System

Abstract

To provide a system.SOLUTION: A system includes: first means for collecting the agenda of a meeting and the opinions of participants of the meeting; second means for acquiring the results of the past meetings from a database; third means for generating a prompt text for outputting the optimum conclusion of the meeting on the basis of the agenda of the meeting, the opinions of the participants, and the results of the past meetings; fourth means for generating the optimum conclusion of the meeting by inputting the generated prompt text into a generative AI model; and fifth means for transmitting the generated optimum conclusion of the meeting to a terminal of the user.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] In traditional organizations, the number of meetings and the need to align views within the organization were problems. These problems made it difficult to reduce the time and number of meetings. [Means for solving the problem]

[0005] The present invention provides a means for preparing meeting conclusions in advance, a means for shortening meeting times, and a means for reducing the number of meetings. Furthermore, it has a function for predicting the optimal conclusion at that point in time from an objective point of view. This allows for a large number of shared understandings within an organization, and realizes more efficient meetings. [Brief description of the drawings]

[0006] [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. [Figure 11] FIG. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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 (registered trademark)).

[0010] 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.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] 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), Bluetooth (registered trademark), etc.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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 wide area network (WAN) and / or a local area network (LAN).

[0018] 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.

[0019] 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 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] 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.

[0022] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The system of the present invention is provided with a means for preparing a meeting conclusion in advance, a means for shortening the meeting time, and a means for reducing the number of meetings themselves. Specifically, as a means for preparing a meeting conclusion in advance, the system has a function for collecting meeting agendas and participant opinions and automatically generating a conclusion based on them. In addition, as a means for shortening meeting time, the system has a scheduling function and agenda management function for making the meeting progress more efficient. Furthermore, as a means for reducing the number of meetings themselves, the system has an optimization function for scheduling only necessary meetings.

[0029] "Example 2"

[0030] As a function that can predict the optimal conclusion at that time from an objective point of view, it has the function of analyzing the meeting agenda, the opinions of participants, the results of past meetings, etc., and predicting the optimal conclusion based on the results. A specific example would be a function that uses AI technology to analyze the meeting agenda and the opinions of participants, and automatically generates the optimal conclusion based on the results.

[0031] The process flow of each embodiment will be described below.

[0032] "Example 1"

[0033] Step 1: Collect the meeting agenda and participants' opinions. This will be the basis for formulating the meeting conclusions in advance.

[0034] Step 2: Automatically generate meeting conclusions based on the collected agenda and opinions, which can shorten the meeting time.

[0035] Step 3: Use scheduling and agenda management features to streamline the meeting, further shortening the meeting time.

[0036] Step 4: Use optimization features to schedule only the meetings you need, which can reduce the number of meetings you have.

[0037] "Example 2"

[0038] Step 1: Collect meeting agendas, participant opinions, past meeting results, etc. This will provide the basic data to objectively estimate the optimal conclusion at that time.

[0039] Step 2: Analyze the collected data using AI technology. This analysis will predict the optimal conclusion at that point in time.

[0040] Step 3: Based on the inferred conclusion, the conclusion of the meeting is automatically generated, which makes it possible to shorten the meeting time and reduce the number of meetings.

[0041] Example 1

[0042] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal".

[0043] In the modern business environment, meetings are important places for decision-making, but they often take too long, have vague conclusions, or are unnecessary. This reduces work efficiency and wastes resources. Therefore, there is a need for a system that can quickly and accurately make meeting conclusions, shorten meeting times, and reduce unnecessary meetings.

[0044] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0045] In this invention, the server includes a means for collecting meeting agendas and participant opinions and automatically generating a conclusion based on them, a means having a scheduling function and an agenda management function for making the meeting proceed efficiently, and a means having an optimization function for scheduling only necessary meetings. This makes it possible to quickly and accurately create a meeting conclusion, shorten the meeting time, and reduce unnecessary meetings.

[0046] A "meeting agenda" is the specific themes or topics to be discussed at a meeting.

[0047] "Participant input" refers to ideas, suggestions, and feedback provided by members attending the meeting.

[0048] "Means for automatically generating conclusions" refers to a function that uses artificial intelligence and algorithms to automatically create optimal conclusions based on collected topics and opinions.

[0049] The "scheduling function" refers to the function that optimizes meeting dates and times and participant schedules to set up meetings efficiently.

[0050] The "agenda management function" refers to the function of organizing the topics to be discussed in a meeting and managing the progress.

[0051] "Optimization function" refers to a function for evaluating the necessity of meetings and reducing duplicate or unnecessary meetings.

[0052] A "function that can make inferences from an objective perspective" is a function that uses data and algorithms to derive optimal conclusions without relying on subjectivity.

[0053] The present invention is a system for optimizing the efficiency of a conference, and is realized by a server, a terminal, and a user each fulfilling their respective roles. A specific embodiment of this system will be described below.

[0054] 1. A way to prepare meeting conclusions in advance

[0055] The server uses Google (registered trademark) Calendar API and Microsoft (registered trademark) Outlook (registered trademark) API to collect meeting agendas and participant opinions. This allows the server to obtain the agenda for the next meeting. The server also collects participant opinions from communication tools such as Slack (registered trademark) and MICROSOFT TEAMS (registered trademark).

[0056] Examples:

[0057] The server calls the Google Calendar API to get the agenda for the next meeting.

[0058] The server uses the Slack API to collect participant opinions from the meeting channel.

[0059] Based on the collected data, the server inputs prompts into a generative AI model (e.g., OpenAI's GPT-4) that generates a conclusion based on the input agenda and opinions.

[0060] Examples:

[0061] Prompt: The topic of the meeting is "Marketing strategy for a new product," and the opinions of the participants are "We should strengthen social media advertising," "We should also consider TV commercials," and "We have a limited budget, so we should choose an efficient method." Please generate a conclusion based on these.

[0062] The generated conclusions are stored in a database by the server and made accessible to the user.

[0063] 2. Ways to shorten meeting times

[0064] The server optimizes meeting schedules using Google Calendar API and Microsoft Outlook API to streamline meeting progress, and manages agendas using task management tools such as Trello (registered trademark) and Asana (registered trademark).

[0065] Examples:

[0066] The server calls the Google Calendar API to get the upcoming meeting schedule.

[0067] The server proposes an optimal schedule taking into account the free time of the participants.

[0068] The server calls the Trello API and creates the meeting agenda as a card.

[0069] The server provides real-time updates on the progress of the agenda.

[0070] 3. Ways to reduce the number of meetings

[0071] The server retrieves and analyzes existing meeting schedules using Google Calendar API and Microsoft Outlook API, detects duplicates and unnecessary meetings, and uses a generative AI model to evaluate the necessity of meetings and propose optimal schedules.

[0072] Examples:

[0073] The server calls the Google Calendar API to get the meeting schedule for the next week.

[0074] The server inputs prompt sentences into the generative AI model to assess the need for a meeting.

[0075] Prompt: Please optimize your meeting schedule for the next week. The current schedule is as follows: Monday: Meeting A, Tuesday: Meeting B, Wednesday: Meeting C. Please reduce overlapping and unnecessary meetings.

[0076] The generative AI model generates suggestions for reducing unnecessary meetings, and the server updates the schedule based on the suggestions.

[0077] This system makes it possible to quickly and accurately draw up meeting conclusions, shorten meeting times, and reduce unnecessary meetings.

[0078] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0079] Step 1:

[0080] The server calls the Google Calendar API or Microsoft Outlook API to get the meeting agenda. As input, it provides the schedule information of the upcoming meeting. The server saves the agenda information obtained from the API in a database.

[0081] Specific behavior:

[0082] The server calls the Google Calendar API to get the agenda for the next meeting.

[0083] The obtained agenda information is stored in a database.

[0084] Step 2:

[0085] The server uses APIs of Slack and Microsoft Teams (registered trademark) to collect participants' opinions. As input, the server provides the channel information of the meeting. The server stores the opinion information obtained from the API in a database.

[0086] Specific behavior:

[0087] The server uses the Slack API to collect participant opinions from the meeting channel.

[0088] The obtained opinion information is stored in a database.

[0089] Step 3:

[0090] The server inputs the collected topics and opinions into the generative AI model. As input, it provides text data of the topics and opinions. The generative AI model generates a conclusion based on the input data and outputs it to the server.

[0091] Specific behavior:

[0092] The server converts the agenda and opinions into text format and inputs them as prompts to the generative AI model.

[0093] The generative AI model analyzes the prompt and generates an optimal conclusion.

[0094] The server receives the generated conclusions and stores them in a database.

[0095] Step 4:

[0096] The server uses Google Calendar API and Microsoft Outlook API to optimize meeting schedules. As input, you provide the schedule information of the participants. The server calculates the optimal schedule and proposes it as output.

