system

Abstract

The system according to this embodiment aims to efficiently extract and provide information tailored to each individual employee from a large amount of internal and external information. [Solution] The system according to the embodiment comprises a profile creation unit, an analysis unit, an extraction unit, a generation unit, and a distribution unit. The profile creation unit creates employee profiles. The analysis unit analyzes information based on the profiles created by the profile creation unit. The extraction unit extracts important information from the information analyzed by the analysis unit. The generation unit generates a newsletter based on the information extracted by the extraction unit. The distribution unit distributes the newsletter generated by the generation unit to employees.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to efficiently extract and provide information suitable for each employee from a large amount of internal and external information.

[0005] The system according to the embodiment aims to efficiently extract and provide information suitable for each employee from a large amount of internal and external information.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a profile creation unit, an analysis unit, an extraction unit, a generation unit, and a distribution unit. The profile creation unit creates employee profiles. The analysis unit analyzes information based on the profiles created by the profile creation unit. The extraction unit extracts important information from the information analyzed by the analysis unit. The generation unit generates a newsletter based on the information extracted by the extraction unit. The distribution unit distributes the newsletter generated by the generation unit to employees. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently extract and provide information tailored to each individual employee from a large amount of internal and external information. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An information provision system according to an embodiment of the present invention is a system that uses LLM to automatically extract and generate information that each employee can utilize in their work from a large amount of internal and external information, and provides a personalized newsletter every morning. The information provision system creates a profile for providing personalized information based on the employee's work content and areas of interest. Next, the LLM analyzes a large amount of internal and external information and extracts the most suitable information for each employee. This information is extracted from various formats such as text, audio, and video. The extracted information is provided to employees every morning as a personalized newsletter. The newsletter includes information directly related to the employee's work and information that helps to improve work efficiency. For example, it includes information on the latest industry trends, the actions of competitors, and technological innovations. With this system, employees can efficiently obtain the information they need, and it is expected that work efficiency and productivity will improve. In addition, by extracting information from audio and video, employees can utilize information in various formats. As a result, the information provision system can provide the most suitable information for each employee and realize work efficiency and productivity improvements.

[0029] The information provision system according to the embodiment comprises a profile creation unit, an analysis unit, an extraction unit, a generation unit, and a distribution unit. The profile creation unit creates employee profiles. The profile creation unit can create profiles based, for example, on an employee's work content and areas of interest. The profile creation unit collects information such as an employee's skill set, work history, and areas of interest, and generates a profile. The analysis unit analyzes information based on the profile created by the profile creation unit. The analysis unit can analyze information in various formats, such as text, audio, and video. The analysis unit uses LLM to analyze a large amount of internal and external information and extract information that is most relevant to the employee. The extraction unit extracts important information from the information analyzed by the analysis unit. The extraction unit can extract information that is most relevant to each individual employee, for example. The extraction unit uses LLM to extract highly relevant information from the analyzed information. The generation unit generates a newsletter based on the information extracted by the extraction unit. The generation unit can generate a personalized newsletter, for example. The generation unit uses LLM to create a newsletter based on the extracted information. The distribution unit distributes the newsletters generated by the generation unit to employees. For example, the distribution unit can distribute newsletters to employees every morning. The distribution unit uses AI to distribute the generated newsletters to employees. As a result, the information provision system according to this embodiment can provide each employee with the most relevant information, thereby improving work efficiency and productivity.

[0030] The Profile Creation Department creates employee profiles. For example, it can create profiles based on an employee's job responsibilities and areas of interest. Specifically, the Profile Creation Department collects information such as an employee's skill set, work history, and areas of interest to generate a profile. An employee's skill set includes technical skills, soft skills, and past project experience. Work history records projects, roles, and achievements the employee has previously handled. Areas of interest include technologies, industries, and trends the employee is interested in. This information is collected based on self-reported data entered by employees and data automatically retrieved from the company's HR system. The Profile Creation Department integrates the collected data to generate a detailed profile for each employee. The generated profile serves as foundational information for addressing individual needs and goals based on the employee's skills and areas of interest. Furthermore, the Profile Creation Department can periodically update profiles to accommodate changes in an employee's skills and areas of interest. For example, if an employee acquires new skills or their areas of interest change, the profile is automatically updated. This allows the profile creation department to always provide profiles based on the latest information, supporting employee growth and career development.

[0031] The analysis unit analyzes information based on profiles created by the profile creation unit. The analysis unit can analyze information in various formats, such as text, audio, and video. Specifically, it uses a Large-Scale Language Model (LLM) to analyze large amounts of internal and external information and extract the most relevant information for each employee. The LLM utilizes natural language processing technology to understand the meaning of text data and identify highly relevant information. For example, based on employee profiles, it analyzes the latest research papers and industry news related to their work and extracts important information. For audio data analysis, it uses speech recognition technology to transcribe meeting recordings and interviews, extracting important statements and keywords. For video data analysis, it uses image recognition technology to analyze video conference recordings and presentations, identifying important slides and charts. The analysis unit integrates these diverse data sources to generate foundational data for providing the most useful information for employees. Furthermore, the analysis unit can analyze historical data and trends to make future predictions and risk assessments. For example, based on past project data, it can identify success and risk factors in specific tasks and provide advice for future projects. This allows the analysis department to provide crucial information to improve employee work efficiency and enhance overall organizational productivity.

[0032] The extraction unit extracts important information from the information analyzed by the analysis unit. For example, the extraction unit can extract information best suited to each individual employee. Specifically, the extraction unit uses LLM to extract highly relevant information from the analyzed data. Based on employee profiles, LLM identifies information that addresses individual needs and interests. For example, an employee interested in a particular technology will receive the latest research papers and industry news related to that technology. Similarly, an employee working on a specific project will receive success stories and best practices related to that project. The extraction unit leverages the natural language processing capabilities of LLM to quickly identify the most relevant information from a vast amount of data. Furthermore, the extraction unit evaluates the importance and reliability of the information to ensure the quality of the information provided to employees. For example, it prioritizes information from reliable sources and filters out less reliable information. The extraction unit can also continuously improve its extraction algorithm based on employee feedback, enhancing the accuracy and relevance of the information provided. This allows the extraction unit to provide each employee with the most relevant information, supporting improved work efficiency and productivity.

