System

Abstract

To automatize schedule adjustment of a next meeting and creation of a thank-for-appointment mail after completion of customer appointment.SOLUTION: A system according to an embodiment of the present invention comprises a collection unit, an analysis unit, an adjustment unit, and a generation unit. The collection unit collects minutes or calendar information. The analysis unit analyzes the information collected by the collection unit. The adjustment unit adjusts schedules for next meetings on the basis of analysis results obtained by the adjustment unit. The generation unit generates written text of a thank-for-appointment mail on the basis of schedules adjusted by the adjustment unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, there was an issue that arranging the next meeting after a customer appointment or creating a thank-you email for the appointment was time-consuming.

[0005] The system according to the embodiment aims to automate the scheduling of the next meeting after a customer appointment and the creation of a thank-you email for the appointment. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, an adjustment unit, and a generation unit. The collection unit collects minutes or calendar information. The analysis unit analyzes the information collected by the collection unit. The adjustment unit adjusts the date of the next meeting based on the analysis result obtained by the analysis unit. The generation unit generates the text of a thank you email for the appointment based on the date adjusted by the adjustment unit. Effect of the Invention

[0007] The system according to the embodiment can automate the scheduling of the next meeting after a customer appointment and the creation of a thank-you email for the appointment. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The appointment thank-you email automatic generation system according to the embodiment of the present invention is a system that automatically creates an appointment thank-you email for a customer after a customer appointment. This system is a mechanism that automatically generates the schedule and text of the next meeting from the minutes and calendar information. First, the minutes and calendar information are collected after the appointment is completed, and AI analyzes this information. Next, the schedule of the next meeting is adjusted based on the analysis results, and an appropriate text is generated. This eliminates the trouble of adjusting the schedule, and allows business negotiations to proceed smoothly. For example, the minutes and calendar information are collected after the appointment is completed. The minutes often contain the contents of the appointment and the desired date and time of the next meeting. In addition, the calendar information contains the schedule of the customer and the person in charge. These pieces of information are collected and analyzed by AI. Next, the information collected by AI is analyzed. For example, the desired date and time of the next meeting is extracted from the minutes, and the free time of the customer and the person in charge is identified from the calendar information. This automatically adjusts the schedule of the next meeting. Furthermore, the AI ​​generates the text of the appointment thank-you email based on the analysis results. For example, the system automatically creates a message such as, "Thank you for taking the time to meet with us today despite your busy schedule. How about scheduling our next meeting on XX / XX / XX?" This allows the person in charge to send a thank-you email to the customer quickly and without any trouble. This system eliminates the need for schedule adjustments and allows business negotiations to proceed smoothly. For example, when a person in charge manually adjusts a schedule, it often takes a long time to communicate with the customer, but by using the present invention, schedule adjustments can be made quickly and efficiently. In addition, the message for the appointment thank-you email is automatically generated, reducing the burden on the person in charge. This allows the appointment thank-you email automatic generation system to quickly and efficiently create an appointment thank-you email for the customer after the appointment is completed.

[0029] The appointment thank-you email automatic generation system according to the embodiment includes a collection unit, an analysis unit, an adjustment unit, and a generation unit. The collection unit collects minutes and calendar information. The minutes often contain, for example, the contents of the appointment and the desired date and time of the next meeting. The calendar information also contains the schedules of the client and the person in charge. The collection unit collects these pieces of information and provides them to the analysis unit. The analysis unit analyzes the information collected by the collection unit. The analysis unit extracts the desired date and time of the next meeting from the minutes using, for example, natural language processing technology, and identifies the free time of the client and the person in charge from the calendar information. The adjustment unit adjusts the schedule of the next meeting based on the analysis result obtained by the analysis unit. The adjustment unit adjusts the schedule while taking into account the free time of the client and the person in charge, for example, using an algorithm that selects the optimal date and time. The generation unit generates the text of the appointment thank-you email based on the schedule adjusted by the adjustment unit. The generation unit can generate the text using, for example, a template. The generation unit can also ensure the quality of the text using a feedback loop. This enables the appointment thank-you email automatic generation system to automatically collect, analyze, adjust schedules, and generate text for minutes and calendar information. For example, the collection unit can specifically describe the format of the minutes and the method for obtaining calendar information. The analysis unit can use natural language processing to extract information from the minutes. The adjustment unit can use an algorithm to select the optimal date and time. The generation unit can include a method for using and customizing templates. The generation unit can ensure the quality of the text using a feedback loop. This enables the appointment thank-you email automatic generation system to quickly and efficiently create appointment thank-you emails for customers after the customer appointments are completed.

[0030] The collection unit collects minutes and calendar information. For example, the minutes often contain the contents of the appointment and the desired date and time of the next meeting. In addition, the calendar information contains the schedules of the client and the person in charge. The collection unit collects these pieces of information and provides them to the analysis unit. Specifically, the collection unit extracts text data according to the format of the minutes, and the calendar information can be acquired through an API. Since the formats of minutes are diverse, such as handwritten notes, voice recordings, and digital documents, the collection unit is equipped with various data collection means to handle these formats. For example, handwritten notes are converted into digital text using OCR technology, and voice recordings are converted into text using voice recognition technology. For digital documents, text data is extracted using an appropriate parser depending on the file format. Calendar information is acquired through an API from general calendar services such as Google (registered trademark) Calendar and Outlook (registered trademark) Calendar, and schedules of clients and the person in charge are collected. This allows the collection unit to efficiently collect minutes and calendar information in various formats and provide it to the analysis unit. Furthermore, the collection unit is equipped with a database for centrally managing the collected data and maintaining the consistency of the data. This database organizes the collected data in chronological order and allows past data to be referenced as necessary, allowing the data collection unit to collect data efficiently and accurately, improving the performance of the entire system.

[0031] The analysis unit analyzes the information collected by the collection unit. For example, the analysis unit uses natural language processing technology to extract the desired date and time of the next meeting from the minutes, and identifies the free time of the customer or person in charge from the calendar information. Specifically, the analysis unit uses natural language processing technology to analyze the text data of the minutes and extract information about the next meeting. For example, a date and time recognition algorithm can be used to extract date and time expressions in the text. In addition, a schedule analysis algorithm can be used from the calendar information to analyze the schedule of the customer or person in charge and identify the free time. This allows the analysis unit to quickly and accurately analyze the collected data and identify the desired date and time of the next meeting and the free time. Furthermore, the analysis unit can also analyze long-term schedule trends by utilizing past data and statistical information. For example, the analysis unit analyzes the schedule pattern of a specific customer or person in charge based on past meeting data, and predicts the optimal meeting date and time. In addition, the analysis unit can use an anomaly detection algorithm to detect schedule patterns that are different from normal or abnormal data, and issue an early warning. This enables the analysis unit to not only grasp the situation in real time, but also handle long-term schedule management and anomaly detection, improving the reliability and efficiency of the entire system.

[0032] The adjustment unit adjusts the date of the next meeting based on the analysis result obtained by the analysis unit. The adjustment unit adjusts the schedule while considering the free time of the customer and the person in charge, for example, using an algorithm for selecting the optimal date and time. Specifically, the adjustment unit executes an algorithm for selecting the optimal meeting date and time based on the schedules of the customer and the person in charge. This algorithm has evaluation criteria for comparing the free time of each schedule and selecting the most suitable date and time. For example, it can preferentially select a time period when both the customer and the person in charge are free, and further consider past meeting trends and preferences for specific days of the week and time periods. This allows the adjustment unit to efficiently adjust the schedules of the customer and the person in charge and select the optimal meeting date and time. Furthermore, the adjustment unit also has a function for sending a meeting reminder to the customer and the person in charge based on the selected date and time. For example, it can send a reminder the day before the meeting to have the customer and the person in charge reconfirm the date and time of the meeting. In addition, the adjustment unit can quickly respond to schedule changes or cancellations and reschedule a new meeting date and time. This enables the coordination department to adjust schedules efficiently and flexibly, improving convenience for customers and staff.