[0097] Specific behavior:

[0098] The server calls the Google Calendar API to obtain the participants' schedule information.

[0099] Based on the acquired schedule information, the optimal meeting schedule is calculated.

[0100] The server proposes an optimal schedule and stores it in a database.

[0101] Step 5:

[0102] The server uses Trello or Asana API to manage the agenda. As input, we provide the meeting agenda information. The server creates the agenda as cards and manages the progress.

[0103] Specific behavior:

[0104] The server calls the Trello API and creates the meeting agenda as a card.

[0105] The server provides real-time updates on the progress of the agenda.

[0106] Step 6:

[0107] The server uses Google Calendar API and Microsoft Outlook API to analyze the existing meeting schedule. As input, you provide the meeting schedule information for the next week. The server detects overlapping and unnecessary meetings and suggests an optimized schedule as output.

[0108] Specific behavior:

[0109] The server calls the Google Calendar API to get the meeting schedule for the next week.

[0110] The server analyzes the schedule to detect overlapping and unnecessary meetings.

[0111] The server inputs prompt sentences into the generative AI model to assess the need for a meeting.

[0112] A generative AI model generates suggestions to cut down on unnecessary meetings.

[0113] The server updates the schedule based on the suggestions.

[0114] (Application example 1)

[0115] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0116] Meetings and discussions in factories are important for improving productivity, but they often take too much time and there are many pointless meetings. It is also difficult to efficiently collect opinions from each department and reach optimal conclusions. To solve these problems, there is a need to streamline and optimize meetings.

[0117] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the time of the meeting, a means for reducing the number of meetings, a means for collecting agendas and opinions from each department in the factory and automatically generating a conclusion using a generative AI model, a means for optimizing the meeting schedule and efficiently managing the agenda, and a means for scheduling only necessary meetings and reducing unnecessary meetings. This makes it possible to make meetings and discussions in the factory more efficient and improve productivity.

[0118] "A means of preparing meeting conclusions in advance" is a function that collects meeting agendas and participants' opinions, and automatically generates conclusions based on them.

[0119] "Means of shortening meeting times" refer to scheduling and agenda management functions to make meetings more efficient.

[0120] "A means to reduce the number of meetings" refers to an optimization function that schedules only necessary meetings.

[0121] "A function that can predict the optimal conclusion at any given time from an objective perspective" is a function that automatically derives the optimal conclusion based on collected information.

[0122] "Means of collecting topics and opinions from each department within the factory" refers to a function that visits each department within the factory and collects opinions using voice recognition technology.

[0123] "Means for automatically generating a conclusion using a generative AI model" refers to a function that automatically generates a conclusion using a generative AI model based on collected topics and opinions.

[0124] "Means for optimizing meeting schedules and efficiently managing agendas" refers to a function for optimizing meeting schedules and efficiently managing agendas using scheduling software.

[0125] "A means of scheduling only necessary meetings and reducing unnecessary meetings" is a function that uses AI to evaluate the necessity of meetings and reduce unnecessary meetings.

[0126] The system for carrying out the present invention is a tool for making meetings and conferences in a factory more efficient and improving productivity. A specific embodiment of this system will be described below.

[0127] Hardware and Software Used

[0128] Hardware: Factory robots, servers, network equipment

[0129] Software: Generative AI models (e.g., OpenAI GPT-4), database management systems (e.g., MySQL), scheduling software (e.g., Google Calendar API)

[0130] Data processing and calculation

[0131] Agenda collection

[0132] The factory robot travels around each department in the factory and collects opinions using voice recognition technology. The collected data is sent to a server and stored in a database. This allows opinions from each department to be efficiently collected.

[0133] Automatic conclusion generation

[0134] The server automatically generates conclusions using a generative AI model (e.g. GPT-4) based on the collected agenda and opinions. The generated conclusions are stored in a database and notified to each department as necessary. This allows the conclusions of meetings to be generated quickly.

[0135] Scheduling and Agenda Management

[0136] The server optimizes the meeting schedule using scheduling software (e.g., Google Calendar API). It also efficiently manages the agenda for each meeting using the agenda management function, allowing the meetings to proceed smoothly.

[0137] Optimizing the number of meetings

[0138] The server uses AI to evaluate the necessity of meetings and schedules only the necessary meetings, thus reducing unnecessary meetings.

[0139] Examples

[0140] For example, if a meeting is held within a factory to introduce a new product line, the process may look like this:

[0141] 1. Gather input from each department about the new product line.

[0142] 2. Based on the collected opinions, the generative AI model automatically generates a conclusion.

[0143] 3. Use scheduling software to schedule the best possible meeting.

[0144] 4. Schedule only the meetings you need and cut down on the unnecessary ones.

[0145] Examples of prompt statements

[0146] Here is an example of a prompt to be input to the generative AI model:

[0147] You have collected opinions regarding the introduction of a new product line. Generate a conclusion based on the opinions below.

[0148] Opinion 1: We should install new machines to improve the efficiency of our production line.

[0149] Opinion 2: It is better to improve the existing machine to reduce costs.

[0150] Statement 3: The introduction of a new product line requires employee training.

[0151] Use these opinions to generate the best conclusion.

[0152] In this way, factory meetings can be made more efficient and productivity can be improved.

[0153] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0154] Step 1:

[0155] The factory robot travels around each department in the factory and collects opinions using voice recognition technology. The input is the voice opinions from the staff in each department, and the output is the opinion data in text format. The robot uses voice recognition software to convert the voice into text and sends it to the server.

[0156] Step 2:

[0157] The server stores the opinion data sent from the robot in a database. The input is the opinion data in text format, and the output is the opinion data stored in the database. The server stores the data using a database management system (e.g., MySQL).

[0158] Step 3:

[0159] The server automatically generates a conclusion using a generative AI model (e.g. GPT-4) based on the opinion data stored in the database. The input is the opinion data obtained from the database, and the output is the generated conclusion. The server inputs a prompt sentence into the generative AI model to generate a conclusion.

[0160] Step 4:

[0161] The server stores the generated conclusions in a database and notifies each department as necessary. The input is the generated conclusion, and the output is the conclusion stored in the database and the notified conclusion. The server sends the conclusions to each department using a notification system.

[0162] Step 5:

[0163] The server optimizes the meeting schedule using scheduling software (e.g. Google Calendar API). The input is the meeting agenda and attendee information, and the output is the optimized meeting schedule. The server uses the scheduling software to set the schedule.

[0164] Step 6:

[0165] The server efficiently manages the agenda of each meeting through the agenda management function. The input is the meeting agenda information, and the output is the managed agenda information. The server manages the agenda using the agenda management software.

[0166] Step 7:

[0167] The server uses AI to assess the need for meetings and schedule only those that are necessary. The input is meeting agenda and participant information, and the output is an optimized meeting schedule. The server uses AI models to assess the need for meetings and reduce unnecessary meetings.

[0168] Example 2

[0169] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0170] In conventional conference systems, it was difficult to prepare a meeting's conclusion in advance, and meetings often dragged on. In addition, as the number of meetings increased, the burden on participants increased, making efficient decision-making difficult. Furthermore, there was a demand for a system that could objectively analyze meeting topics and participants' opinions to arrive at optimal conclusions.

[0171] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0172] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a means for collecting, preprocessing, and analyzing meeting agendas, participants' opinions, and results of past meetings, a means for predicting an optimal conclusion using a generative AI model, and a means for outputting the predicted conclusion, thereby making it possible to improve the efficiency of meetings and derive optimal conclusions.

[0173] A "means for preparing a meeting conclusion in advance" is a method or device for preparing a conclusion based on existing information before the meeting begins.

[0174] A "means for shortening the duration of a meeting" is a method or device for making the meeting proceed more efficiently and shortening the time required for the meeting.

[0175] A "means for realizing a reduction in the number of meetings" is a method or device for reducing the number of necessary meetings and reducing the overall number of meetings.

[0176] A "means for collecting meeting agendas, participant opinions, and results of past meetings" is a method or device for collecting information related to meetings.

[0177] A "preprocessing means" is a method or device for preparing collected data in a form that is easy to analyze.

[0178] An "analyzing means" is a method or device for analyzing the pre-processed data and extracting significant information.

[0179] A "means for inferring optimal conclusions using a generative AI model" is a method or device for using artificial intelligence technology to derive optimal conclusions from collected and analyzed data.

[0180] A "means for outputting an inferred conclusion" is a method or device for providing a user with the conclusion inferred by the generative AI model.

[0181] The present invention is directed to a system for improving the efficiency of a meeting and deriving an optimal conclusion. A specific embodiment of this system will be described below.