[0033] The generation unit generates newsletters based on the information extracted by the extraction unit. The generation unit can, for example, generate personalized newsletters. Specifically, the generation unit uses LLM (Language Language Generation) to create newsletters based on the extracted information. LLM utilizes natural language generation technology to organize the extracted information clearly and generate newsletters in an easy-to-read format for employees. The newsletters include the latest information related to employees' areas of interest and work, important announcements, and industry trends. The generation unit customizes the content of the newsletters for each employee, providing information that meets their individual needs. For example, it provides the latest technology trends and research findings to employees in the technology department, and market trends and competitor information to employees in the sales department. Furthermore, the generation unit automatically generates the design and layout of the newsletters, providing information in a visually appealing format. In addition, the generation unit can adjust the frequency and timing of newsletter distribution, providing information at the optimal time to match employees' work schedules. This allows the generation unit to effectively provide employees with useful information, supporting improved work efficiency and productivity.

[0034] The distribution department distributes newsletters generated by the generation department to employees. For example, the distribution department can distribute newsletters to employees every morning. Specifically, the distribution department uses AI to distribute the generated newsletters to employees. The AI ​​calculates the optimal distribution timing based on the employee's schedule and work content, and distributes the newsletters accordingly. For example, it can distribute newsletters before employees arrive at work so that they can check the latest information before starting work. The distribution department also utilizes multiple distribution channels to ensure that information reaches employees reliably. For example, it distributes newsletters via email, the company's messaging system, and mobile apps. Furthermore, the distribution department can collect feedback after distribution and continuously improve the distribution algorithm. For example, it analyzes employee open rates and click-through rates to optimize the content and timing of distribution. The distribution department also improves the content and format of newsletters based on employee feedback, enabling more effective information delivery. In this way, the distribution department can provide information to employees quickly and reliably, supporting improved work efficiency and productivity.

[0035] The profile creation unit can create profiles based on employees' job duties and areas of interest. For example, the profile creation unit creates profiles based on employees' job duties and areas of interest. The profile creation unit collects information such as employees' skill sets, work history, and areas of interest to generate profiles. This allows for the provision of more personalized information by creating profiles based on employees' job duties and areas of interest.

[0036] The analysis unit can analyze information in various formats, such as text, audio, and video. For example, the analysis unit analyzes information in various formats, such as text, audio, and video. Using LLM, the analysis unit analyzes large amounts of internal and external information and extracts the most relevant information for employees. This broadens the range of information provided to employees by analyzing diverse formats.

[0037] The extraction unit can extract information best suited to each employee from the information analyzed by the analysis unit. For example, the extraction unit extracts information best suited to each employee from the information analyzed by the analysis unit. The extraction unit uses LLM to extract highly relevant information from the analyzed information. This allows for the efficient provision of information useful for work by extracting information best suited to each employee.

[0038] The generation unit can generate personalized newsletters based on the extracted information. For example, the generation unit generates personalized newsletters based on the extracted information. The generation unit uses LLM to create newsletters based on the extracted information. This allows for the generation of personalized newsletters, providing employees with valuable information.

[0039] The distribution department can send the generated newsletter to employees every morning. For example, the distribution department sends the generated newsletter to employees every morning. The distribution department uses AI to send the generated newsletter to employees. This ensures that employees receive the latest information in a timely manner by sending the newsletter every morning.

[0040] The profiling department can analyze an employee's past work history to improve the accuracy of their profile. For example, it can analyze data from projects an employee has been involved in in the past and incorporate it into the profile. It can also evaluate an employee's past work performance to improve the accuracy of their profile. Furthermore, the profiling department can add skills and knowledge useful for future work based on an employee's past work history to their profile. This allows for improved profile accuracy and the provision of more relevant information by analyzing past work history.

[0041] The profile creation department can customize employee profiles by considering their skill sets and career goals. For example, it can analyze an employee's skill set and reflect it in the profile. It can also customize the profile by considering the employee's career goals. Furthermore, based on the employee's skill set and career goals, the profile creation department can add information to the profile that will be useful for future work. This allows for the provision of more personalized information by considering the employee's skill set and career goals.

[0042] The profile creation unit can optimize employee profiles by considering their geographical location during the profile creation process. For example, it can add region-specific information to the profile based on the employee's work location. It can also add information about business trip destinations to the profile based on the employee's business trip destinations. Furthermore, it can consider the distance between the employee's home and work location and add information useful for commuting to the profile. In this way, by considering geographical location information, it can provide region-specific information.

[0043] The profile creation department can analyze employees' social media activity and reflect it in their profiles during the profile creation process. For example, it can analyze employees' areas of interest on social media and reflect them in their profiles. It can also analyze employees' social media activity history and reflect it in their profiles. Furthermore, it can analyze information about employees' followers and friends on social media and reflect it in their profiles. This allows the department to provide information based on employees' areas of interest by analyzing their social media activity.

[0044] The analysis unit can evaluate the reliability of information during analysis and prioritize the analysis of highly reliable information. For example, the analysis unit can evaluate the reliability of information sources and prioritize the analysis of highly reliable information. Furthermore, the analysis unit can evaluate the content of information and prioritize the analysis of highly reliable information. In addition, the analysis unit can evaluate the reliability of information providers and prioritize the analysis of highly reliable information. By prioritizing the analysis of highly reliable information, more accurate information can be provided.

[0045] The analysis unit can apply different analysis methods depending on the category of information during analysis. For example, it can apply natural language processing to text information and perform analysis. It can also apply speech recognition technology to audio information and perform analysis. Furthermore, it can apply image recognition technology to video information and perform analysis. By applying analysis methods appropriate to the category of information, the accuracy of the analysis is improved.

[0046] The analysis unit can determine the priority of analysis based on when the information was submitted. For example, the analysis unit will prioritize the analysis of the most recent information. It can also postpone the analysis of older information. Furthermore, it can prioritize the analysis of information that has been submitted recently. By determining the priority of analysis based on when the information was submitted, the latest information can be provided preferentially.

[0047] The analysis unit can adjust the order of analysis based on the relevance of the information during the analysis process. For example, the analysis unit can prioritize the analysis of information directly related to the business. It can also postpone the analysis of less relevant information. Furthermore, the analysis unit can prioritize the analysis of highly relevant information. By adjusting the order of analysis based on the relevance of the information, it can provide more relevant information.