[0033] The generation unit generates the text of the appointment thank-you email based on the schedule adjusted by the adjustment unit. The generation unit can generate the text using, for example, a template. The generation unit can also ensure the quality of the text using a feedback loop. Specifically, the generation unit can select and customize the optimal text according to the customer and the contents of the meeting based on multiple templates prepared in advance. For example, the template includes general thank-you text and a confirmation text for the next meeting date and time, and generates the text by combining these. The generation unit can also use natural language generation technology to automatically customize the text of the template and generate more natural and individualized text. Furthermore, the generation unit uses a feedback loop to ensure the quality of the generated text. Specifically, the generated text is sent to the customer or the person in charge, and the reaction and feedback are collected. Based on this feedback, the template and the generation algorithm can be improved, and the quality of the text can be continuously improved. For example, the response rate and satisfaction level from the customer can be evaluated, and the wording and structure of the template can be reviewed based on this. This enables the generation unit to consistently generate high-quality appointment thank-you emails and facilitate smooth communication with customers.

[0034] The collection unit can specifically describe the format of the minutes or the method of acquiring the calendar information. The collection unit can, for example, specifically describe the format of the minutes. The format of the minutes includes, for example, a text format, an audio format, and the like, but is not limited to such examples. The collection unit can also specifically describe the method of acquiring the calendar information. The method of acquiring the calendar information includes, for example, acquisition using an API, manual input, and the like, but is not limited to such examples. By specifically describing the format of the minutes and the method of acquiring the calendar information, the accuracy of information collection is improved. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the format of the minutes and the method of acquiring the calendar information to AI, and have AI select the optimal format and acquisition method.

[0035] The analysis unit can extract information from the minutes using natural language processing. The analysis unit extracts information from the minutes using, for example, natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, semantic analysis, etc., but is not limited to such examples. For example, the analysis unit divides the text of the minutes into words using morphological analysis, analyzes the structure of the sentence using grammatical analysis, and understands the meaning of the sentence using semantic analysis. As a result, the accuracy of information extraction from the minutes is improved by using natural language processing. Part or all of the above-mentioned processing in the analysis unit is performed using a generation AI. For example, the analysis unit inputs the text data of the minutes to a generation AI, which performs morphological analysis, grammatical analysis, and semantic analysis to extract information.

[0036] The adjustment unit can use an algorithm for selecting an appropriate date and time. The adjustment unit uses, for example, an algorithm for selecting an appropriate date and time. The algorithm for selecting an appropriate date and time includes, for example, an optimization algorithm, a heuristic algorithm, and the like, but is not limited to such examples. For example, the adjustment unit uses an optimization algorithm to select an optimal date and time while considering the free time of the customer and the person in charge. The adjustment unit can also use a heuristic algorithm to select an optimal date and time based on past data. As a result, by using an algorithm for selecting an optimal date and time, the accuracy of schedule adjustment is improved. A part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can input schedule data of the customer and the person in charge into AI and cause AI to execute an algorithm for selecting an optimal date and time.

[0037] The generation unit may include a method for using or customizing a template. The generation unit may include, for example, a method for using a template. The method for using a template may include, for example, a fixed template, a dynamic template, and the like, but is not limited to such examples. For example, the generation unit may generate a text using a fixed template. The generation unit may also customize a text based on a user's input using a dynamic template. Furthermore, the generation unit may include a method for customization. The method for customization may include, for example, customization based on a user's input, customization based on past data, and the like, but is not limited to such examples. For example, the generation unit may customize a text based on a user's input. The generation unit may also customize a text based on past data. As a result, the inclusion of a method for using or customizing a template improves the flexibility of text generation. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit inputs template data to the generation AI, and the generation AI generates a text based on the template.

[0038] The generation unit can ensure the quality of the text by using a feedback loop. The generation unit, for example, ensures the quality of the text by using a feedback loop. The feedback loop includes, for example, a method of collecting user feedback, a method of reflecting the feedback, and the like, but is not limited to such examples. For example, the generation unit collects user feedback and improves the text based on the feedback. The generation unit can also continuously improve the quality of the text by using a method of reflecting the feedback. As a result, the quality of the text is continuously improved by using the feedback loop. A part or all of the above-mentioned processing in the generation unit is performed by using a generation AI. For example, the generation unit inputs user feedback data into the generation AI, and the generation AI improves the text based on the feedback.

[0039] The collection unit can handle data from the viewpoint of security or privacy protection. The collection unit handles data from the viewpoint of security, for example. Security measures include, but are not limited to, data encryption and access control. For example, the collection unit ensures the safety of data by encrypting and storing data and performing access control. The collection unit can also handle data from the viewpoint of privacy protection. Privacy protection measures include, but are not limited to, personal information anonymization and data minimization. For example, the collection unit protects privacy by anonymizing and storing personal information and collecting only the minimum necessary data. As a result, the safety of information is improved by handling data from the viewpoint of security and privacy protection. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can cause AI to perform data encryption and access control.

[0040] The collection unit can optimize the format of the minutes or the method of acquiring calendar information based on the user's past behavior history. For example, the collection unit automatically selects and collects a format of minutes used by the user in the past. The collection unit can also preferentially acquire information from a calendar app used by the user in the past. Furthermore, the collection unit can also suggest the most efficient information acquisition method from the user's past behavior history. This improves the efficiency of information collection by optimizing the information acquisition method based on the user's past behavior history. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's past behavior history data to the generation AI and cause the generation AI to select the optimal information acquisition method.

[0041] The collection unit can determine the priority of collection based on the contents of the minutes and the importance of the calendar information at the time of collection. For example, the collection unit preferentially collects minutes of important meetings. The collection unit can also preferentially collect calendar information including important events. Furthermore, the collection unit can prioritize collecting information of high importance while leaving information of low importance for later. In this way, important information can be preferentially collected by determining the priority of collection based on the importance of information. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input importance data of the minutes and calendar information to the generation AI and have the generation AI determine the priority of collection.

[0042] The collection unit can collect highly relevant information preferentially based on the user's geographical location information at the time of collection. For example, when the user is in a specific location, the collection unit preferentially collects information related to the location. In addition, when the user is moving, the collection unit can also preferentially collect information related to the destination. Furthermore, when the user is at home, the collection unit can also preferentially collect information related to the home. As a result, by preferentially collecting highly relevant information based on the user's geographical location information, the accuracy of information collection is improved. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit inputs the user's geographical location information data to the generation AI and allows the generation AI to select highly relevant information.

[0043] The collection unit can analyze the user's social media activity at the time of collection and collect related information. The collection unit can collect related minutes and calendar information based on information shared by the user on social media, for example. The collection unit can also collect information related to the next meeting from the user's social media activity. Furthermore, the collection unit can also collect information related to topics mentioned by the user on social media. This improves the accuracy of information collection by collecting related information based on the user's social media activity. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or without using AI. For example, the collection unit can input the user's social media activity data to the generation AI and have the generation AI collect related information.