[0182] The server generates programs to collect, preprocess, and analyze meeting agendas, participant opinions, and past meeting results. The programs use natural language processing libraries (e.g., NLTK, spaCy) and generative AI models (e.g., GPT-4) to process and compute the data.

[0183] First, the server connects to a database and collects meeting agendas, participant opinions, and results of past meetings. For example, it obtains the minutes and participant opinions of a meeting on "New Product Launch Strategy."

[0184] The server then pre-processes the collected data, which involves cleaning the text data, tokenizing it, removing stop words, etc., making the data easier to analyze.

[0185] The server then feeds the pre-processed data into a generative AI model to extract key keywords and themes, such as "market research," "competitive analysis," and "marketing strategy."

[0186] Next, the server uses the generative AI model to predict the optimal conclusion based on the analysis results, taking into account the results of past meetings and the opinions of the participants. For example, the generative AI model is given a prompt such as, "Please predict the optimal conclusion regarding the market launch strategy for a new product."

[0187] Finally, the server outputs the inferred conclusion to the terminal. The user can confirm this conclusion through the terminal. For example, the conclusion "Strengthen market research and develop a marketing strategy based on competitive analysis" is confirmed on the screen of the terminal.

[0188] As a concrete example, consider a case where a user holds a meeting and sets the topic as "New product launch strategy." Participants express their opinions and note that similar topics have been discussed in past meetings. In this case, the server inputs the following prompt sentence into the generative AI model:

[0189] Example prompt:

[0190] "Based on the agenda and participants' opinions of a meeting about a new product launch strategy, infer the best outcome. Also take into account the results of previous meetings."

[0191] By inputting this prompt into a generative AI model, the server can infer the optimal conclusion and provide it to the user.

[0192] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0193] Step 1: Data collection

[0194] The server collects meeting agendas, participant opinions, and past meeting results by connecting to a database and retrieving relevant meeting minutes and speech records.

[0195] Input: meeting agendas, participant comments, results of past meetings

[0196] Output: Raw data collected

[0197] What happens: The server uses an SQL query to retrieve meeting minutes and participant opinions on "New Product Launch Strategy" from the database.

[0198] Step 2: Data Preprocessing

[0199] The server pre-processes the collected data, specifically cleaning the text data, tokenizing it, removing stop words, etc.

[0200] Input: Raw data collected

[0201] Output: Preprocessed data

[0202] Specific operation: The server removes unnecessary symbols and spaces from the acquired text data, tokenizes it, and removes stop words. This is done using a natural language processing library (e.g. NLTK, spaCy).

[0203] Step 3: Data analysis

[0204] The server feeds the pre-processed data into a generative AI model to extract key keywords and themes.

[0205] Input: Preprocessed data

[0206] Output: Extracted keywords and themes

[0207] How it works: The server inputs the preprocessed text data into a generative AI model (e.g., GPT-4) and extracts important keywords such as "market research," "competitive analysis," and "marketing strategy."

[0208] Step 4: Inferring conclusions

[0209] The server uses a generative AI model to infer the optimal conclusion based on the analysis results.

[0210] Input: Extracted keywords or themes

[0211] Output: Inferred conclusion

[0212] Specific operation: Based on the extracted keywords and themes, the server inputs a prompt to the generative AI model: "Please predict the optimal conclusion regarding the new product's market launch strategy." The generative AI model considers the results of past meetings and the opinions of participants and generates the conclusion: "Strengthen market research and develop a marketing strategy based on competitive analysis."

[0213] Step 5: Output the results

[0214] The server outputs the inferred conclusion to the terminal, where the user can confirm the conclusion.

[0215] Input: Inferred conclusion

[0216] Output: conclusions provided to the user

[0217] Specific operation: The server transmits the generated conclusion to the terminal, and the user confirms the conclusion "strengthen market research and develop a marketing strategy based on competitive analysis" on the terminal screen.

[0218] (Application example 2)

[0219] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0220] In conventional conference systems, it was difficult to prepare the conclusion of a meeting in advance, which resulted in long meeting times and an increase in the number of meetings. In addition, it was difficult to objectively predict the optimal conclusion, which meant that it took a lot of time and effort to align the understanding within the organization.

[0221] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0222] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for acquiring the results of past meetings from a database, a means for automatically generating an optimal conclusion using a generative AI model, and a means for outputting the generated conclusion. This makes it possible to improve the efficiency of meetings and automatically generate optimal conclusions.

[0223] The "means for creating a meeting conclusion in advance" is a function for automatically generating a conclusion based on the agenda before the meeting begins.

[0224] "Means of shortening meeting times" refers to functions that make meetings more efficient and shorten the amount of time required.

[0225] "Means for reducing the number of meetings" refers to a function for evaluating the necessity of meetings and reducing unnecessary meetings.

[0226] "A function that can predict the optimal conclusion at that time from an objective perspective" is a function that automatically predicts the most appropriate conclusion based on data collected while the meeting is in progress.

[0227] The "means for acquiring the results of past meetings from a database" is a function for searching and acquiring the results of meetings that were previously held from a database.

[0228] "Means for automatically generating optimal conclusions using a generative AI model" refers to a function that uses artificial intelligence technology to automatically generate optimal conclusions based on collected data.

[0229] The "means for outputting the generated conclusion" is a function for displaying the generated conclusion to the user.

[0230] In the system for carrying out the present invention, a server, a terminal, and a user work in cooperation with each other. The server includes a means for preparing a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for acquiring the results of past meetings from a database, a means for automatically generating an optimal conclusion using a generative AI model, and a means for outputting the generated conclusion.

[0231] The server first collects the meeting agenda and the opinions of the participants. This includes the function of collecting information entered by users in real time using terminals (such as smartphones and tablets). Next, the server retrieves the results of past meetings from a database and automatically generates optimal conclusions based on this data using a generative AI model.

[0232] The generative AI model uses advanced natural language processing technology such as OpenAI's GPT-3 (registered trademark). The server inputs the collected agenda, opinions, and past results as prompt sentences into the generative AI model to generate the optimal conclusion. The generated conclusion is displayed to the user through the terminal.

[0233] As a concrete example, the following prompt sentence is input to the generative AI model:

[0234] Agenda: Improving production line efficiency

[0235] opinion:

[0236] Person A: We should get new machines.

[0237] Person B: We should review our work procedures.

[0238] Person C: Working hours should be adjusted.

[0239] Past results:

[0240] Reconfiguring production lines increases efficiency by 10%

[0241] New software implementation reduces error rate by 5%

[0242] Generate the best conclusion.

[0243] Based on this prompt, the generative AI model outputs the optimal conclusion, such as "Production efficiency can be further improved by combining the introduction of new machinery with a review of work procedures."

[0244] This system makes it possible to streamline meetings and automatically generate optimal conclusions, and can handle the many different views within an organization. The hardware used includes mobile devices such as smartphones and tablets, and the software uses Python (registered trademark), SQLite (registered trademark), and OpenAI API.

[0245] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0246] Step 1:

[0247] The server collects the meeting agenda and the opinions of the participants. The user inputs the meeting agenda and their opinions using a terminal (such as a smartphone or tablet). The input data is sent to the server and stored in a database. In this way, the meeting agenda and the opinions of the participants are collected.

[0248] Step 2:

[0249] The server retrieves the results of past conferences from the database. The server queries the database to search for the results of past conferences. The retrieved data is temporarily stored in the server. In this way, the results of past conferences are retrieved.

[0250] Step 3:

[0251] The server generates prompt sentences based on the collected topics, opinions, and past results. The server converts the collected data into text format and creates prompt sentences to input to the generative AI model. This generates prompt sentences to input to the generative AI model.

[0252] Step 4:

[0253] The server automatically generates an optimal conclusion using a generative AI model. The server inputs the generated prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) and generates an optimal conclusion. The generative AI model performs data calculations based on the input prompt sentence and outputs an optimal conclusion. In this way, the optimal conclusion is automatically generated.

[0254] Step 5:

[0255] The server transmits the generated conclusion to the terminal and displays it to the user. The server transmits the generated conclusion to the terminal and allows the user to view it. The user can check the generated conclusion through the terminal. Thus, the generated conclusion is displayed to the user.

[0256] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0257] "Example 1"

[0258] One embodiment of the present invention is a system that combines an emotion engine that recognizes the emotions of a user. This system includes a means for creating a meeting conclusion in advance, a means for shortening the time of the meeting, a means for reducing the number of meetings, and a function for predicting the optimal conclusion at that time from an objective point of view. The emotion engine recognizes the user's emotions, and controls the means for creating a meeting conclusion in advance based on the emotions. Specifically, if the user's emotions are positive, a meeting conclusion is created in advance in a positive direction. Conversely, if the user's emotions are negative, a meeting conclusion is created in advance in a cautious direction.