[0048] The extraction unit can improve the accuracy of extraction by considering the interrelationships of information during the extraction process. For example, the extraction unit can analyze the interrelationships of information and extract highly relevant information. Furthermore, the extraction unit can prioritize the extraction of important information by considering the interrelationships of information. In addition, the extraction unit can evaluate the interrelationships of information and extract highly accurate information. This allows for the extraction of more accurate information by considering the interrelationships of information.

[0049] The extraction unit can perform extraction while considering the attribute information of the information submitter. For example, the extraction unit can consider the submitter's field of expertise and extract highly relevant information. Furthermore, the extraction unit can evaluate the submitter's reliability and extract highly reliable information. In addition, the extraction unit can consider the submitter's past performance and extract important information. This allows for the extraction of more reliable information by considering the submitter's attribute information.

[0050] The extraction unit can perform extraction while considering the geographical distribution of information. For example, the extraction unit can prioritize extracting information that is geographically close. It can also extract information that is highly geographically relevant. Furthermore, the extraction unit can extract important information while considering geographical distribution. This allows for the provision of region-specific information by considering geographical distribution.

[0051] The extraction unit can improve the accuracy of its extraction by referring to relevant literature during the extraction process. For example, the extraction unit can refer to relevant literature to extract highly accurate information. Furthermore, the extraction unit can analyze relevant literature and extract important information. In addition, the extraction unit can evaluate relevant literature and extract reliable information. This allows for the extraction of more accurate information by referring to relevant literature.

[0052] The generation unit can adjust the level of detail in a newsletter based on the importance of the information during the newsletter generation process. For example, it can increase the level of detail by describing important information in detail. It can also adjust the level of detail by describing less important information concisely. Furthermore, the generation unit can customize the content of the newsletter according to the importance of the information. This allows for the provision of more relevant information by adjusting the level of detail in the newsletter based on the importance of the information.

[0053] The generation unit can apply different generation algorithms depending on the category of information when generating newsletters. For example, it can apply a specific generation algorithm to information about industry trends. It can also apply a different generation algorithm to information about technological innovations. Furthermore, it can apply yet another generation algorithm to information about the actions of competitors. By applying generation algorithms according to the category of information, the accuracy of the newsletter is improved.

[0054] The generation unit can prioritize newsletters based on when the information was submitted. For example, it can prioritize including the most recent information in the newsletter. It can also postpone older information. Furthermore, it can prioritize including information that is about to be submitted. This allows the newsletter to provide the most up-to-date information by prioritizing newsletters based on when the information was submitted.

[0055] The generation unit can adjust the order of information in a newsletter based on its relevance during the newsletter generation process. For example, it can prioritize placing information directly related to business operations at the beginning of the newsletter. It can also postpone less relevant information. Furthermore, it can prioritize including highly relevant information in the newsletter. This allows for the delivery of more relevant information by adjusting the newsletter's order based on its relevance.

[0056] The distribution department can select the optimal distribution method by referring to employees' past newsletter viewing history at the time of distribution. For example, the distribution department can distribute newsletters in the format that employees have previously preferred to view. The distribution department can also select the optimal distribution time based on employees' past viewing history. Furthermore, the distribution department can analyze employees' past viewing history to select the optimal distribution method. In this way, by referring to past viewing history, the distribution department can select the most suitable distribution method for each employee.

[0057] The distribution department can select the optimal distribution method by considering the employee's device information at the time of distribution. For example, if an employee is using a smartphone, the distribution department will distribute the newsletter in a format optimized for smartphones. Furthermore, if an employee is using a tablet, the distribution department can distribute the newsletter in a format optimized for tablets. In addition, if an employee is using a desktop, the distribution department can distribute the newsletter in a format optimized for desktops. This allows the distribution department to deliver newsletters in the most suitable format for each employee by considering their device information.

[0058] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0059] The profiling unit can collect employee health data and incorporate it into their profiles. For example, it can collect data from employees' fitness trackers and smartwatches to understand their health status. The profiling unit can also provide work-related health information based on the employee's health status. Furthermore, if an employee's health is deteriorating, it can prioritize providing information that will help improve their health. This enables the provision of information that takes employee health status into consideration, supporting employee health management.

[0060] The analytics department can analyze employees' past newsletter viewing history to gain a more accurate understanding of their interests. For example, it can extract frequently viewed topics and keywords and incorporate them into their profiles. The analytics department can also analyze the content of newsletters employees have previously viewed to track changes in their interests. Furthermore, it can customize the content of future newsletters based on employees' viewing history. This enables the delivery of more personalized information based on employees' interests.

[0061] The extraction unit can extract information while taking into account the employee's work schedule. For example, if an employee is busy with meetings or business trips, it will prioritize extracting only the most important information. The extraction unit can also provide work-related information in a timely manner based on the employee's work schedule. Furthermore, if an employee's work schedule changes, the content of the extracted information can be adjusted in real time. This enables flexible information provision tailored to the employee's work schedule.

[0062] The generation unit can adjust the format of newsletters to take into account employees' learning styles when generating them. For example, employees who prefer visual learning can be provided with newsletters that make extensive use of graphs and charts. Similarly, employees who prefer auditory learning can be provided with newsletters that include audio content. Furthermore, employees who prefer practical learning can be provided with newsletters that include specific examples and case studies. This enables effective information delivery tailored to each employee's learning style.

[0063] The distribution department can monitor employees' device usage in real time and select the optimal distribution method. For example, if an employee is using a smartphone, the newsletter can be delivered in a format optimized for smartphones. Similarly, if an employee is using a tablet, the newsletter can be delivered in a format optimized for tablets. Furthermore, if an employee is using a desktop computer, the newsletter can be delivered in a format optimized for desktops. This allows for the delivery of newsletters in the most appropriate format based on device usage.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The Profile Creation Department creates employee profiles. The Profile Creation Department collects information such as the employee's job duties, areas of interest, skill set, and work history, and generates the profile. Step 2: The analysis unit analyzes the information based on the profile created by the profile creation unit. The analysis unit analyzes information in various formats such as text, audio, and video, and uses LLM to analyze a large amount of internal and external information. Step 3: The extraction unit extracts important information from the information analyzed by the analysis unit. The extraction unit extracts the most relevant information for each employee and extracts highly relevant information from the information analyzed using LLM. Step 4: The generation unit generates a newsletter based on the information extracted by the extraction unit. The generation unit generates a personalized newsletter and creates a newsletter based on the information extracted using LLM. Step 5: The distribution department distributes the newsletters generated by the generation department to employees. The distribution department distributes newsletters to employees every morning, including newsletters generated using AI.