[0044] When extracting information from the minutes using natural language processing, the analysis unit can adjust the level of detail of the analysis based on the importance of the contents of the minutes. For example, the analysis unit analyzes the minutes of important meetings in detail. The analysis unit can also analyze the minutes of less important meetings simply. Furthermore, the analysis unit can dynamically adjust the level of detail of the analysis according to the importance. As a result, important information can be analyzed in detail by adjusting the level of detail of the analysis based on the importance of the contents of the minutes. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input importance data of the contents of the minutes to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0045] The analysis unit can apply different analysis algorithms depending on the category of the minutes during analysis. For example, the analysis unit applies an analysis algorithm specialized for technical terms to minutes of a technical meeting. The analysis unit can also apply an analysis algorithm specialized for sales terms to minutes of a sales meeting. Furthermore, the analysis unit can dynamically select an optimal analysis algorithm depending on the category. This improves the accuracy of the analysis by applying different analysis algorithms depending on the category of the minutes. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input category data of the minutes to the generation AI and have the generation AI select the optimal analysis algorithm.

[0046] During analysis, the analysis unit can determine the priority of the analysis based on the submission time of the minutes. For example, the analysis unit prioritizes the analysis of the minutes that were submitted most recently. The analysis unit can also postpone minutes that were submitted earlier. Furthermore, the analysis unit can dynamically adjust the priority of the analysis according to the submission time. In this way, by determining the priority of the analysis based on the submission time of the minutes, it is possible to prioritize the analysis of the latest information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the submission time data of the minutes to the generation AI and have the generation AI determine the priority of the analysis.

[0047] The analysis unit can adjust the order of analysis based on the relevance of the minutes during analysis. For example, the analysis unit prioritizes analysis of minutes of important meetings. The analysis unit can also postpone analysis of minutes with low relevance. Furthermore, the analysis unit can dynamically adjust the order of analysis according to the relevance. As a result, important information can be analyzed with priority by adjusting the order of analysis based on the relevance of the minutes. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input relevance data of the minutes to the generation AI and have the generation AI adjust the order of analysis.

[0048] When using an algorithm for selecting an appropriate date and time, the adjustment unit can optimize the algorithm by referring to the user's past schedule history. For example, the adjustment unit preferentially selects a date and time that the user has frequently used in the past. The adjustment unit can also predict the optimal date and time from the user's past schedule history. Furthermore, the adjustment unit can dynamically select the optimal date and time based on the user's past schedule history. This improves the accuracy of selecting the optimal date and time by referring to the user's past schedule history. A part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the user's past schedule history data to the generation AI and have the generation AI select the optimal date and time.

[0049] The adjustment unit can customize the adjustment means based on the user's current living situation when adjusting the schedule. For example, when the user is busy, the adjustment unit provides a simplified schedule adjustment means. Also, when the user is relaxed, the adjustment unit can provide a detailed schedule adjustment means. Furthermore, the adjustment unit can dynamically select an optimal schedule adjustment means according to the user's living situation. This allows the user to adjust the schedule optimally by customizing the adjustment means according to the user's living situation. A part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the user's living situation data to the generation AI and have the generation AI customize the adjustment means.

[0050] The adjustment unit can select an appropriate date and time in consideration of the user's geographical location information when adjusting the schedule. For example, when the user is in a specific location, the adjustment unit preferentially selects a date and time related to that location. In addition, when the user is moving, the adjustment unit can also preferentially select a date and time related to the destination. Furthermore, when the user is at home, the adjustment unit can also preferentially select a date and time related to the home. This improves the accuracy of schedule adjustment by selecting the optimal date and time based on the user's geographical location information. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the user's geographical location information data to the generation AI and cause the generation AI to select the optimal date and time.

[0051] The adjustment unit can analyze the user's social media activity and suggest a means of adjustment when adjusting the schedule. The adjustment unit can suggest a relevant date and time based on, for example, information shared by the user on social media. The adjustment unit can also suggest a date and time related to the next meeting based on the user's social media activity. Furthermore, the adjustment unit can also suggest a date and time related to a topic mentioned by the user on social media. This improves the accuracy of schedule adjustment by suggesting a means of adjustment based on the user's social media activity. A part or all of the above-mentioned processing in the adjustment unit can be performed, for example, using AI or can be performed without using AI. For example, the adjustment unit can input the user's social media activity data to the generation AI and have the generation AI suggest a means of adjustment.

[0052] The generation unit can optimize the use of templates and the customization method based on the user's past email history. For example, the generation unit automatically selects an email template that the user has used in the past and generates text. The generation unit can also generate new text based on the style of text that the user has customized in the past. Furthermore, the generation unit can suggest the most effective text from the user's past email history. This improves the accuracy of text generation by optimizing the template and the customization method based on the user's past email history. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input the user's past email history data into the generation AI and have the generation AI select the optimal template and customization method.

[0053] When using a feedback loop to ensure the quality of a text, the generation unit can optimize the text by referring to the user's past feedback. The generation unit reflects improvements to the text based on, for example, feedback provided by the user in the past. The generation unit can also generate the most effective text from the user's past feedback. Furthermore, the generation unit can also continuously improve the quality of the text using a feedback loop. This improves the quality of the text by optimizing the quality of the text based on the user's past feedback. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input the user's past feedback data into the generation AI and have the generation AI optimize the quality of the text.

[0054] The generation unit can determine the priority of the text based on the time of sending the email when generating the text. For example, the generation unit generates and sends important emails with priority. The generation unit can also generate emails with a priority when the time of sending is approaching with priority. Furthermore, the generation unit can dynamically adjust the priority of the text according to the time of sending. This allows important emails to be generated with priority by determining the priority of the text based on the time of sending the email. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input email sending time data to the generation AI and have the generation AI determine the priority of the text.

[0055] The generation unit can adjust the order of the text based on the relevance of the emails when generating the text. For example, the generation unit generates the text of important emails with priority. The generation unit can also postpone the text of emails with low relevance. Furthermore, the generation unit can dynamically adjust the order of the text according to the relevance. This allows important emails to be generated with priority by adjusting the order of the text based on the relevance of the emails. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input email relevance data to the generation AI and have the generation AI adjust the order of the text.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] The collection unit can optimize the method of collecting minutes and calendar information based on the user's past behavior history. For example, the collection unit can automatically select and collect the format of minutes used by the user in the past. It can also preferentially acquire information from a calendar app used by the user in the past. Furthermore, it can suggest the most efficient information acquisition method based on the user's past behavior history. This improves the efficiency of information collection by optimizing the information acquisition method based on the user's past behavior history.

[0058] The analysis unit can adjust the level of detail of the analysis based on the importance of the contents of the minutes. For example, minutes of important meetings can be analyzed in detail, and minutes of less important meetings can be analyzed simply. Furthermore, the level of detail of the analysis can be dynamically adjusted according to the importance. This allows important information to be analyzed in detail by adjusting the level of detail of the analysis based on the importance of the contents of the minutes.

[0059] The adjustment unit can select the optimal date and time by referring to the user's past schedule history. For example, the adjustment unit preferentially selects a date and time that the user has frequently used in the past. The adjustment unit can also predict the optimal date and time from the user's past schedule history. Furthermore, the adjustment unit can dynamically select the optimal date and time based on the user's past schedule history. This improves the accuracy of selecting the optimal date and time by referring to the user's past schedule history.

[0060] The generation unit can optimize templates and customization methods based on the user's past email history. For example, it can automatically select an email template that the user has used in the past to generate text. It can also generate new text based on the style of text that the user has customized in the past. It can also suggest the most effective text from the user's past email history. This improves the accuracy of text generation by optimizing templates and customization methods based on the user's past email history.