[0259] "Example 2"

[0260] The emotion engine also controls a function that recognizes the user's emotions and predicts the optimal conclusion at that time from an objective point of view based on those emotions. Specifically, if the user's emotions are positive, the optimal conclusion at that time is predicted to be in the positive direction. Conversely, if the user's emotions are negative, the optimal conclusion at that time is predicted to be in the cautious direction. In this way, by taking the user's emotions into consideration, it becomes possible to create a more appropriate meeting conclusion in advance and predict the optimal conclusion at that time.

[0261] The process flow of each embodiment will be described below.

[0262] "Example 1"

[0263] Step 1: A user starts a conference.

[0264] Step 2: The emotion engine recognizes the user's emotion.

[0265] Step 3: Pre-create a meeting conclusion based on the emotions recognized by the emotion engine.

[0266] Step 4: Present the pre-created conclusions to the user.

[0267] Step 5: The user reviews the proposed conclusions and modifies them if necessary.

[0268] "Example 2"

[0269] Step 1: A user starts a conference.

[0270] Step 2: The emotion engine recognizes the user's emotion.

[0271] Step 3: Based on the emotions identified by the emotion engine, an objective guess is made as to the best outcome at that point in time.

[0272] Step 4: Present the best guess to the user.

[0273] Step 5: The user reviews the proposed conclusions and modifies them if necessary.

[0274] Example 1

[0275] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal".

[0276] In conventional conference systems, it was difficult to efficiently reach a meeting conclusion, and meetings often dragged on. In addition, there was a tendency for the number of meetings to increase, which increased the burden on participants. Furthermore, the conclusions of meetings tended to be subjective and often influenced by the emotions of participants. There is a need to solve these problems and improve the efficiency and optimization of meetings.

[0277] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0278] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a means for recognizing the user's emotions and adjusting the meeting conclusion based on the emotions, and a function for predicting the optimal conclusion at that time from an objective point of view. This makes it possible to efficiently create a meeting conclusion, shorten the meeting time, and select only the necessary meetings. In addition, by adjusting the conclusion taking the user's emotions into account, a more objective and appropriate conclusion can be derived.

[0279] "A means of preparing meeting conclusions in advance" refers to a function that collects meeting agendas and participants' opinions, and automatically generates conclusions based on them.

[0280] "Means of shortening meeting times" refers to functions that provide scheduling and agenda management functions to make meetings more efficient.

[0281] "Means of reducing the number of meetings" refers to the ability to provide optimization functions to schedule only necessary meetings.

[0282] "Means for recognizing a user's emotions and adjusting the conclusion of the meeting based on those emotions" refers to a function for analyzing a user's emotions and adjusting the conclusion of the meeting in a positive or cautious direction depending on those emotions.

[0283] "A function that can predict the optimal conclusion at any given time from an objective perspective" refers to a function that automatically predicts the most appropriate conclusion based on collected data and user emotions.

[0284] The present invention relates to a system for improving the efficiency and optimizing a conference. A specific embodiment of the system will be described below.

[0285] A means of preparing meeting conclusions in advance

[0286] The server uses APIs of common communication tools (e.g., communication platforms and messaging applications) to collect meeting agendas and participant opinions. The collected data is stored in a database. The server then uses a generative AI model (e.g., a natural language processing model) to automatically generate a conclusion based on the collected data. Specifically, the server inputs the following prompt sentence into the generative AI model:

[0287] "The topic of the meeting is XX, and the opinions of the participants are △△. Please generate a conclusion based on this."

[0288] The generated conclusions are again stored in the database.

[0289] A way to shorten meeting times

[0290] The server optimizes meeting schedules using scheduling software (e.g., a calendar application) to automatically adjust meeting start and end times, and uses a project management tool (e.g., a task management application) to manage agendas by creating tasks for each agenda item and tracking their progress.

[0291] A means to reduce the number of meetings

[0292] The server uses machine learning algorithms to analyze past meeting data and select only necessary meetings. Specifically, it uses a Python machine learning library to build a model that evaluates the importance of meetings. This model evaluates the necessity of meetings and schedules only high-importance meetings.

[0293] A means of recognizing a user's emotions and adjusting the outcome of a meeting based on those emotions

[0294] The terminal uses an emotion analysis engine (e.g., emotion recognition API) to recognize the user's emotions. The terminal analyzes the user's speech and facial expressions to obtain emotion data. The obtained emotion data is sent to the server. The server adjusts the conclusion based on the emotion data. For example, if the user's emotion is positive, the server corrects the conclusion in a positive direction. Conversely, if the user's emotion is negative, the server corrects the conclusion in a cautious direction.

[0295] Examples

[0296] For example, if the topic of a meeting is "New product launch strategy" and the participants' opinions are "We should conduct an aggressive marketing campaign," we can input the following prompt into the generative AI model:

[0297] "The topic of the meeting should be a new product launch strategy, and the participants' input should be about an aggressive marketing campaign. Use this as a basis for generating conclusions."

[0298] Based on this prompt, the generative AI model generates the conclusion that "it is optimal to conduct an aggressive marketing campaign as a new product launch strategy." If the user's sentiment is positive, the sentiment engine sends this information to the server, which then generates a positive conclusion. For example, it generates the conclusion that "since the user's sentiment is positive, it is recommended to further strengthen the marketing campaign."

[0299] In this way, the system of the present invention realizes efficiency and optimization of meetings.

[0300] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0301] Step 1:

[0302] The server collects the meeting agenda and participant opinions.

[0303] Specifically, the server uses the communication platform's API to obtain the chat log and minutes of the meeting.

[0304] Input: Meeting chat logs, minutes

[0305] Output: Collected topics and opinion data

[0306] Step 2:

[0307] The server stores the collected topics and opinions in a database.

[0308] As a specific operation, the server executes an INSERT query on the database to insert data into the agenda table and the opinion table.

[0309] Input: Collected agenda and opinion data

[0310] Output: Topics and opinions stored in a database

[0311] Step 3:

[0312] The server creates a prompt based on the collected topics and opinions.

[0313] Specifically, the server converts the agenda and opinion data into text format and generates prompt sentences to input into the generative AI model.

[0314] Input: Topics and opinions stored in the database

[0315] Output: Generated prompt statement

[0316] Step 4:

[0317] The server inputs a prompt sentence into the generative AI model and generates a conclusion.

[0318] Specifically, the server calls the API of the generative AI model, inputs a prompt sentence, and generates a conclusion.

[0319] Input: Generated prompt text

[0320] Output: Generated conclusions

[0321] Step 5:

[0322] The server stores the generated conclusions in a database.

[0323] As a specific operation, the server executes an INSERT query on the database to insert data into the conclusion table.

[0324] Input: Generated conclusions

[0325] Output: conclusions stored in a database

[0326] Step 6:

[0327] The server uses scheduling software to optimize the schedule of meetings.

[0328] Specifically, the server uses the calendar application's API to automatically adjust the start and end times of meetings.

[0329] Input: Meeting schedule information

[0330] Output: Optimized meeting schedule

[0331] Step 7:

[0332] The server uses a project management tool to manage the agenda.

[0333] Specifically, the server uses the API of the task management application to create tasks for each agenda item and track their progress.

[0334] Input:Agenda information

[0335] Output: Managed agenda tasks

[0336] Step 8:

[0337] The server analyzes past conference data and selects only the necessary conferences.

[0338] Specifically, the server uses a machine learning algorithm to build a model that evaluates the importance of meetings and selects only meetings with high importance.

[0339] Input: Past meeting data

[0340] Output: Select the required meeting

[0341] Step 9:

[0342] The terminal uses an emotion analysis engine to recognize the user's emotions.

[0343] Specifically, the device uses an emotion recognition API to analyze the user's statements and facial expressions and obtain emotional data.

[0344] Input: User's speech and facial expressions

[0345] Output: The acquired emotion data

[0346] Step 10:

[0347] The terminal transmits the recognized emotion data to the server.

[0348] Specifically, the device sends a POST request to the server with emotion data in JSON format.

[0349] Input: Acquired emotion data

[0350] Output: Emotion data sent to the server

[0351] Step 11:

[0352] The server adjusts the conclusion based on the emotion data.

[0353] Specifically, the server analyzes the emotion data, and if the user's emotion is positive, the server corrects the conclusion to a positive direction, and if the user's emotion is negative, the server corrects the conclusion to a more cautious direction.

[0354] Input: Emotion data sent to the server

[0355] Output: Adjusted conclusion

[0356] (Application example 1)

[0357] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0358] In conventional conference systems, it was difficult to reach a conclusion in a meeting efficiently, leading to problems such as long meetings and frequent useless meetings. In addition, the quality of the conclusions was often poor because the conclusions were reached without considering the feelings of the participants. Furthermore, production data and maintenance data within the factory could not be effectively utilized, which often led to inefficient progress in meetings.