[0066] (Example of form 2) An information provision system according to an embodiment of the present invention is a system that uses LLM to automatically extract and generate information that each employee can utilize in their work from a large amount of internal and external information, and provides a personalized newsletter every morning. The information provision system creates a profile for providing personalized information based on the employee's work content and areas of interest. Next, the LLM analyzes a large amount of internal and external information and extracts the most suitable information for each employee. This information is extracted from various formats such as text, audio, and video. The extracted information is provided to employees every morning as a personalized newsletter. The newsletter includes information directly related to the employee's work and information that helps to improve work efficiency. For example, it includes information on the latest industry trends, the actions of competitors, and technological innovations. With this system, employees can efficiently obtain the information they need, and it is expected that work efficiency and productivity will improve. In addition, by extracting information from audio and video, employees can utilize information in various formats. As a result, the information provision system can provide the most suitable information for each employee and realize work efficiency and productivity improvements.

[0067] The information provision system according to the embodiment comprises a profile creation unit, an analysis unit, an extraction unit, a generation unit, and a distribution unit. The profile creation unit creates employee profiles. The profile creation unit can create profiles based, for example, on an employee's work content and areas of interest. The profile creation unit collects information such as an employee's skill set, work history, and areas of interest, and generates a profile. The analysis unit analyzes information based on the profile created by the profile creation unit. The analysis unit can analyze information in various formats, such as text, audio, and video. The analysis unit uses LLM to analyze a large amount of internal and external information and extract information that is most relevant to the employee. The extraction unit extracts important information from the information analyzed by the analysis unit. The extraction unit can extract information that is most relevant to each individual employee, for example. The extraction unit uses LLM to extract highly relevant information from the analyzed information. The generation unit generates a newsletter based on the information extracted by the extraction unit. The generation unit can generate a personalized newsletter, for example. The generation unit uses LLM to create a newsletter based on the extracted information. The distribution unit distributes the newsletters generated by the generation unit to employees. For example, the distribution unit can distribute newsletters to employees every morning. The distribution unit uses AI to distribute the generated newsletters to employees. As a result, the information provision system according to this embodiment can provide each employee with the most relevant information, thereby improving work efficiency and productivity.

[0068] The Profile Creation Department creates employee profiles. For example, it can create profiles based on an employee's job responsibilities and areas of interest. Specifically, the Profile Creation Department collects information such as an employee's skill set, work history, and areas of interest to generate a profile. An employee's skill set includes technical skills, soft skills, and past project experience. Work history records projects, roles, and achievements the employee has previously handled. Areas of interest include technologies, industries, and trends the employee is interested in. This information is collected based on self-reported data entered by employees and data automatically retrieved from the company's HR system. The Profile Creation Department integrates the collected data to generate a detailed profile for each employee. The generated profile serves as foundational information for addressing individual needs and goals based on the employee's skills and areas of interest. Furthermore, the Profile Creation Department can periodically update profiles to accommodate changes in an employee's skills and areas of interest. For example, if an employee acquires new skills or their areas of interest change, the profile is automatically updated. This allows the profile creation department to always provide profiles based on the latest information, supporting employee growth and career development.

[0069] The analysis unit analyzes information based on profiles created by the profile creation unit. The analysis unit can analyze information in various formats, such as text, audio, and video. Specifically, it uses a Large-Scale Language Model (LLM) to analyze large amounts of internal and external information and extract the most relevant information for each employee. The LLM utilizes natural language processing technology to understand the meaning of text data and identify highly relevant information. For example, based on employee profiles, it analyzes the latest research papers and industry news related to their work and extracts important information. For audio data analysis, it uses speech recognition technology to transcribe meeting recordings and interviews, extracting important statements and keywords. For video data analysis, it uses image recognition technology to analyze video conference recordings and presentations, identifying important slides and charts. The analysis unit integrates these diverse data sources to generate foundational data for providing the most useful information for employees. Furthermore, the analysis unit can analyze historical data and trends to make future predictions and risk assessments. For example, based on past project data, it can identify success and risk factors in specific tasks and provide advice for future projects. This allows the analysis department to provide crucial information to improve employee work efficiency and enhance overall organizational productivity.

[0070] The extraction unit extracts important information from the information analyzed by the analysis unit. For example, the extraction unit can extract information best suited to each individual employee. Specifically, the extraction unit uses LLM to extract highly relevant information from the analyzed data. Based on employee profiles, LLM identifies information that addresses individual needs and interests. For example, an employee interested in a particular technology will receive the latest research papers and industry news related to that technology. Similarly, an employee working on a specific project will receive success stories and best practices related to that project. The extraction unit leverages the natural language processing capabilities of LLM to quickly identify the most relevant information from a vast amount of data. Furthermore, the extraction unit evaluates the importance and reliability of the information to ensure the quality of the information provided to employees. For example, it prioritizes information from reliable sources and filters out less reliable information. The extraction unit can also continuously improve its extraction algorithm based on employee feedback, enhancing the accuracy and relevance of the information provided. This allows the extraction unit to provide each employee with the most relevant information, supporting improved work efficiency and productivity.

[0071] The generation unit generates newsletters based on the information extracted by the extraction unit. The generation unit can, for example, generate personalized newsletters. Specifically, the generation unit uses LLM (Language Language Generation) to create newsletters based on the extracted information. LLM utilizes natural language generation technology to organize the extracted information clearly and generate newsletters in an easy-to-read format for employees. The newsletters include the latest information related to employees' areas of interest and work, important announcements, and industry trends. The generation unit customizes the content of the newsletters for each employee, providing information that meets their individual needs. For example, it provides the latest technology trends and research findings to employees in the technology department, and market trends and competitor information to employees in the sales department. Furthermore, the generation unit automatically generates the design and layout of the newsletters, providing information in a visually appealing format. In addition, the generation unit can adjust the frequency and timing of newsletter distribution, providing information at the optimal time to match employees' work schedules. This allows the generation unit to effectively provide employees with useful information, supporting improved work efficiency and productivity.