[0061] When using the feedback loop to ensure the quality of the text, the generation unit can optimize the text by referring to the user's past feedback. For example, the generation unit reflects improvements to the text based on feedback provided by the user in the past. The generation unit can also generate the most effective text from the user's past feedback. Furthermore, the feedback loop can be used to continuously improve the quality of the text. This improves the quality of the text by optimizing the quality of the text based on the user's past feedback.

[0062] The process flow of the first embodiment will be briefly described below.

[0063] Step 1: The collection department collects minutes and calendar information. Minutes often contain the details of appointments and the desired date and time of the next meeting, and calendar information contains the schedules of clients and staff. The collection department collects this information and provides it to the analysis department. Step 2: The analysis unit analyzes the information collected by the collection unit. The analysis unit uses natural language processing technology to extract the desired date and time of the next meeting from the minutes, and identifies the free time of the customer and person in charge from the calendar information. Step 3: The coordination department adjusts the schedule for the next meeting based on the analysis results obtained by the analysis department. The coordination department adjusts the schedule using an algorithm that selects the optimal date and time, taking into account the free time of the customer and the person in charge. Step 4: The generation unit generates the text of the appointment thank-you email based on the schedule adjusted by the adjustment unit. The generation unit can generate the text using a template and can also ensure the quality of the text using a feedback loop.

[0064] (Example 2) The appointment thank-you email automatic generation system according to the embodiment of the present invention is a system that automatically creates an appointment thank-you email for a customer after a customer appointment. This system is a mechanism that automatically generates the schedule and text of the next meeting from the minutes and calendar information. First, the minutes and calendar information are collected after the appointment is completed, and AI analyzes this information. Next, the schedule of the next meeting is adjusted based on the analysis results, and an appropriate text is generated. This eliminates the trouble of adjusting the schedule, and allows business negotiations to proceed smoothly. For example, the minutes and calendar information are collected after the appointment is completed. The minutes often contain the contents of the appointment and the desired date and time of the next meeting. In addition, the calendar information contains the schedule of the customer and the person in charge. These pieces of information are collected and analyzed by AI. Next, the information collected by AI is analyzed. For example, the desired date and time of the next meeting is extracted from the minutes, and the free time of the customer and the person in charge is identified from the calendar information. This automatically adjusts the schedule of the next meeting. Furthermore, the AI ​​generates the text of the appointment thank-you email based on the analysis results. For example, the system automatically creates a message such as, "Thank you for taking the time to meet with us today despite your busy schedule. How about scheduling our next meeting on XX / XX / XX?" This allows the person in charge to send a thank-you email to the customer quickly and without any trouble. This system eliminates the need for schedule adjustments and allows business negotiations to proceed smoothly. For example, when a person in charge manually adjusts a schedule, it often takes a long time to communicate with the customer, but by using the present invention, schedule adjustments can be made quickly and efficiently. In addition, the message for the appointment thank-you email is automatically generated, reducing the burden on the person in charge. This allows the appointment thank-you email automatic generation system to quickly and efficiently create an appointment thank-you email for the customer after the appointment is completed.

[0065] The appointment thank-you email automatic generation system according to the embodiment includes a collection unit, an analysis unit, an adjustment unit, and a generation unit. The collection unit collects minutes and calendar information. The minutes often contain, for example, the contents of the appointment and the desired date and time of the next meeting. The calendar information also contains the schedules of the client and the person in charge. The collection unit collects these pieces of information and provides them to the analysis unit. The analysis unit analyzes the information collected by the collection unit. The analysis unit extracts the desired date and time of the next meeting from the minutes using, for example, natural language processing technology, and identifies the free time of the client and the person in charge from the calendar information. The adjustment unit adjusts the schedule of the next meeting based on the analysis result obtained by the analysis unit. The adjustment unit adjusts the schedule while taking into account the free time of the client and the person in charge, for example, using an algorithm that selects the optimal date and time. The generation unit generates the text of the appointment thank-you email based on the schedule adjusted by the adjustment unit. The generation unit can generate the text using, for example, a template. The generation unit can also ensure the quality of the text using a feedback loop. This enables the appointment thank-you email automatic generation system to automatically collect, analyze, adjust schedules, and generate text for minutes and calendar information. For example, the collection unit can specifically describe the format of the minutes and the method for obtaining calendar information. The analysis unit can use natural language processing to extract information from the minutes. The adjustment unit can use an algorithm to select the optimal date and time. The generation unit can include a method for using and customizing templates. The generation unit can ensure the quality of the text using a feedback loop. This enables the appointment thank-you email automatic generation system to quickly and efficiently create appointment thank-you emails for customers after the customer appointments are completed.

[0066] The collection department collects minutes and calendar information. For example, the minutes often contain the contents of the appointment and the desired date and time of the next meeting. In addition, the calendar information contains the schedules of the client and the person in charge. The collection department collects this information and provides it to the analysis department. Specifically, the collection department extracts text data according to the format of the minutes, and the calendar information can be obtained through an API. Since the formats of minutes are diverse, such as handwritten notes, voice recordings, and digital documents, the collection department has various data collection means to handle these formats. For example, handwritten notes are converted into digital text using OCR technology, and voice recordings are converted into text using voice recognition technology. For digital documents, text data is extracted using an appropriate parser depending on the file format. Calendar information is obtained through APIs from common calendar services such as Google Calendar and Outlook Calendar, and schedules of clients and people in charge are collected. This allows the collection department to efficiently collect minutes and calendar information in various formats and provide it to the analysis department. In addition, the collection department has a database for centrally managing the collected data and maintaining the consistency of the data. This database organizes the collected data in chronological order and allows past data to be referenced as necessary, allowing the data collection unit to collect data efficiently and accurately, improving the performance of the entire system.

[0067] The analysis unit analyzes the information collected by the collection unit. For example, the analysis unit uses natural language processing technology to extract the desired date and time of the next meeting from the minutes, and identifies the free time of the customer or person in charge from the calendar information. Specifically, the analysis unit uses natural language processing technology to analyze the text data of the minutes and extract information about the next meeting. For example, a date and time recognition algorithm can be used to extract date and time expressions in the text. In addition, a schedule analysis algorithm can be used from the calendar information to analyze the schedule of the customer or person in charge and identify the free time. This allows the analysis unit to quickly and accurately analyze the collected data and identify the desired date and time of the next meeting and the free time. Furthermore, the analysis unit can also analyze long-term schedule trends by utilizing past data and statistical information. For example, the analysis unit analyzes the schedule pattern of a specific customer or person in charge based on past meeting data, and predicts the optimal meeting date and time. In addition, the analysis unit can use an anomaly detection algorithm to detect schedule patterns that are different from normal or abnormal data, and issue an early warning. This enables the analysis unit to not only grasp the situation in real time, but also handle long-term schedule management and anomaly detection, improving the reliability and efficiency of the entire system.