[0359] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0360] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view using an emotion engine that recognizes the user's emotions, a means for collecting production data and maintenance data in the factory and automatically generating the optimal conclusion using AI, a means for providing a scheduling function and an agenda management function for streamlining the progress of the meeting, and a means for having an optimization function for scheduling only necessary meetings. This makes it possible to efficiently derive a meeting conclusion, shorten the meeting time, and reduce unnecessary meetings. In addition, the quality of the conclusion can be improved by drawing a conclusion that takes into account the emotions of the participants. Furthermore, the progress of the meeting can be made more efficient by effectively utilizing the production data and maintenance data in the factory.

[0361] The "means for preparing a meeting conclusion in advance" is a function for collecting the meeting agenda and the opinions of the participants, and automatically generating the meeting conclusion based on them.

[0362] "Means of shortening meeting times" refers to functions that provide scheduling and agenda management functions to make meetings more efficient.

[0363] "Means for reducing the number of meetings" refers to a feature that provides an optimization function for scheduling only necessary meetings.

[0364] The "emotion engine that recognizes the user's emotions" is a function that recognizes the user's emotions and controls a means for preparing a meeting conclusion in advance based on the emotions.

[0365] The "means for collecting production data and maintenance data within the factory" is a function for collecting data regarding production activities and maintenance activities within the factory.

[0366] "Means for AI to automatically generate optimal conclusions" refers to a function in which artificial intelligence automatically generates optimal meeting conclusions based on collected data.

[0367] The "scheduling function for making meetings more efficient" is a function for optimizing the meeting schedule and making the meeting proceed efficiently.

[0368] The "agenda management function" is a function for managing the agenda of a meeting and progressing the meeting efficiently.

[0369] The "optimization function" is a function that evaluates the necessity of meetings and generates an optimal schedule in order to schedule only necessary meetings.

[0370] The system for carrying out the present invention has a plurality of functions for preparing a meeting conclusion in advance and realizing shortening the time and number of meetings. A specific embodiment of this system will be described below.

[0371] System Configuration

[0372] The system consists of the following main components:

[0373] 1. Server

[0374] A means for preparing a meeting conclusion in advance: The server has a function for collecting the meeting agenda and the opinions of the participants, and automatically generating the meeting conclusion based on them.

[0375] Means to reduce meeting times: The server provides scheduling and agenda management functions to make meetings more efficient.

[0376] A means to reduce the number of meetings: The server has an optimization function to schedule only necessary meetings.

[0377] Emotion Engine: The server controls the means to recognize the user's emotions and pre-plan the outcome of the meeting based on those emotions.

[0378] Data collection method: The server collects production data and maintenance data within the factory.

[0379] AI conclusion generation method: The server automatically generates the optimal meeting conclusion using artificial intelligence based on the collected data.

[0380] Hardware and software used

[0381] EmotionEngine: An engine for recognizing user emotions. It uses the camera and microphone to collect emotion data.

[0382] Scheduler: Software for scheduling meetings.

[0383] ConclusionGenerator: Software for generating meeting conclusions using AI.

[0384] Data processing and calculation

[0385] 1. Data collection: The server collects production data and maintenance data. For example, it collects data such as "Production line A's operating rate has reached 90%" or "Machine B needs maintenance."

[0386] 2. Emotion Recognition: The server uses the EmotionEngine to recognize participants' emotions from the camera and microphone. For example, it collects data such as "Participant's emotion is positive."

[0387] 3. Conclusion Generation: Based on the collected data and sentiment data, the server uses the ConclusionGenerator to generate an optimal conclusion for the meeting.

[0388] 4. Meeting Scheduling: The server uses the Scheduler to schedule the optimal meeting time.

[0389] Examples

[0390] For example, consider the case where the following data is collected in a factory:

[0391] Production data: "Production line A has reached 90% utilization."

[0392] Maintenance data: "Machine B requires maintenance."

[0393] Sentiment data: "Participants' sentiment is positive."

[0394] Based on this data, the server generates the following prompt sentence and inputs it into the AI ​​conclusion generation means.

[0395] Examples of prompt statements

[0396] The utilization rate of production line A has reached 90%. Machine B needs maintenance. The participants' sentiment is positive. Based on these data, generate the optimal meeting conclusion.

[0397] Based on this prompt, the AI ​​generates the optimal meeting conclusion, and the server optimizes the meeting schedule based on that conclusion. This makes it possible to efficiently reach meeting conclusions, shorten meeting times, and reduce unnecessary meetings. In addition, by drawing conclusions that take into account the emotions of the participants, the quality of conclusions can be improved. Furthermore, by effectively utilizing production data and maintenance data from within the factory, the progress of meetings can be made more efficient.

[0398] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0399] Step 1:

[0400] The server collects production data and maintenance data. Specifically, it obtains data such as "Production line A's operating rate has reached 90%" or "Machine B requires maintenance" from sensors and databases in the factory. The input is data from sensors and databases in the factory, and the output is the collected production data and maintenance data.

[0401] Step 2:

[0402] The server uses the EmotionEngine to recognize the user's emotions. Specifically, it uses a camera and microphone to analyze the participant's facial expressions and tone of voice, and obtains emotion data such as "The participant's emotion is positive." The input is video and audio data from the camera and microphone, and the output is the recognized emotion data.

[0403] Step 3:

[0404] The server generates a prompt sentence based on the collected production data, maintenance data, and emotion data. Specifically, it combines these data to create a prompt sentence such as "Production line A's operating rate has reached 90%. Machine B needs maintenance. Participants' emotions are positive. Please generate the optimal meeting conclusion based on these data." The input is the collected data, and the output is the generated prompt sentence.

[0405] Step 4:

[0406] The server uses the ConclusionGenerator to generate an optimal meeting conclusion based on the prompt sentence. Specifically, the prompt sentence is input to the generative AI model, and the AI ​​outputs the optimal conclusion. The input is the prompt sentence, and the output is the generated meeting conclusion.

[0407] Step 5:

[0408] The server uses the Scheduler to optimize the meeting schedule: it schedules optimal meeting times based on the generated meeting outcomes. The input is the generated meeting outcomes, and the output is the optimized meeting schedule.

[0409] Step 6:

[0410] The server notifies the user of the generated meeting conclusion and schedule. Specifically, it sends the meeting conclusion and schedule to the participants using email or a notification system. The input is the generated meeting conclusion and schedule, and the output is the notification to the user.

[0411] Example 2

[0412] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0413] Conventional conference systems had the problem that it took a lot of time and effort to reach a conclusion, which reduced the efficiency of the meeting. In addition, it was difficult to reach an optimal conclusion because the conclusion was reached without fully considering the opinions and feelings of the participants. Furthermore, as the number of meetings increased, it became difficult to align the understanding within the organization, which slowed down the speed of decision-making.

[0414] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0415] In this invention, the server includes a means for preparing a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for recognizing the user's emotions and adjusting the conclusion based on the emotions, a means for analyzing data using a generative AI model and extracting important points, and a means for analyzing the user's emotions using emotion recognition software. This makes it possible to improve the efficiency of the meeting and quickly derive an optimal conclusion that takes into account the opinions and emotions of the participants.

[0416] A "means for preparing a meeting conclusion in advance" is a means for generating a conclusion in advance based on information such as the meeting agenda, the opinions of participants, and the results of past meetings.

[0417] "Means of shortening the time of meetings" are means of making the meeting proceed more efficiently and shortening the time required.

[0418] "Methods to reduce the number of meetings" are means to reduce the number of meetings and make decision-making more efficient within an organization.

[0419] "The ability to predict the optimal conclusion at any given time from an objective point of view" is the ability to objectively derive the most appropriate conclusion based on collected data.

[0420] The "means for recognizing a user's emotion and adjusting a conclusion based on the emotion" refers to a means for analyzing a user's emotion and adjusting a conclusion based on the result of the analysis.

[0421] "Means for analyzing data and extracting important points using a generative AI model" means means for using a generative AI model to analyze input data and extract important information.

[0422] "Means for analyzing a user's emotions using emotion recognition software" refers to means for analyzing a user's emotions using emotion recognition software.

[0423] This invention is a system for improving the efficiency of a meeting and quickly deriving an optimal conclusion. This system operates in cooperation with a server, a terminal, and a user.

[0424] Hardware and Software Used

[0425] Hardware: Servers, terminals (PCs, tablets, smartphones)

[0426] Software: Generative AI models (e.g. GPT-4), emotion recognition software (e.g. IBM Watson® Tone Analyzer)

[0427] System Overview

[0428] 1. Data Collection

[0429] The user inputs the meeting agenda and opinions into the terminal.