[0072] The distribution department distributes newsletters generated by the generation department to employees. For example, the distribution department can distribute newsletters to employees every morning. Specifically, the distribution department uses AI to distribute the generated newsletters to employees. The AI ​​calculates the optimal distribution timing based on the employee's schedule and work content, and distributes the newsletters accordingly. For example, it can distribute newsletters before employees arrive at work so that they can check the latest information before starting work. The distribution department also utilizes multiple distribution channels to ensure that information reaches employees reliably. For example, it distributes newsletters via email, the company's messaging system, and mobile apps. Furthermore, the distribution department can collect feedback after distribution and continuously improve the distribution algorithm. For example, it analyzes employee open rates and click-through rates to optimize the content and timing of distribution. The distribution department also improves the content and format of newsletters based on employee feedback, enabling more effective information delivery. In this way, the distribution department can provide information to employees quickly and reliably, supporting improved work efficiency and productivity.

[0073] The profile creation unit can create profiles based on employees' job duties and areas of interest. For example, the profile creation unit creates profiles based on employees' job duties and areas of interest. The profile creation unit collects information such as employees' skill sets, work history, and areas of interest to generate profiles. This allows for the provision of more personalized information by creating profiles based on employees' job duties and areas of interest.

[0074] The analysis unit can analyze information in various formats, such as text, audio, and video. For example, the analysis unit analyzes information in various formats, such as text, audio, and video. Using LLM, the analysis unit analyzes large amounts of internal and external information and extracts the most relevant information for employees. This broadens the range of information provided to employees by analyzing diverse formats.

[0075] The extraction unit can extract information best suited to each employee from the information analyzed by the analysis unit. For example, the extraction unit extracts information best suited to each employee from the information analyzed by the analysis unit. The extraction unit uses LLM to extract highly relevant information from the analyzed information. This allows for the efficient provision of information useful for work by extracting information best suited to each employee.

[0076] The generation unit can generate personalized newsletters based on the extracted information. For example, the generation unit generates personalized newsletters based on the extracted information. The generation unit uses LLM to create newsletters based on the extracted information. This allows for the generation of personalized newsletters, providing employees with valuable information.

[0077] The distribution department can send the generated newsletter to employees every morning. For example, the distribution department sends the generated newsletter to employees every morning. The distribution department uses AI to send the generated newsletter to employees. This ensures that employees receive the latest information in a timely manner by sending the newsletter every morning.

[0078] The profiling unit can estimate an employee's emotions and adjust the frequency of profile updates based on the estimated emotions. For example, if an employee is stressed, the profiling unit can reduce the frequency of profile updates to alleviate their burden. Conversely, if an employee is relaxed, the profiling unit can increase the frequency of profile updates to provide the most up-to-date information. Furthermore, if an employee is busy, the profiling unit can adjust the frequency of profile updates to provide only essential information. This allows for reduced burden on employees and the provision of optimal information by adjusting the frequency of profile updates according to their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0079] The profiling department can analyze an employee's past work history to improve the accuracy of their profile. For example, it can analyze data from projects an employee has been involved in in the past and incorporate it into the profile. It can also evaluate an employee's past work performance to improve the accuracy of their profile. Furthermore, the profiling department can add skills and knowledge useful for future work based on an employee's past work history to their profile. This allows for improved profile accuracy and the provision of more relevant information by analyzing past work history.

[0080] The profile creation department can customize employee profiles by considering their skill sets and career goals. For example, it can analyze an employee's skill set and reflect it in the profile. It can also customize the profile by considering the employee's career goals. Furthermore, based on the employee's skill set and career goals, the profile creation department can add information to the profile that will be useful for future work. This allows for the provision of more personalized information by considering the employee's skill set and career goals.

[0081] The profiling unit can estimate an employee's emotions and determine profile priorities based on those emotions. For example, if an employee is stressed, the profiling unit will prioritize providing information that helps them relax. If an employee is relaxed, the profiling unit can also prioritize providing information that is helpful for their work. Furthermore, if an employee is busy, the profiling unit can prioritize providing only important information. This allows for the provision of more appropriate information by determining profile priorities according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0082] The profile creation unit can optimize employee profiles by considering their geographical location during the profile creation process. For example, it can add region-specific information to the profile based on the employee's work location. It can also add information about business trip destinations to the profile based on the employee's business trip destinations. Furthermore, it can consider the distance between the employee's home and work location and add information useful for commuting to the profile. In this way, by considering geographical location information, it can provide region-specific information.

[0083] The profile creation department can analyze employees' social media activity and reflect it in their profiles during the profile creation process. For example, it can analyze employees' areas of interest on social media and reflect them in their profiles. It can also analyze employees' social media activity history and reflect it in their profiles. Furthermore, it can analyze information about employees' followers and friends on social media and reflect it in their profiles. This allows the department to provide information based on employees' areas of interest by analyzing their social media activity.

[0084] The analysis unit can estimate employees' emotions and adjust the analysis algorithm based on the estimated emotions. For example, if an employee is stressed, the analysis unit can simplify the analysis algorithm to reduce its workload. Conversely, if an employee is relaxed, the analysis unit can perform a more detailed analysis to improve accuracy. Furthermore, if an employee is busy, the analysis unit can prioritize analyzing only the most important information. This allows for the provision of more relevant information by adjusting the analysis algorithm according to the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0085] The analysis unit can evaluate the reliability of information during analysis and prioritize the analysis of highly reliable information. For example, the analysis unit can evaluate the reliability of information sources and prioritize the analysis of highly reliable information. Furthermore, the analysis unit can evaluate the content of information and prioritize the analysis of highly reliable information. In addition, the analysis unit can evaluate the reliability of information providers and prioritize the analysis of highly reliable information. By prioritizing the analysis of highly reliable information, more accurate information can be provided.

[0086] The analysis unit can apply different analysis methods depending on the category of information during analysis. For example, it can apply natural language processing to text information and perform analysis. It can also apply speech recognition technology to audio information and perform analysis. Furthermore, it can apply image recognition technology to video information and perform analysis. By applying analysis methods appropriate to the category of information, the accuracy of the analysis is improved.

[0087] The analysis unit can estimate employees' emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if an employee is stressed, the analysis unit can provide a simple and highly visible display method. If an employee is relaxed, the analysis unit can also provide a display method that includes detailed information. Furthermore, if an employee is busy, the analysis unit can provide a concise display method. In this way, by adjusting the display method of the analysis results according to the employee's emotions, more visually appealing information can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0088] The analysis unit can determine the priority of analysis based on when the information was submitted. For example, the analysis unit will prioritize the analysis of the most recent information. It can also postpone the analysis of older information. Furthermore, it can prioritize the analysis of information that has been submitted recently. By determining the priority of analysis based on when the information was submitted, the latest information can be provided preferentially.