[0068] The adjustment unit adjusts the date of the next meeting based on the analysis result obtained by the analysis unit. The adjustment unit adjusts the schedule while considering the free time of the customer and the person in charge, for example, using an algorithm for selecting the optimal date and time. Specifically, the adjustment unit executes an algorithm for selecting the optimal meeting date and time based on the schedules of the customer and the person in charge. This algorithm has evaluation criteria for comparing the free time of each schedule and selecting the most suitable date and time. For example, it can preferentially select a time period when both the customer and the person in charge are free, and further consider past meeting trends and preferences for specific days of the week and time periods. This allows the adjustment unit to efficiently adjust the schedules of the customer and the person in charge and select the optimal meeting date and time. Furthermore, the adjustment unit also has a function for sending a meeting reminder to the customer and the person in charge based on the selected date and time. For example, it can send a reminder the day before the meeting to have the customer and the person in charge reconfirm the date and time of the meeting. In addition, the adjustment unit can quickly respond to schedule changes or cancellations and reschedule a new meeting date and time. This enables the coordination department to adjust schedules efficiently and flexibly, improving convenience for customers and staff.

[0069] The generation unit generates the text of the appointment thank-you email based on the schedule adjusted by the adjustment unit. The generation unit can generate the text using, for example, a template. The generation unit can also ensure the quality of the text using a feedback loop. Specifically, the generation unit can select and customize the optimal text according to the customer and the contents of the meeting based on multiple templates prepared in advance. For example, the template includes general thank-you text and a confirmation text for the next meeting date and time, and generates the text by combining these. The generation unit can also use natural language generation technology to automatically customize the text of the template and generate more natural and individualized text. Furthermore, the generation unit uses a feedback loop to ensure the quality of the generated text. Specifically, the generated text is sent to the customer or the person in charge, and the reaction and feedback are collected. Based on this feedback, the template and the generation algorithm can be improved, and the quality of the text can be continuously improved. For example, the response rate and satisfaction level from the customer can be evaluated, and the wording and structure of the template can be reviewed based on this. This enables the generation unit to consistently generate high-quality appointment thank-you emails and facilitate smooth communication with customers.

[0070] The collection unit can specifically describe the format of the minutes or the method of acquiring the calendar information. The collection unit can, for example, specifically describe the format of the minutes. The format of the minutes includes, for example, a text format, an audio format, and the like, but is not limited to such examples. The collection unit can also specifically describe the method of acquiring the calendar information. The method of acquiring the calendar information includes, for example, acquisition using an API, manual input, and the like, but is not limited to such examples. By specifically describing the format of the minutes and the method of acquiring the calendar information, the accuracy of information collection is improved. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the format of the minutes and the method of acquiring the calendar information to AI, and have AI select the optimal format and acquisition method.

[0071] The analysis unit can extract information from the minutes using natural language processing. The analysis unit extracts information from the minutes using, for example, natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, semantic analysis, etc., but is not limited to such examples. For example, the analysis unit divides the text of the minutes into words using morphological analysis, analyzes the structure of the sentence using grammatical analysis, and understands the meaning of the sentence using semantic analysis. As a result, the accuracy of information extraction from the minutes is improved by using natural language processing. Part or all of the above-mentioned processing in the analysis unit is performed using a generation AI. For example, the analysis unit inputs the text data of the minutes to a generation AI, which performs morphological analysis, grammatical analysis, and semantic analysis to extract information.

[0072] The adjustment unit can use an algorithm for selecting an appropriate date and time. The adjustment unit uses, for example, an algorithm for selecting an appropriate date and time. The algorithm for selecting an appropriate date and time includes, for example, an optimization algorithm, a heuristic algorithm, and the like, but is not limited to such examples. For example, the adjustment unit uses an optimization algorithm to select an optimal date and time while considering the free time of the customer and the person in charge. The adjustment unit can also use a heuristic algorithm to select an optimal date and time based on past data. As a result, by using an algorithm for selecting an optimal date and time, the accuracy of schedule adjustment is improved. A part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can input schedule data of the customer and the person in charge into AI and cause AI to execute an algorithm for selecting an optimal date and time.

[0073] The generation unit may include a method for using or customizing a template. The generation unit may include, for example, a method for using a template. The method for using a template may include, for example, a fixed template, a dynamic template, and the like, but is not limited to such examples. For example, the generation unit may generate a text using a fixed template. The generation unit may also customize a text based on a user's input using a dynamic template. Furthermore, the generation unit may include a method for customization. The method for customization may include, for example, customization based on a user's input, customization based on past data, and the like, but is not limited to such examples. For example, the generation unit may customize a text based on a user's input. The generation unit may also customize a text based on past data. As a result, the inclusion of a method for using or customizing a template improves the flexibility of text generation. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit inputs template data to the generation AI, and the generation AI generates a text based on the template.

[0074] The generation unit can ensure the quality of the text by using a feedback loop. The generation unit, for example, ensures the quality of the text by using a feedback loop. The feedback loop includes, for example, a method of collecting user feedback, a method of reflecting the feedback, and the like, but is not limited to such examples. For example, the generation unit collects user feedback and improves the text based on the feedback. The generation unit can also continuously improve the quality of the text by using a method of reflecting the feedback. As a result, the quality of the text is continuously improved by using the feedback loop. A part or all of the above-mentioned processing in the generation unit is performed by using a generation AI. For example, the generation unit inputs user feedback data into the generation AI, and the generation AI improves the text based on the feedback.

[0075] The collection unit can handle data from the viewpoint of security or privacy protection. The collection unit handles data from the viewpoint of security, for example. Security measures include, but are not limited to, data encryption and access control. For example, the collection unit ensures the safety of data by encrypting and storing data and performing access control. The collection unit can also handle data from the viewpoint of privacy protection. Privacy protection measures include, but are not limited to, personal information anonymization and data minimization. For example, the collection unit protects privacy by anonymizing and storing personal information and collecting only the minimum necessary data. As a result, the safety of information is improved by handling data from the viewpoint of security and privacy protection. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can cause AI to perform data encryption and access control.

[0076] The collection unit can estimate the user's emotion and adjust the collection timing of the minutes and calendar information based on the estimated user's emotion. For example, when the user is feeling stressed, the collection unit delays the collection timing to collect information when the user is in a relaxed state. In addition, when the user is relaxed, the collection unit can immediately collect information and quickly start analysis. Furthermore, when the user is in a hurry, the collection unit can advance the collection timing to quickly proceed to the next step. This reduces the burden on the user by adjusting the collection timing based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the collection timing.

[0077] The collection unit can optimize the format of the minutes or the method of acquiring calendar information based on the user's past behavior history. For example, the collection unit automatically selects and collects a format of minutes used by the user in the past. The collection unit can also preferentially acquire information from a calendar app used by the user in the past. Furthermore, the collection unit can also suggest the most efficient information acquisition method from the user's past behavior history. This improves the efficiency of information collection by optimizing the information acquisition method based on the user's past behavior history. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's past behavior history data to the generation AI and cause the generation AI to select the optimal information acquisition method.

[0078] The collection unit can determine the priority of collection based on the contents of the minutes and the importance of the calendar information at the time of collection. For example, the collection unit preferentially collects minutes of important meetings. The collection unit can also preferentially collect calendar information including important events. Furthermore, the collection unit can prioritize collecting information of high importance while leaving information of low importance for later. In this way, important information can be preferentially collected by determining the priority of collection based on the importance of information. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input importance data of the minutes and calendar information to the generation AI and have the generation AI determine the priority of collection.

[0079] The collection unit can estimate the user's emotion and determine the priority of information to be collected based on the estimated user's emotion. For example, when the user is feeling stressed, the collection unit postpones information of low importance. In addition, when the user is relaxed, the collection unit can also collect all information evenly. Furthermore, when the user is in a hurry, the collection unit can also collect information of high importance preferentially. This reduces the burden on the user by determining the priority of information based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and have the generation AI determine the priority of information.