[0430] The terminal transmits the input data to the server.

[0431] The server retrieves the results of past meetings from a database.

[0432] 2. Data Analysis

[0433] The server feeds a generative AI model (e.g., GPT-4) with the meeting agenda, participant opinions, and results of past meetings.

[0434] The server uses a generative AI model to analyze the input data and extract key points.

[0435] The server analyzes the user's emotions using emotion recognition software (e.g., IBM Watson Tone Analyzer).

[0436] 3. Inferring conclusions

[0437] The server uses a generative AI model to automatically generate optimal conclusions from the analysis results.

[0438] The server uses the results of emotion recognition software to adjust its conclusions depending on the user's emotions.

[0439] 4. Presentation of results

[0440] The server transmits the best guess to the terminal.

[0441] The terminal displays the optimal conclusion to the user.

[0442] Examples

[0443] For example, if the topic of the meeting is "New Product Launch Strategy", the user might enter:

[0444] Meeting Agenda: New Product Launch Strategy

[0445] Participant opinions: "I think the new product will be popular with younger generations" "I think the cost is too high"

[0446] Outcome of past meetings: "The new product was priced too high and didn't sell."

[0447] Example prompt:

[0448] The topic of the meeting is "New product launch strategy." The opinions of the participants are "I think the new product will be popular with young people" and "I think the cost is too high." The outcome of a past meeting was "The new product was priced too high and didn't sell." Based on this information, please infer the best conclusion.

[0449] The system can improve the efficiency of meetings and quickly reach optimal conclusions that take into account the opinions and feelings of participants.

[0450] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0451] Step 1:

[0452] The user inputs the meeting agenda and opinions into the terminal.

[0453] Input: Meeting topic: "New product launch strategy", participant opinions: "I think the new product will be popular with younger generations" and "Isn't the cost too high?"

[0454] Output: Data entered into the terminal

[0455] Step 2:

[0456] The terminal transmits the input data to the server.

[0457] Input: Meeting topic and comments entered by the user

[0458] Output: Data sent to the server

[0459] Step 3:

[0460] The server retrieves the results of past meetings from a database.

[0461] Input: Database query

[0462] Output: Results of past meetings: "The price of the new product was too high and it didn't sell."

[0463] Step 4:

[0464] The server feeds a generative AI model (e.g., GPT-4) with the meeting agenda, participant opinions, and results of past meetings.

[0465] Input: meeting agendas, participant comments, results of past meetings

[0466] Output: The data fed into the generative AI model

[0467] Step 5:

[0468] The server uses a generative AI model to analyze the input data and extract key points.

[0469] Input: Data fed into the generative AI model

[0470] Data processing: Generative AI models analyze data and extract key takeaways

[0471] Output: Key point: "It is likely to be popular among young people, but there are concerns about its high cost."

[0472] Step 6:

[0473] The server analyzes the user's emotions using emotion recognition software (e.g., IBM Watson Tone Analyzer).

[0474] Input: User opinion data

[0475] Data processing: Emotion recognition software analyzes user emotions

[0476] Output: User sentiment analysis result: "Positive"

[0477] Step 7:

[0478] The server uses a generative AI model to automatically generate optimal conclusions from the analysis results.

[0479] Input: Key points, user sentiment analysis results

[0480] Data processing: Generative AI models generate optimal conclusions

[0481] Output: Optimal conclusion: "Review the price of the new product and strengthen the marketing strategy for younger generations."

[0482] Step 8:

[0483] The server uses the results of emotion recognition software to adjust its conclusions depending on the user's emotions.

[0484] Input: Optimal conclusion, user sentiment analysis results

[0485] Data manipulation: Adjusting conclusions based on user sentiment

[0486] Output: Adjusted conclusion: "Review the price of the new product and strengthen the marketing strategy for younger generations (positive direction)."

[0487] Step 9:

[0488] The server transmits the best guess to the terminal.

[0489] Input: Adjusted conclusion

[0490] Output: conclusion sent to terminal

[0491] Step 10:

[0492] The terminal displays the optimal conclusion to the user.

[0493] Input: The conclusion sent by the server

[0494] Output: Conclusion displayed to the user: "Review the price of the new product and strengthen the marketing strategy for younger generations."

[0495] In this way, the system analyzes meeting agendas, opinions, and past results, and takes into account the user's emotions to arrive at optimal conclusions.

[0496] (Application example 2)

[0497] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0498] With conventional conference systems, it was difficult to prepare a meeting's conclusion in advance, which often resulted in lengthy meetings. In addition, there was a problem that efficient management became difficult as the number of meetings increased. Furthermore, in the manufacturing process, it was difficult to collect and analyze data from each step and propose optimal manufacturing procedures and improvements, and adjustments to work plans were not made that took into account the emotions of workers. To solve these problems, a system that could simultaneously improve meeting efficiency and optimize the manufacturing process was needed.

[0499] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0500] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for collecting and analyzing data on each step in the manufacturing process and proposing optimal manufacturing procedures and improvements, and a means for recognizing the emotions of workers and adjusting the work plan based on the emotions. This makes it possible to improve the efficiency of meetings and optimize the manufacturing process.

[0501] A "means for preparing meeting conclusions in advance" is a method for analyzing the meeting agenda, the opinions of participants, and the results of past meetings to generate optimal conclusions in advance.

[0502] "Means of shortening the time of meetings" are methods for making meetings more efficient and shortening the time required for meetings.

[0503] "Methods to reduce the number of meetings" are methods for evaluating the necessity of meetings and reducing unnecessary meetings.

[0504] "A function that can predict the optimal conclusion at any given time from an objective point of view" refers to a function that enables a meeting to reach an optimal conclusion based on collected data while the meeting is in progress.

[0505] "A means of collecting and analyzing data from each step in the manufacturing process and proposing optimal manufacturing procedures and improvements" is a method for proposing optimal manufacturing procedures and improvements by collecting and analyzing data generated at each step of the manufacturing line.

[0506] A "means for recognizing worker emotions and adjusting a work plan based on the emotions" is a method for recognizing a worker's emotional state and adjusting a work plan based on that information.

[0507] The system for carrying out the present invention is capable of simultaneously improving the efficiency of meetings and optimizing the manufacturing process. A specific embodiment of this system will be described below.

[0508] Hardware and Software Used

[0509] Hardware

[0510] Factory robots: Robots used in manufacturing lines (e.g. general-purpose robot arms)

[0511] Emotion recognition camera: A camera to recognize the emotions of workers (e.g. high-precision camera)

[0512] Data collection sensors: Sensors for collecting data at each step of the manufacturing process (e.g. IoT sensors)

[0513] software

[0514] AI Models: AI models for data analysis and optimization (e.g., TENSORFLOW®, PyTorch®)

[0515] Emotion recognition software: Software for analyzing worker emotions (e.g. Microsoft Azure Emotion API)

[0516] Data analysis tools: Tools for pre-processing and analyzing data (e.g. Apache Spark)

[0517] System Operation

[0518] Data collection

[0519] The server uses IoT sensors to collect data generated at each step of the production line (time, error rate, worker performance, etc.) and also collects worker emotion data using an emotion recognition camera.

[0520] Data analysis

[0521] The server preprocesses the collected data using Apache Spark and inputs it into an AI model built using TensorFlow and PyTorch to optimize the manufacturing process.

[0522] emotion recognition

[0523] The server uses the Microsoft Azure Emotion API to analyze the emotion data of workers and adjusts the work plan based on the analysis results.

[0524] Optimization suggestions

[0525] The server then proposes optimal manufacturing procedures and improvements based on the AI ​​model, adjusting the suggestions according to the worker's emotional state.

[0526] Examples

[0527] For example, if there is a bottleneck on a production line, the server might do the following:

[0528] Collect data from sensors to identify at which step delays are occurring.

[0529] Emotion-recognition cameras check workers' stress levels.

[0530] The AI ​​model suggests optimal improvement measures (for example, automating certain steps or adjusting worker break times).

[0531] Examples of prompt statements

[0532] "Collect data from the production line and analyze the efficiency of each step. Collect emotional data from workers and adjust work plans according to their stress levels. Suggest optimal production procedures and areas for improvement."

[0533] In this way, a system is created that simultaneously improves meeting efficiency and optimizes the manufacturing process.

[0534] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0535] Step 1:

[0536] The server uses IoT sensors to collect data (time, error rate, worker performance, etc.) generated at each step of the production line. The input is the sensor data for each step, and the output is a set of collected data. Specifically, the server obtains data from the sensors in real time and stores it in a database.

[0537] Step 2:

[0538] The server collects the workers' emotional data using an emotion recognition camera. The input is the camera footage, and the output is the analyzed emotional data. Specifically, the camera footage is captured in real time, and the emotional state is analyzed using emotion recognition software.