[0089] The analysis unit can adjust the order of analysis based on the relevance of the information during the analysis process. For example, the analysis unit can prioritize the analysis of information directly related to the business. It can also postpone the analysis of less relevant information. Furthermore, the analysis unit can prioritize the analysis of highly relevant information. By adjusting the order of analysis based on the relevance of the information, it can provide more relevant information.

[0090] The extraction unit can estimate an employee's emotions and determine the priority of information to extract based on the estimated emotions. For example, if an employee is stressed, the extraction unit will prioritize extracting information that promotes relaxation. If an employee is relaxed, the extraction unit can also prioritize extracting information that is useful for their work. Furthermore, if an employee is busy, the extraction unit can prioritize extracting only important information. This allows for the provision of more appropriate information by prioritizing the information extracted according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0091] The extraction unit can improve the accuracy of extraction by considering the interrelationships of information during the extraction process. For example, the extraction unit can analyze the interrelationships of information and extract highly relevant information. Furthermore, the extraction unit can prioritize the extraction of important information by considering the interrelationships of information. In addition, the extraction unit can evaluate the interrelationships of information and extract highly accurate information. This allows for the extraction of more accurate information by considering the interrelationships of information.

[0092] The extraction unit can perform extraction while considering the attribute information of the information submitter. For example, the extraction unit can consider the submitter's field of expertise and extract highly relevant information. Furthermore, the extraction unit can evaluate the submitter's reliability and extract highly reliable information. In addition, the extraction unit can consider the submitter's past performance and extract important information. This allows for the extraction of more reliable information by considering the submitter's attribute information.

[0093] The extraction unit can estimate an employee's emotions and adjust how the extracted information is displayed based on the estimated emotions. For example, if an employee is stressed, the extraction unit can provide a simple and highly visible display. If an employee is relaxed, the extraction unit can also provide a display that includes detailed information. Furthermore, if an employee is busy, the extraction unit can provide a concise display. This allows for more visually appealing information by adjusting the display method according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0094] The extraction unit can perform extraction while considering the geographical distribution of information. For example, the extraction unit can prioritize extracting information that is geographically close. It can also extract information that is highly geographically relevant. Furthermore, the extraction unit can extract important information while considering geographical distribution. This allows for the provision of region-specific information by considering geographical distribution.

[0095] The extraction unit can improve the accuracy of its extraction by referring to relevant literature during the extraction process. For example, the extraction unit can refer to relevant literature to extract highly accurate information. Furthermore, the extraction unit can analyze relevant literature and extract important information. In addition, the extraction unit can evaluate relevant literature and extract reliable information. This allows for the extraction of more accurate information by referring to relevant literature.

[0096] The generation unit can estimate employees' emotions and adjust the newsletter's presentation based on those emotions. For example, if an employee is stressed, the generation unit can provide a simple and visually appealing presentation. If an employee is relaxed, it can provide a more detailed presentation. Furthermore, if an employee is busy, it can provide a concise presentation. By adjusting the newsletter's presentation according to employees' emotions, more visually appealing information can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0097] The generation unit can adjust the level of detail in a newsletter based on the importance of the information during the newsletter generation process. For example, it can increase the level of detail by describing important information in detail. It can also adjust the level of detail by describing less important information concisely. Furthermore, the generation unit can customize the content of the newsletter according to the importance of the information. This allows for the provision of more relevant information by adjusting the level of detail in the newsletter based on the importance of the information.

[0098] The generation unit can apply different generation algorithms depending on the category of information when generating newsletters. For example, it can apply a specific generation algorithm to information about industry trends. It can also apply a different generation algorithm to information about technological innovations. Furthermore, it can apply yet another generation algorithm to information about the actions of competitors. By applying generation algorithms according to the category of information, the accuracy of the newsletter is improved.

[0099] The generation unit can estimate an employee's emotions and adjust the length of the newsletter based on that estimation. For example, if an employee is stressed, the generation unit can provide a short, to-the-point newsletter. If an employee is relaxed, the generation unit can provide a longer newsletter with more detailed information. Furthermore, if an employee is busy, the generation unit can provide a short newsletter containing only the essential information. This allows for the provision of more relevant information by adjusting the newsletter length according to the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0100] The generation unit can prioritize newsletters based on when the information was submitted. For example, it can prioritize including the most recent information in the newsletter. It can also postpone older information. Furthermore, it can prioritize including information that is about to be submitted. This allows the newsletter to provide the most up-to-date information by prioritizing newsletters based on when the information was submitted.

[0101] The generation unit can adjust the order of information in a newsletter based on its relevance during the newsletter generation process. For example, it can prioritize placing information directly related to business operations at the beginning of the newsletter. It can also postpone less relevant information. Furthermore, it can prioritize including highly relevant information in the newsletter. This allows for the delivery of more relevant information by adjusting the newsletter's order based on its relevance.

[0102] The distribution department can estimate employees' emotions and adjust the timing of newsletter delivery based on those estimated emotions. For example, if an employee is feeling stressed, the department can deliver the newsletter during a time when they can relax. Alternatively, if an employee is relaxed, the department can deliver the newsletter before the start of work. Furthermore, if an employee is busy, the department can deliver the newsletter after work. This allows for timely information delivery by adjusting the newsletter delivery timing according to employees' emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0103] The distribution department can select the optimal distribution method by referring to employees' past newsletter viewing history at the time of distribution. For example, the distribution department can distribute newsletters in the format that employees have previously preferred to view. The distribution department can also select the optimal distribution time based on employees' past viewing history. Furthermore, the distribution department can analyze employees' past viewing history to select the optimal distribution method. In this way, by referring to past viewing history, the distribution department can select the most suitable distribution method for each employee.

[0104] The distribution department can estimate employees' emotions and adjust the frequency of newsletter delivery based on those estimated emotions. For example, if an employee is stressed, the distribution department can reduce the delivery frequency to alleviate their burden. Conversely, if an employee is relaxed, the distribution department can increase the delivery frequency to provide the latest information. Furthermore, if an employee is busy, the distribution department can adjust the delivery frequency to provide only essential information. This allows for the delivery of more relevant information by adjusting the newsletter delivery frequency according to employees' emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0105] The distribution department can select the optimal distribution method by considering the employee's device information at the time of distribution. For example, if an employee is using a smartphone, the distribution department will distribute the newsletter in a format optimized for smartphones. Furthermore, if an employee is using a tablet, the distribution department can distribute the newsletter in a format optimized for tablets. In addition, if an employee is using a desktop, the distribution department can distribute the newsletter in a format optimized for desktops. This allows the distribution department to deliver newsletters in the most suitable format for each employee by considering their device information.