[0080] The collection unit can collect highly relevant information preferentially based on the user's geographical location information at the time of collection. For example, when the user is in a specific location, the collection unit preferentially collects information related to the location. In addition, when the user is moving, the collection unit can also preferentially collect information related to the destination. Furthermore, when the user is at home, the collection unit can also preferentially collect information related to the home. As a result, by preferentially collecting highly relevant information based on the user's geographical location information, the accuracy of information collection is improved. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit inputs the user's geographical location information data to the generation AI and allows the generation AI to select highly relevant information.

[0081] The collection unit can analyze the user's social media activity at the time of collection and collect related information. The collection unit can collect related minutes and calendar information based on information shared by the user on social media, for example. The collection unit can also collect information related to the next meeting from the user's social media activity. Furthermore, the collection unit can also collect information related to topics mentioned by the user on social media. This improves the accuracy of information collection by collecting related information based on the user's social media activity. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or without using AI. For example, the collection unit can input the user's social media activity data to the generation AI and have the generation AI collect related information.

[0082] The analysis unit can estimate the user's emotion and adjust the expression method of the analysis based on the estimated user's emotion. For example, when the user is nervous, the analysis unit provides a simple and highly visible analysis result. In addition, when the user is relaxed, the analysis unit can also provide a detailed analysis result. Furthermore, when the user is in a hurry, the analysis unit can also provide an analysis result that covers the main points. In this way, by adjusting the expression method of the analysis based on the user's emotion, it is possible to provide an analysis result that is easy for the user to understand. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the expression method of the analysis.

[0083] When extracting information from the minutes using natural language processing, the analysis unit can adjust the level of detail of the analysis based on the importance of the contents of the minutes. For example, the analysis unit analyzes the minutes of important meetings in detail. The analysis unit can also analyze the minutes of less important meetings simply. Furthermore, the analysis unit can dynamically adjust the level of detail of the analysis according to the importance. As a result, important information can be analyzed in detail by adjusting the level of detail of the analysis based on the importance of the contents of the minutes. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input importance data of the contents of the minutes to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0084] The analysis unit can apply different analysis algorithms depending on the category of the minutes during analysis. For example, the analysis unit applies an analysis algorithm specialized for technical terms to minutes of a technical meeting. The analysis unit can also apply an analysis algorithm specialized for sales terms to minutes of a sales meeting. Furthermore, the analysis unit can dynamically select an optimal analysis algorithm depending on the category. This improves the accuracy of the analysis by applying different analysis algorithms depending on the category of the minutes. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input category data of the minutes to the generation AI and have the generation AI select the optimal analysis algorithm.

[0085] The analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user's emotion. For example, when the user is in a hurry, the analysis unit provides a short and to the point analysis result. In addition, when the user is relaxed, the analysis unit can also provide a detailed analysis result. Furthermore, when the user is excited, the analysis unit can also provide an analysis result with a visually stimulating effect. In this way, by adjusting the length of the analysis based on the user's emotion, an analysis result of an appropriate length for the user can be provided. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the analysis.

[0086] During analysis, the analysis unit can determine the priority of the analysis based on the submission time of the minutes. For example, the analysis unit prioritizes the analysis of the minutes that were submitted most recently. The analysis unit can also postpone minutes that were submitted earlier. Furthermore, the analysis unit can dynamically adjust the priority of the analysis according to the submission time. In this way, by determining the priority of the analysis based on the submission time of the minutes, it is possible to prioritize the analysis of the latest information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the submission time data of the minutes to the generation AI and have the generation AI determine the priority of the analysis.

[0087] The analysis unit can adjust the order of analysis based on the relevance of the minutes during analysis. For example, the analysis unit prioritizes analysis of minutes of important meetings. The analysis unit can also postpone analysis of minutes with low relevance. Furthermore, the analysis unit can dynamically adjust the order of analysis according to the relevance. As a result, important information can be analyzed with priority by adjusting the order of analysis based on the relevance of the minutes. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input relevance data of the minutes to the generation AI and have the generation AI adjust the order of analysis.

[0088] The adjustment unit can estimate the user's emotion and adjust the schedule adjustment criteria based on the estimated user's emotion. For example, when the user is stressed, the adjustment unit performs flexible schedule adjustment. In addition, when the user is relaxed, the adjustment unit can also perform strict schedule adjustment. Furthermore, when the user is in a hurry, the adjustment unit can quickly adjust the schedule. This allows the schedule adjustment to be appropriate for the user by adjusting the schedule adjustment criteria based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the adjustment unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the adjustment unit can input the user's emotion data to the generation AI and have the generation AI adjust the schedule adjustment criteria.

[0089] When using an algorithm for selecting an appropriate date and time, the adjustment unit can optimize the algorithm by referring to the user's past schedule history. For example, the adjustment unit preferentially selects a date and time that the user has frequently used in the past. The adjustment unit can also predict the optimal date and time from the user's past schedule history. Furthermore, the adjustment unit can dynamically select the optimal date and time based on the user's past schedule history. This improves the accuracy of selecting the optimal date and time by referring to the user's past schedule history. A part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the user's past schedule history data to the generation AI and have the generation AI select the optimal date and time.

[0090] The adjustment unit can customize the adjustment means based on the user's current living situation when adjusting the schedule. For example, when the user is busy, the adjustment unit provides a simplified schedule adjustment means. Also, when the user is relaxed, the adjustment unit can provide a detailed schedule adjustment means. Furthermore, the adjustment unit can dynamically select an optimal schedule adjustment means according to the user's living situation. This allows the user to adjust the schedule optimally by customizing the adjustment means according to the user's living situation. A part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the user's living situation data to the generation AI and have the generation AI customize the adjustment means.

[0091] The adjustment unit can estimate the user's emotions and determine the priority of schedule adjustments based on the estimated user's emotions. For example, when the user is feeling stressed, the adjustment unit postpones schedule adjustments with low importance. In addition, when the user is relaxed, the adjustment unit can also perform all schedule adjustments equally. Furthermore, when the user is in a hurry, the adjustment unit can also prioritize schedule adjustments with high importance. In this way, the priority of schedule adjustments is determined based on the user's emotions, thereby reducing the burden on the user. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the adjustment unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the adjustment unit can input the user's emotion data to the generation AI and have the generation AI determine the priority of schedule adjustments.

[0092] The adjustment unit can select an appropriate date and time in consideration of the user's geographical location information when adjusting the schedule. For example, when the user is in a specific location, the adjustment unit preferentially selects a date and time related to that location. In addition, when the user is moving, the adjustment unit can also preferentially select a date and time related to the destination. Furthermore, when the user is at home, the adjustment unit can also preferentially select a date and time related to the home. This improves the accuracy of schedule adjustment by selecting the optimal date and time based on the user's geographical location information. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the user's geographical location information data to the generation AI and cause the generation AI to select the optimal date and time.

[0093] The adjustment unit can analyze the user's social media activity and suggest a means of adjustment when adjusting the schedule. The adjustment unit can suggest a relevant date and time based on, for example, information shared by the user on social media. The adjustment unit can also suggest a date and time related to the next meeting based on the user's social media activity. Furthermore, the adjustment unit can also suggest a date and time related to a topic mentioned by the user on social media. This improves the accuracy of schedule adjustment by suggesting a means of adjustment based on the user's social media activity. A part or all of the above-mentioned processing in the adjustment unit can be performed, for example, using AI or can be performed without using AI. For example, the adjustment unit can input the user's social media activity data to the generation AI and have the generation AI suggest a means of adjustment.