[0539] Step 3:

[0540] The server preprocesses the collected data using Apache Spark. The input is sensor data and emotion data, and the output is a preprocessed dataset. Specifically, it fills in missing values ​​in the data, removes outliers, and converts it into a format suitable for AI models.

[0541] Step 4:

[0542] The server inputs the preprocessed data into an AI model to optimize the manufacturing process. The input is the preprocessed data set, and the output is the optimal manufacturing procedure or suggestions for improvements. Specifically, the data is input into an AI model built using TensorFlow and PyTorch to generate the optimization results.

[0543] Step 5:

[0544] The server analyzes the worker's emotional data using the Microsoft Azure Emotion API. The input is the emotional data, and the output is the evaluation result of the emotional state. Specifically, the server sends the emotional data to the API and obtains the evaluation result in return.

[0545] Step 6:

[0546] The server proposes optimal manufacturing procedures and improvements generated by the AI ​​model. The input is the optimization results and the evaluation results of the emotional state, and the output is an adjusted work plan. Specifically, the server adjusts the work plan based on the optimization results and the emotional state and presents it to the worker.

[0547] Step 7:

[0548] The user executes the manufacturing process based on the work plan presented by the server. The input is the adjusted work plan, and the output is the result of the executed manufacturing process. Specifically, the user operates the manufacturing line according to the work plan and feeds back the results to the server.

[0549] 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.

[0550] 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 making a neural network perform deep learning. 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 is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0551] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0552] In the above embodiment, an example has been given in which the specific process is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0553] [Second embodiment]

[0554] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0555] 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.

[0556] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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 wide area network (WAN) and / or a local area network (LAN).

[0557] 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.

[0558] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, 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.

[0559] 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 surroundings of user 20 (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).

[0560] 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. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0561] 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.

[0562] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0563] 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.

[0564] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0565] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0566] "Example 1"

[0567] The system of the present invention is provided with a means for preparing a meeting conclusion in advance, a means for shortening the meeting time, and a means for reducing the number of meetings themselves. Specifically, as a means for preparing a meeting conclusion in advance, the system has a function for collecting meeting agendas and participant opinions and automatically generating a conclusion based on them. In addition, as a means for shortening meeting time, the system has a scheduling function and agenda management function for making the meeting progress more efficient. Furthermore, as a means for reducing the number of meetings themselves, the system has an optimization function for scheduling only necessary meetings.

[0568] "Example 2"

[0569] As a function that can predict the optimal conclusion at that time from an objective point of view, it has the function of analyzing the meeting agenda, the opinions of participants, the results of past meetings, etc., and predicting the optimal conclusion based on the results. A specific example would be a function that uses AI technology to analyze the meeting agenda and the opinions of participants, and automatically generates the optimal conclusion based on the results.

[0570] The process flow of each embodiment will be described below.

[0571] "Example 1"

[0572] Step 1: Collect the meeting agenda and participants' opinions. This will be the basis for formulating the meeting conclusions in advance.

[0573] Step 2: Automatically generate meeting conclusions based on the collected agenda and opinions, which can shorten the meeting time.

[0574] Step 3: Use scheduling and agenda management features to streamline the meeting, further shortening the meeting time.

[0575] Step 4: Use optimization features to schedule only the meetings you need, which can reduce the number of meetings you have.

[0576] "Example 2"

[0577] Step 1: Collect meeting agendas, participant opinions, past meeting results, etc. This will provide the basic data to objectively estimate the optimal conclusion at that time.

[0578] Step 2: Analyze the collected data using AI technology. This analysis will predict the optimal conclusion at that point in time.

[0579] Step 3: Based on the inferred conclusion, the conclusion of the meeting is automatically generated, which makes it possible to shorten the meeting time and reduce the number of meetings.

[0580] Example 1

[0581] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0582] In the modern business environment, meetings are important places for decision-making, but they often take too long, have vague conclusions, or are unnecessary. This reduces work efficiency and wastes resources. Therefore, there is a need for a system that can quickly and accurately make meeting conclusions, shorten meeting times, and reduce unnecessary meetings.

[0583] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0584] In this invention, the server includes a means for collecting meeting agendas and participant opinions and automatically generating a conclusion based on them, a means having a scheduling function and an agenda management function for making the meeting proceed efficiently, and a means having an optimization function for scheduling only necessary meetings. This makes it possible to quickly and accurately create a meeting conclusion, shorten the meeting time, and reduce unnecessary meetings.

[0585] A "meeting agenda" is the specific themes or topics to be discussed at a meeting.

[0586] "Participant input" refers to ideas, suggestions, and feedback provided by members attending the meeting.

[0587] "Means for automatically generating conclusions" refers to a function that uses artificial intelligence and algorithms to automatically create optimal conclusions based on collected topics and opinions.

[0588] The "scheduling function" refers to the function that optimizes meeting dates and times and participant schedules to set up meetings efficiently.

[0589] The "agenda management function" refers to the function of organizing the topics to be discussed in a meeting and managing the progress.

[0590] "Optimization function" refers to a function for evaluating the necessity of meetings and reducing duplicate or unnecessary meetings.

[0591] A "function that can make inferences from an objective perspective" is a function that uses data and algorithms to derive optimal conclusions without relying on subjectivity.

[0592] The present invention is a system for optimizing the efficiency of a conference, and is realized by a server, a terminal, and a user each fulfilling their respective roles. A specific embodiment of this system will be described below.

[0593] 1. A way to prepare meeting conclusions in advance

[0594] The server uses Google Calendar API and Microsoft Outlook API to collect meeting agendas and participant opinions. This allows it to obtain the agenda for the next meeting. It also collects participant opinions from communication tools such as Slack and Microsoft Teams.

[0595] Examples:

[0596] The server calls the Google Calendar API to get the agenda for the next meeting.

[0597] The server uses the Slack API to collect participant opinions from the meeting channel.

[0598] Based on the collected data, the server inputs prompts into a generative AI model (e.g., OpenAI's GPT-4), which generates a conclusion based on the input agenda and opinions.

[0599] Examples:

[0600] Prompt: The topic of the meeting is "Marketing strategy for a new product," and the opinions of the participants are "We should strengthen social media advertising," "We should also consider TV commercials," and "We have a limited budget, so we should choose an efficient method." Please generate a conclusion based on these.

[0601] The generated conclusions are stored in a database by the server and made accessible to the user.

[0602] 2. Ways to shorten meeting times

[0603] To streamline meetings, the server optimizes meeting schedules using Google Calendar API and Microsoft Outlook API, and manages agendas using task management tools such as Trello and Asana.

[0604] Examples:

[0605] The server calls the Google Calendar API to get the upcoming meeting schedule.

[0606] The server proposes an optimal schedule taking into account the free time of the participants.

[0607] The server calls the Trello API and creates the meeting agenda as a card.

[0608] The server provides real-time updates on the progress of the agenda.

[0609] 3. Ways to reduce the number of meetings

[0610] The server retrieves and analyzes existing meeting schedules using Google Calendar API and Microsoft Outlook API, detects duplicates and unnecessary meetings, and uses a generative AI model to evaluate the necessity of meetings and propose optimal schedules.

[0611] Examples:

[0612] The server calls the Google Calendar API to get the meeting schedule for the next week.

[0613] The server inputs prompt sentences into the generative AI model to assess the need for a meeting.

[0614] Prompt: Please optimize your meeting schedule for the next week. The current schedule is as follows: Monday: Meeting A, Tuesday: Meeting B, Wednesday: Meeting C. Please reduce overlapping and unnecessary meetings.

[0615] The generative AI model generates suggestions for reducing unnecessary meetings, and the server updates the schedule based on the suggestions.

[0616] This system makes it possible to quickly and accurately draw up meeting conclusions, shorten meeting times, and reduce unnecessary meetings.

[0617] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0618] Step 1:

[0619] The server calls the Google Calendar API or Microsoft Outlook API to get the meeting agenda. As input, it provides the schedule information of the upcoming meeting. The server saves the agenda information obtained from the API in a database.

[0620] Specific behavior:

[0621] The server calls the Google Calendar API to get the agenda for the next meeting.

[0622] The obtained agenda information is stored in a database.

[0623] Step 2:

[0624] The server uses APIs of Slack and Microsoft Teams to collect participants' opinions. As input, it provides the channel information of the meeting. The server stores the opinion information obtained from the API in a database.

[0625] Specific behavior:

[0626] The server uses the Slack API to collect participant opinions from the meeting channel.

[0627] The obtained opinion information is stored in a database.

[0628] Step 3:

[0629] The server inputs the collected topics and opinions into the generative AI model. As input, it provides text data of the topics and opinions. The generative AI model generates a conclusion based on the input data and outputs it to the server.