[0106] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0107] The profiling unit can collect employee health data and incorporate it into their profiles. For example, it can collect data from employees' fitness trackers and smartwatches to understand their health status. The profiling unit can also provide work-related health information based on the employee's health status. Furthermore, if an employee's health is deteriorating, it can prioritize providing information that will help improve their health. This enables the provision of information that takes employee health status into consideration, supporting employee health management.

[0108] The analytics department can analyze employees' past newsletter viewing history to gain a more accurate understanding of their interests. For example, it can extract frequently viewed topics and keywords and incorporate them into their profiles. The analytics department can also analyze the content of newsletters employees have previously viewed to track changes in their interests. Furthermore, it can customize the content of future newsletters based on employees' viewing history. This enables the delivery of more personalized information based on employees' interests.

[0109] The extraction unit can extract information while taking into account the employee's work schedule. For example, if an employee is busy with meetings or business trips, it will prioritize extracting only the most important information. The extraction unit can also provide work-related information in a timely manner based on the employee's work schedule. Furthermore, if an employee's work schedule changes, the content of the extracted information can be adjusted in real time. This enables flexible information provision tailored to the employee's work schedule.

[0110] The generation unit can adjust the format of newsletters to take into account employees' learning styles when generating them. For example, employees who prefer visual learning can be provided with newsletters that make extensive use of graphs and charts. Similarly, employees who prefer auditory learning can be provided with newsletters that include audio content. Furthermore, employees who prefer practical learning can be provided with newsletters that include specific examples and case studies. This enables effective information delivery tailored to each employee's learning style.

[0111] The distribution department can monitor employees' device usage in real time and select the optimal distribution method. For example, if an employee is using a smartphone, the newsletter can be delivered in a format optimized for smartphones. Similarly, if an employee is using a tablet, the newsletter can be delivered in a format optimized for tablets. Furthermore, if an employee is using a desktop computer, the newsletter can be delivered in a format optimized for desktops. This allows for the delivery of newsletters in the most appropriate format based on device usage.

[0112] The profile creation unit can estimate an employee's emotions and adjust the frequency of profile updates based on those estimates. For example, if an employee is stressed, the frequency of profile updates can be reduced to lessen their burden. Conversely, if an employee is relaxed, the frequency of profile updates can be increased to provide the most up-to-date information. Furthermore, if an employee is busy, the frequency of profile updates can be adjusted to provide only essential information. By adjusting the frequency of profile updates according to an employee's emotions, the system can reduce their burden and provide them with the most relevant information.

[0113] The analysis unit can estimate employees' emotions and adjust the analysis algorithm based on those estimates. For example, if an employee is stressed, the analysis algorithm can be simplified to reduce the burden. Conversely, if an employee is relaxed, a more detailed analysis can be performed to improve accuracy. Furthermore, if an employee is busy, only the most important information can be prioritized for analysis. In this way, by adjusting the analysis algorithm according to the employee's emotions, more relevant information can be provided.

[0114] The extraction unit can estimate an employee's emotions and determine the priority of information to extract based on that estimated emotion. For example, if an employee is stressed, it can prioritize extracting information that helps them relax. If an employee is relaxed, it can prioritize extracting information that is useful for their work. Furthermore, if an employee is busy, it can prioritize extracting only important information. In this way, by determining the priority of information to extract according to the employee's emotions, more appropriate information can be provided.

[0115] The generation unit can estimate employees' emotions and adjust the newsletter's presentation based on those estimates. For example, if an employee is stressed, it can provide a simple and visually appealing presentation. If an employee is relaxed, it can provide a presentation that includes more detailed information. Furthermore, if an employee is busy, it can provide a concise presentation. By adjusting the newsletter's presentation according to employees' emotions, it can provide more visually appealing information.

[0116] The distribution department can estimate employees' emotions and adjust the timing of newsletter delivery based on those estimates. For example, if an employee is feeling stressed, the newsletter can be delivered during a time when they can relax. If an employee is relaxed, the newsletter can be delivered before the start of work. Furthermore, if an employee is busy, the newsletter can be delivered after the end of work. By adjusting the timing of newsletter delivery according to employees' emotions, information can be provided at a more appropriate time.

[0117] The following briefly describes the processing flow for example form 2.

[0118] Step 1: The Profile Creation Department creates employee profiles. The Profile Creation Department collects information such as the employee's job duties, areas of interest, skill set, and work history, and generates the profile. Step 2: The analysis unit analyzes the information based on the profile created by the profile creation unit. The analysis unit analyzes information in various formats such as text, audio, and video, and uses LLM to analyze a large amount of internal and external information. Step 3: The extraction unit extracts important information from the information analyzed by the analysis unit. The extraction unit extracts the most relevant information for each employee and extracts highly relevant information from the information analyzed using LLM. Step 4: The generation unit generates a newsletter based on the information extracted by the extraction unit. The generation unit generates a personalized newsletter and creates a newsletter based on the information extracted using LLM. Step 5: The distribution department distributes the newsletters generated by the generation department to employees. The distribution department distributes newsletters to employees every morning, including newsletters generated using AI.

[0119] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0120] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0121] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0122] Each of the multiple elements described above, including the profile creation unit, analysis unit, extraction unit, generation unit, and distribution unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the profile creation unit is implemented by the control unit 46A of the smart device 14 and creates a profile based on the employee's work content and areas of interest. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes a large amount of internal and external information using LLM. The extraction unit is implemented by the specific processing unit 290 of the data processing unit 12 and extracts important information from the analyzed information. The generation unit is implemented by the control unit 46A of the smart device 14 and generates a newsletter based on the extracted information. The distribution unit is implemented by the control unit 46A of the smart device 14 and distributes the generated newsletter to employees. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0123] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0124] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0125] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0126] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0127] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0129] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0130] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0131] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0132] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0133] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0134] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0135] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0137] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0138] Each of the multiple elements described above, including the profile creation unit, analysis unit, extraction unit, generation unit, and distribution unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the profile creation unit is implemented by the control unit 46A of the smart glasses 214 and creates a profile based on the employee's work content and areas of interest. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes a large amount of internal and external information using LLM. The extraction unit is implemented by the specific processing unit 290 of the data processing unit 12 and extracts important information from the analyzed information. The generation unit is implemented by the control unit 46A of the smart glasses 214 and generates a newsletter based on the extracted information. The distribution unit is implemented by the control unit 46A of the smart glasses 214 and distributes the generated newsletter to employees. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0139] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0140] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0141] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0142] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0143] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0145] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0146] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0147] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0148] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0149] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0151] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0153] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] Each of the multiple elements described above, including the profile creation unit, analysis unit, extraction unit, generation unit, and distribution unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the profile creation unit is implemented by the control unit 46A of the headset terminal 314 and creates a profile based on the employee's work content and areas of interest. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes a large amount of internal and external information using LLM. The extraction unit is implemented by the specific processing unit 290 of the data processing unit 12 and extracts important information from the analyzed information. The generation unit is implemented by the control unit 46A of the headset terminal 314 and generates a newsletter based on the extracted information. The distribution unit is implemented by the control unit 46A of the headset terminal 314 and distributes the generated newsletter to employees. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0155] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0156] As shown in Figure 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.