[0094] The generation unit can estimate the user's emotions and adjust the text of the appointment thank-you email based on the estimated user's emotions. For example, when the user is relaxed, the generation unit generates polite and detailed text. When the user is in a hurry, the generation unit can also generate concise text that focuses on the main points. Furthermore, when the user is excited, the generation unit can also generate text with visually stimulating effects. This allows the generation of text appropriate for the user by adjusting the text based on the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the text.

[0095] The generation unit can optimize the use of templates and the customization method based on the user's past email history. For example, the generation unit automatically selects an email template that the user has used in the past and generates text. The generation unit can also generate new text based on the style of text that the user has customized in the past. Furthermore, the generation unit can suggest the most effective text from the user's past email history. This improves the accuracy of text generation by optimizing the template and the customization method based on the user's past email history. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input the user's past email history data into the generation AI and have the generation AI select the optimal template and customization method.

[0096] When using a feedback loop to ensure the quality of a text, the generation unit can optimize the text by referring to the user's past feedback. The generation unit reflects improvements to the text based on, for example, feedback provided by the user in the past. The generation unit can also generate the most effective text from the user's past feedback. Furthermore, the generation unit can also continuously improve the quality of the text using a feedback loop. This improves the quality of the text by optimizing the quality of the text based on the user's past feedback. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input the user's past feedback data into the generation AI and have the generation AI optimize the quality of the text.

[0097] The generation unit can estimate the user's emotion and adjust the length of the text based on the estimated user's emotion. For example, when the user is in a hurry, the generation unit generates a short text that is to the point. In addition, when the user is relaxed, the generation unit can also generate a longer text that includes a detailed explanation. Furthermore, when the user is excited, the generation unit can also generate a text that adds a visually stimulating effect. In this way, by adjusting the length of the text based on the user's emotion, a text of an appropriate length for the user can be generated. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input the user's emotion data to the generation AI and have the generation AI adjust the length of the text.

[0098] The generation unit can determine the priority of the text based on the time of sending the email when generating the text. For example, the generation unit generates and sends important emails with priority. The generation unit can also generate emails with a priority when the time of sending is approaching with priority. Furthermore, the generation unit can dynamically adjust the priority of the text according to the time of sending. This allows important emails to be generated with priority by determining the priority of the text based on the time of sending the email. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input email sending time data to the generation AI and have the generation AI determine the priority of the text.

[0099] The generation unit can adjust the order of the text based on the relevance of the emails when generating the text. For example, the generation unit generates the text of important emails with priority. The generation unit can also postpone the text of emails with low relevance. Furthermore, the generation unit can dynamically adjust the order of the text according to the relevance. This allows important emails to be generated with priority by adjusting the order of the text based on the relevance of the emails. A part or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input email relevance data to the generation AI and have the generation AI adjust the order of the text.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The collection unit can optimize the method of collecting minutes and calendar information based on the user's past behavior history. For example, the collection unit can automatically select and collect the format of minutes used by the user in the past. It can also preferentially acquire information from a calendar app used by the user in the past. Furthermore, it can suggest the most efficient information acquisition method based on the user's past behavior history. This improves the efficiency of information collection by optimizing the information acquisition method based on the user's past behavior history.

[0102] The analysis unit can adjust the level of detail of the analysis based on the importance of the contents of the minutes. For example, minutes of important meetings can be analyzed in detail, and minutes of less important meetings can be analyzed simply. Furthermore, the level of detail of the analysis can be dynamically adjusted according to the importance. This allows important information to be analyzed in detail by adjusting the level of detail of the analysis based on the importance of the contents of the minutes.

[0103] The adjustment unit can select the optimal date and time by referring to the user's past schedule history. For example, the adjustment unit preferentially selects a date and time that the user has frequently used in the past. The adjustment unit can also predict the optimal date and time from the user's past schedule history. Furthermore, the adjustment unit can dynamically select the optimal date and time based on the user's past schedule history. This improves the accuracy of selecting the optimal date and time by referring to the user's past schedule history.

[0104] The generation unit can optimize templates and customization methods based on the user's past email history. For example, it can automatically select an email template that the user has used in the past to generate text. It can also generate new text based on the style of text that the user has customized in the past. It can also suggest the most effective text from the user's past email history. This improves the accuracy of text generation by optimizing templates and customization methods based on the user's past email history.

[0105] When using the feedback loop to ensure the quality of the text, the generation unit can optimize the text by referring to the user's past feedback. For example, the generation unit reflects improvements to the text based on feedback provided by the user in the past. The generation unit can also generate the most effective text from the user's past feedback. Furthermore, the feedback loop can be used to continuously improve the quality of the text. This improves the quality of the text by optimizing the quality of the text based on the user's past feedback.

[0106] The collection unit can estimate the user's emotions and adjust the timing of collection of minutes and calendar information based on the estimated user's emotions. For example, if the user is feeling stressed, the collection timing can be delayed to collect information when the user is in a relaxed state. Also, if the user is relaxed, information can be collected immediately and analysis can be started quickly. Furthermore, if the user is in a hurry, the collection timing can be advanced to quickly proceed to the next step. In this way, the burden on the user is reduced by adjusting the collection timing based on the user's emotions.

[0107] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user's emotions. For example, if the user is nervous, a simple and highly visible analysis result can be provided. If the user is relaxed, a detailed analysis result can be provided. Furthermore, if the user is in a hurry, an analysis result that focuses on the main points can be provided. In this way, by adjusting the way the analysis is presented based on the user's emotions, it is possible to provide an analysis result that is easy for the user to understand.

[0108] The adjustment unit can estimate the user's emotions and adjust the schedule adjustment criteria based on the estimated user's emotions. For example, if the user is stressed, flexible schedule adjustments can be made. Also, if the user is relaxed, strict schedule adjustments can be made. Furthermore, if the user is in a hurry, quick schedule adjustments can be made. In this way, by adjusting the schedule adjustment criteria based on the user's emotions, it becomes possible to make appropriate schedule adjustments for the user.

[0109] The generation unit can estimate the user's emotions and adjust the wording of the appointment thank-you email based on the estimated user's emotions. For example, if the user is relaxed, polite and detailed wording can be generated. If the user is in a hurry, concise wording that gets to the point can be generated. Furthermore, if the user is excited, wording that includes visually stimulating effects can be generated. In this way, by adjusting the wording based on the user's emotions, appropriate wording for the user can be generated.

[0110] The generation unit can estimate the user's emotion and adjust the length of the text based on the estimated user's emotion. For example, if the user is in a hurry, a short text that is to the point can be generated. If the user is relaxed, a longer text that includes a detailed explanation can be generated. Furthermore, if the user is excited, a text that includes a visually stimulating effect can be generated. In this way, by adjusting the length of the text based on the user's emotion, a text of an appropriate length for the user can be generated.

[0111] The process flow of the second embodiment will be briefly described below.

[0112] Step 1: The collection department collects minutes and calendar information. Minutes often contain the details of appointments and the desired date and time of the next meeting, and calendar information contains the schedules of clients and staff. The collection department collects this information and provides it to the analysis department. Step 2: The analysis unit analyzes the information collected by the collection unit. The analysis unit uses natural language processing technology to extract the desired date and time of the next meeting from the minutes, and identifies the free time of the customer and person in charge from the calendar information. Step 3: The coordination department adjusts the schedule for the next meeting based on the analysis results obtained by the analysis department. The coordination department adjusts the schedule using an algorithm that selects the optimal date and time, taking into account the free time of the customer and the person in charge. Step 4: The generation unit generates the text of the appointment thank-you email based on the schedule adjusted by the adjustment unit. The generation unit can generate the text using a template and can also ensure the quality of the text using a feedback loop.

