It can also analyze the user's behavior patterns during a specific time period and evaluate the importance of topics. This makes it possible to provide more personalized information by taking user behavior data into consideration.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The topic extraction unit analyzes recent press releases, interview articles, and internal email correspondence to extract topics. For example, it uses natural language processing technology or generative AI to extract important keywords and phrases. Step 2: The newsletter creation unit creates a newsletter, including visuals, based on the topics extracted by the topic extraction unit. For example, it selects appropriate images from an image database and automatically generates graphs and charts related to the topics. It is also possible to create a newsletter using generative AI. Step 3: The email body creation unit creates the email body for the newsletter created by the newsletter creation unit. For example, it generates appropriate sentences based on the topic based on pre-set templates and context. It is also possible to create the email body using generative AI.

[0101] 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.

[0102] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0103] 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.

[0104] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

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

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 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.

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

[0124] The 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.

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

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

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

[0128] Fig. 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.

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

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

[0131] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

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

[0133] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0135] The data processing system 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.

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

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 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.

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

[0140] The 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.

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

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS 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).

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

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] 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."

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] [Explanation of symbols]

[0173] 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 system comprises a topic extraction unit that analyzes the most recent press releases or interview articles and internal email exchanges to extract topics, a newsletter creation unit that creates a newsletter including visuals based on the topics extracted by the topic extraction unit, and an email body creation unit that creates an email body to accompany the distribution of the newsletter created by the newsletter creation unit.

2. 2. The system according to claim 1, wherein the topic extraction unit uses natural language processing technology to analyze the contents of press releases, interview articles, and internal emails, and extracts important keywords or phrases.

3. 10. The system of claim 1, wherein the newsletter creator selects images from an image database and automatically generates graphs and charts related to the topic.

4. The system according to claim 1 , wherein the email body creation unit creates a message according to a topic based on a preset template or context.

5. 2. The system according to claim 1, wherein the topic extraction unit estimates a user's emotion and determines the priority of topics to be extracted based on the estimated user's emotion.

6. The system according to claim 1, wherein the topic extraction unit improves the accuracy of extraction based on data of past press releases or news articles.

7. The system according to claim 1 , wherein the topic extractor extracts important topics based on trends in a particular industry or market.

8. The system of claim 1, wherein the topic extraction unit improves extraction accuracy based on feedback from different departments within the company.

Images