[0157] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0158] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0159] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0161] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0162] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0163] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0164] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0165] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0166] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0167] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0168] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0169] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0170] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0171] Each of the multiple elements described above, including the profile creation unit, analysis unit, extraction unit, generation unit, and distribution unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the profile creation unit is implemented by the control unit 46A of the robot 414 and creates a profile based on the employee's work content and areas of interest. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes a large amount of internal and external information using LLM. The extraction unit is implemented by the specific processing unit 290 of the data processing unit 12 and extracts important information from the analyzed information. The generation unit is implemented by the control unit 46A of the robot 414 and generates a newsletter based on the extracted information. The distribution unit is implemented by the control unit 46A of the robot 414 and distributes the generated newsletter to employees. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0172] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0173] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0174] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0175] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0176] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0177] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0178] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0179] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0180] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0181] 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.

[0182] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0183] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0184] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0185] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0186] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0187] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0188] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0189] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0190] (Note 1) The Profile Creation Department creates employee profiles, An analysis unit that analyzes information based on the profile created by the profile creation unit, An extraction unit extracts important information from the information analyzed by the aforementioned analysis unit, A generation unit generates a newsletter based on the information extracted by the extraction unit, The system comprises a distribution unit that distributes the newsletters generated by the generation unit to employees. A system characterized by the following features. (Note 2) The aforementioned profile creation unit, Create profiles based on employees' job responsibilities and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, It analyzes information in various formats such as text, audio, and video. The system described in Appendix 1, characterized by the features described herein. (Note 4) The extraction unit is The analysis unit extracts information that is optimal for each individual employee from the analyzed data. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is Generate a personalized newsletter based on the extracted information. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned distribution unit, The generated newsletter will be distributed to employees every morning. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned profile creation unit, The system estimates employee sentiment and adjusts the frequency of profile updates based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned profile creation unit, Analyze employees' past work history to improve the accuracy of their profiles. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned profile creation unit, When creating a profile, customize it to take into account the employee's skill set and career goals. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned profile creation unit, The system estimates employee sentiment and determines profile priorities based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned profile creation unit, When creating a profile, optimize the profile by taking into account the employee's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned profile creation unit, When creating profiles, analyze employees' social media activity and reflect it in the profiles. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, The system estimates employee emotions and adjusts the analysis algorithm based on the estimated employee emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, the reliability of the information is evaluated, and the most reliable information is prioritized for analysis. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, different analytical methods are applied depending on the category of information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, The system estimates employee emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During the analysis, the priority of the analysis is determined based on when the information was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The extraction unit is The system estimates employee sentiment and prioritizes the information to extract based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The extraction unit is During extraction, the interrelationships between pieces of information are taken into consideration to improve the accuracy of the extraction. The system described in Appendix 1, characterized by the features described herein. (Note 21) The extraction unit is During extraction, the attribute information of the information submitter is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The extraction unit is We estimate employee sentiment and adjust how information extracted based on that estimated sentiment is displayed. The system described in Appendix 1, characterized by the features described herein. (Note 23) The extraction unit is During extraction, the geographical distribution of the information is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The extraction unit is During extraction, we improve the accuracy of the extraction by referring to relevant literature. The system described in Appendix 1, characterized by the features described herein. (Note 25) The generating unit is We estimate employee sentiment and adjust the tone of the newsletter based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The generating unit is When generating a newsletter, adjust the level of detail based on the importance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 27) The generating unit is When generating newsletters, different generation algorithms are applied depending on the category of information. The system described in Appendix 1, characterized by the features described herein. (Note 28) The generating unit is Estimate employee sentiment and adjust the length of the newsletter based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The generating unit is When generating newsletters, we prioritize them based on when the information was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The generating unit is When generating newsletters, adjust the order of the newsletters based on the relevance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned distribution unit, We estimate employee sentiment and adjust the timing of newsletter delivery based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned distribution unit, When sending out newsletters, the system will select the most suitable delivery method by referring to employees' past newsletter viewing history. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned distribution unit, We estimate employee sentiment and adjust the frequency of newsletter delivery based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned distribution unit, When distributing information, the optimal distribution method is selected, taking into account the device information of the employees. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0191] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The Profile Creation Department creates employee profiles, An analysis unit that analyzes information based on the profile created by the profile creation unit, An extraction unit extracts important information from the information analyzed by the aforementioned analysis unit, A generation unit generates a newsletter based on the information extracted by the extraction unit, The system comprises a distribution unit that distributes the newsletters generated by the generation unit to employees. A system characterized by the following features.

2. The aforementioned profile creation unit, Create profiles based on employees' job responsibilities and areas of interest. The system according to feature 1.

3. The aforementioned analysis unit, It analyzes information in various formats such as text, audio, and video. The system according to feature 1.

4. The extraction unit is The analysis unit extracts information that is optimal for each individual employee from the analyzed data. The system according to feature 1.

5. The generating unit is Generate a personalized newsletter based on the extracted information. The system according to feature 1.

6. The aforementioned distribution unit, The generated newsletter will be distributed to employees every morning. The system according to feature 1.

7. The aforementioned profile creation unit, The system estimates employee sentiment and adjusts the frequency of profile updates based on the estimated sentiment. The system according to feature 1.

8. The aforementioned profile creation unit, Analyze employees' past work history to improve the accuracy of their profiles. The system according to feature 1.

Images