[0113] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0114] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0115] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0116] Each of the multiple elements including the above-mentioned collection unit, analysis unit, adjustment unit, and generation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart device 14, and collects minutes and calendar information. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected information. The adjustment unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the schedule of the next meeting based on the analysis result. The generation unit is realized, for example, by the control unit 46A of the smart device 14, and generates the text of the appointment thank-you email based on the adjusted schedule. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0117] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0118] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0124] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0127] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0129] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0131] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements including the above-mentioned collection unit, analysis unit, adjustment unit, and generation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart glasses 214, and collects minutes and calendar information. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected information. The adjustment unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the schedule of the next meeting based on the analysis result. The generation unit is realized, for example, by the control unit 46A of the smart glasses 214, and generates the text of the appointment thank you email based on the adjusted schedule. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0133] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0134] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0135] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0140] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0143] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0148] Each of the multiple elements including the above-mentioned collection unit, analysis unit, adjustment unit, and generation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the headset type terminal 314, and collects minutes and calendar information. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected information. The adjustment unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the schedule of the next meeting based on the analysis result. The generation unit is realized, for example, by the control unit 46A of the headset type terminal 314, and generates the text of the appointment thank you email based on the adjusted schedule. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0149] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0150] 7, a 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.

[0151] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0153] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0155] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0156] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0157] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0158] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0159] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0160] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0161] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0162] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0163] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0164] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0165] Each of the multiple elements including the above-mentioned collection unit, analysis unit, adjustment unit, and generation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the robot 414, and collects minutes and calendar information. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected information. The adjustment unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the schedule of the next meeting based on the analysis result. The generation unit is realized, for example, by the control unit 46A of the robot 414, and generates the text of the appointment thank-you email based on the adjusted schedule. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0166] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0167] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0168] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0169] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0170] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0171] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0174] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0175] In addition, 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 upon request from the data processing device 12.

[0176] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0177] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0178] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0179] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0180] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0181] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0182] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0183] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0184] (Appendix 1) a collection unit for collecting meeting minutes or calendar information; an analysis unit that analyzes the information collected by the collection unit; A coordination unit that adjusts the date of the next meeting based on the analysis result obtained by the analysis unit; A generation unit generates a message for an appointment thank-you email based on the schedule adjusted by the adjustment unit. A system characterized by: (Appendix 2) The collecting unit includes: Specify the format of the minutes or how to obtain calendar information 2. The system of claim 1, (Appendix 3) The analysis unit is Extracting information from meeting minutes using natural language processing 2. The system of claim 1, (Appendix 4) The adjustment unit is Use an algorithm to select the appropriate date and time 2. The system of claim 1, (Appendix 5) The generation unit is Includes instructions on how to use or customize the template 2. The system of claim 1, (Appendix 6) The generation unit is Use feedback loops to ensure quality of writing 2. The system of claim 1, (Appendix 7) The collecting unit includes: Handling data from a security or privacy perspective 2. The system of claim 1, (Appendix 8) The collecting unit includes: To estimate a user's emotion and adjust the timing of collection of meeting minutes and calendar information based on the estimated user's emotion. 2. The system of claim 1, (Appendix 9) The collecting unit includes: Optimize the format of meeting minutes or how calendar information is captured based on the user's past actions 2. The system of claim 1, (Appendix 10) The collecting unit includes: When collecting, prioritize collection based on the importance of the minutes content and calendar information. 2. The system of claim 1, (Appendix 11) The collecting unit includes: Estimate user emotions and prioritize information to be collected based on the estimated user emotions. 2. The system of claim 1, (Appendix 12) The collecting unit includes: At the time of collection, prioritize collection of information that is more relevant based on the user's geographic location 2. The system of claim 1, (Appendix 13) The collecting unit includes: At the time of collection, we analyze your social media activity and collect related information. 2. The system of claim 1, (Appendix 14) The analysis unit is Infer user emotions and adjust the presentation of analytics based on the inferred user emotions 2. The system of claim 1, (Appendix 15) The analysis unit is When extracting information from minutes using natural language processing, the level of analysis detail is adjusted based on the importance of the contents of the minutes. 2. The system of claim 1, (Appendix 16) The analysis unit is During parsing, apply different parsing algorithms depending on the category of the minutes. 2. The system of claim 1, (Appendix 17) The analysis unit is Infer user sentiment and adjust the length of the analysis based on the inferred user sentiment 2. The system of claim 1, (Appendix 18) The analysis unit is During analysis, prioritize analysis based on when minutes were submitted. 2. The system of claim 1, (Appendix 19) The analysis unit is During parsing, adjust the order of parsing based on the relevance of the minutes 2. The system of claim 1, (Appendix 20) The adjustment unit is To estimate a user's emotion and adjust a schedule adjustment criterion based on the estimated user's emotion. 2. The system of claim 1, (Appendix 21) The adjustment unit is When using an algorithm to select the appropriate date and time, the system optimizes by referring to the user's past schedule history. 2. The system of claim 1, (Appendix 22) The adjustment unit is Customize scheduling based on the user's current life situation 2. The system of claim 1, (Appendix 23) The adjustment unit is To estimate a user's emotions and determine the priority of schedule adjustments based on the estimated user's emotions 2. The system of claim 1, (Appendix 24) The adjustment unit is When scheduling, select an appropriate date and time by taking into account the user's geographic location information 2. The system of claim 1, (Appendix 25) The adjustment unit is Analyze users' social media activity to suggest adjustments when scheduling 2. The system of claim 1, (Appendix 26) The generation unit is Infer the user's emotions and adjust the wording of the appointment thank-you email based on the estimated user emotions 2. The system of claim 1, (Appendix 27) The generation unit is Optimize how templates are used and customized based on a user's past email history 2. The system of claim 1, (Appendix 28) The generation unit is Use feedback loops to ensure quality and optimize content based on past user feedback 2. The system of claim 1, (Appendix 29) The generation unit is The system estimates the user's emotions and adjusts the length of the text based on the estimated user emotions. 2. The system of claim 1, (Appendix 30) The generation unit is During message generation, messages are prioritized based on when the email is sent 2. The system of claim 1, (Appendix 31) The generation unit is During message generation, adjust the order of messages based on the relevance of the email 2. The system of claim 1, [Explanation of symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit for collecting meeting minutes or calendar information; an analysis unit that analyzes the information collected by the collection unit; A coordination unit that adjusts the date of the next meeting based on the analysis result obtained by the analysis unit; A generation unit generates a message for an appointment thank-you email based on the schedule adjusted by the adjustment unit. A system characterized by:

2. The collecting unit includes: Specify the format of the minutes or how to obtain calendar information 2. The system of claim 1 .

3. The analysis unit is Extracting information from meeting minutes using natural language processing 2. The system of claim 1 .

4. The adjustment unit is Use an algorithm to select the appropriate date and time 2. The system of claim 1 .

5. The generation unit is Includes instructions on how to use or customize the template 2. The system of claim 1 .

6. The generation unit is Use feedback loops to ensure quality of writing 2. The system of claim 1 .

7. The collecting unit includes: Handling data from a security or privacy perspective 2. The system of claim 1 .

8. The collecting unit includes: To estimate a user's emotion and adjust the timing of collection of meeting minutes and calendar information based on the estimated user's emotion.

2. The system of claim 1 .

Images