[0630] Specific behavior:

[0631] The server converts the agenda and opinions into text format and inputs them as prompts to the generative AI model.

[0632] The generative AI model analyzes the prompt and generates an optimal conclusion.

[0633] The server receives the generated conclusions and stores them in a database.

[0634] Step 4:

[0635] The server uses Google Calendar API and Microsoft Outlook API to optimize meeting schedules. As input, you provide the schedule information of the participants. The server calculates the optimal schedule and proposes it as output.

[0636] Specific behavior:

[0637] The server calls the Google Calendar API to obtain the participants' schedule information.

[0638] Based on the acquired schedule information, the optimal meeting schedule is calculated.

[0639] The server proposes an optimal schedule and stores it in a database.

[0640] Step 5:

[0641] The server uses Trello or Asana API to manage the agenda. As input, we provide the meeting agenda information. The server creates the agenda as cards and manages the progress.

[0642] Specific behavior:

[0643] The server calls the Trello API and creates the meeting agenda as a card.

[0644] The server provides real-time updates on the progress of the agenda.

[0645] Step 6:

[0646] The server uses Google Calendar API and Microsoft Outlook API to analyze the existing meeting schedule. As input, you provide the meeting schedule information for the next week. The server detects overlapping and unnecessary meetings and suggests an optimized schedule as output.

[0647] Specific behavior:

[0648] The server calls the Google Calendar API to get the meeting schedule for the next week.

[0649] The server analyzes the schedule to detect overlapping and unnecessary meetings.

[0650] The server inputs prompt sentences into the generative AI model to assess the need for a meeting.

[0651] A generative AI model generates suggestions to cut down on unnecessary meetings.

[0652] The server updates the schedule based on the suggestions.

[0653] (Application example 1)

[0654] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0655] Meetings and discussions in factories are important for improving productivity, but they often take too much time and there are many pointless meetings. It is also difficult to efficiently collect opinions from each department and reach optimal conclusions. To solve these problems, there is a need to streamline and optimize meetings.

[0656] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the time of the meeting, a means for reducing the number of meetings, a means for collecting agendas and opinions from each department in the factory and automatically generating a conclusion using a generative AI model, a means for optimizing the meeting schedule and efficiently managing the agenda, and a means for scheduling only necessary meetings and reducing unnecessary meetings. This makes it possible to make meetings and discussions in the factory more efficient and improve productivity.

[0657] "A means of preparing meeting conclusions in advance" is a function that collects meeting agendas and participants' opinions, and automatically generates conclusions based on them.

[0658] "Means of shortening meeting times" refer to scheduling and agenda management functions to make meetings more efficient.

[0659] "A means to reduce the number of meetings" refers to an optimization function that schedules only necessary meetings.

[0660] "A function that can predict the optimal conclusion at any given time from an objective perspective" is a function that automatically derives the optimal conclusion based on collected information.

[0661] "Means of collecting topics and opinions from each department within the factory" refers to a function that visits each department within the factory and collects opinions using voice recognition technology.

[0662] "Means for automatically generating a conclusion using a generative AI model" refers to a function that automatically generates a conclusion using a generative AI model based on collected topics and opinions.

[0663] "Means for optimizing meeting schedules and efficiently managing agendas" refers to a function for optimizing meeting schedules and efficiently managing agendas using scheduling software.

[0664] "A means of scheduling only necessary meetings and reducing unnecessary meetings" is a function that uses AI to evaluate the necessity of meetings and reduce unnecessary meetings.

[0665] The system for carrying out the present invention is a tool for making meetings and conferences in a factory more efficient and improving productivity. A specific embodiment of this system will be described below.

[0666] Hardware and Software Used

[0667] Hardware: Factory robots, servers, network equipment

[0668] Software: Generative AI models (e.g. OpenAI GPT-4), database management systems (e.g. MySQL), scheduling software (e.g. Google Calendar API)

[0669] Data processing and calculation

[0670] Agenda collection

[0671] The factory robot travels around each department in the factory and collects opinions using voice recognition technology. The collected data is sent to a server and stored in a database. This allows opinions from each department to be efficiently collected.

[0672] Automatic conclusion generation

[0673] The server automatically generates conclusions using a generative AI model (e.g. GPT-4) based on the collected agenda and opinions. The generated conclusions are stored in a database and notified to each department as necessary. This allows the conclusions of meetings to be generated quickly.

[0674] Scheduling and Agenda Management

[0675] The server optimizes the meeting schedule using scheduling software (e.g., Google Calendar API). It also efficiently manages the agenda for each meeting using the agenda management function, allowing the meetings to proceed smoothly.

[0676] Optimizing the number of meetings

[0677] The server uses AI to evaluate the necessity of meetings and schedules only the necessary meetings, thus reducing unnecessary meetings.

[0678] Examples

[0679] For example, if a meeting is held within a factory to introduce a new product line, the process may look like this:

[0680] 1. Gather input from each department about the new product line.

[0681] 2. Based on the collected opinions, the generative AI model automatically generates a conclusion.

[0682] 3. Use scheduling software to schedule the best possible meeting.

[0683] 4. Schedule only the meetings you need and cut down on the unnecessary ones.

[0684] Examples of prompt statements

[0685] Here is an example of a prompt to be input to the generative AI model:

[0686] You have collected opinions regarding the introduction of a new product line. Generate a conclusion based on the opinions below.

[0687] Opinion 1: We should install new machines to improve the efficiency of our production line.

[0688] Opinion 2: It is better to improve the existing machine to reduce costs.

[0689] Statement 3: The introduction of a new product line requires employee training.

[0690] Use these opinions to generate the best conclusion.

[0691] In this way, factory meetings can be made more efficient and productivity can be improved.

[0692] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0693] Step 1:

[0694] The factory robot travels around each department in the factory and collects opinions using voice recognition technology. The input is the voice opinions from the staff in each department, and the output is the opinion data in text format. The robot uses voice recognition software to convert the voice into text and sends it to the server.

[0695] Step 2:

[0696] The server stores the opinion data sent from the robot in a database. The input is the opinion data in text format, and the output is the opinion data stored in the database. The server stores the data using a database management system (e.g., MySQL).

[0697] Step 3:

[0698] The server automatically generates a conclusion using a generative AI model (e.g. GPT-4) based on the opinion data stored in the database. The input is the opinion data obtained from the database, and the output is the generated conclusion. The server inputs a prompt sentence into the generative AI model to generate a conclusion.

[0699] Step 4:

[0700] The server stores the generated conclusions in a database and notifies each department as necessary. The input is the generated conclusion, and the output is the conclusion stored in the database and the notified conclusion. The server sends the conclusions to each department using a notification system.

[0701] Step 5:

[0702] The server optimizes the meeting schedule using scheduling software (e.g. Google Calendar API). The input is the meeting agenda and attendee information, and the output is the optimized meeting schedule. The server uses the scheduling software to set the schedule.

[0703] Step 6:

[0704] The server efficiently manages the agenda of each meeting through the agenda management function. The input is the meeting agenda information, and the output is the managed agenda information. The server manages the agenda using the agenda management software.

[0705] Step 7:

[0706] The server uses AI to assess the need for meetings and schedule only those that are necessary. The input is meeting agenda and participant information, and the output is an optimized meeting schedule. The server uses AI models to assess the need for meetings and reduce unnecessary meetings.

[0707] Example 2

[0708] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0709] In conventional conference systems, it was difficult to prepare a meeting's conclusion in advance, and meetings often dragged on. In addition, as the number of meetings increased, the burden on participants increased, making efficient decision-making difficult. Furthermore, there was a demand for a system that could objectively analyze meeting topics and participants' opinions to arrive at optimal conclusions.

[0710] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0711] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a means for collecting, preprocessing, and analyzing meeting agendas, participants' opinions, and results of past meetings, a means for predicting an optimal conclusion using a generative AI model, and a means for outputting the predicted conclusion, thereby making it possible to improve the efficiency of meetings and derive optimal conclusions.

[0712] A "means for preparing a meeting conclusion in advance" is a method or device for preparing a conclusion based on existing information before the meeting begins.

[0713] A "means for shortening the duration of a meeting" is a method or device for making the meeting proceed more efficiently and shortening the time required for the meeting.

[0714] A "means for realizing a reduction in the number of meetings" is a method or device for reducing the number of necessary meetings and reducing the overall number of meetings.

[0715] A "means for collecting meeting agendas, participant opinions, and results of past meetings" is a method or device for collecting information related to meetings.

[0716] A "preprocessing means" is a method or device for preparing collected data in a form that is easy to analyze.

[0717] An "analyzing means" is a method or device for analyzing the pre-processed data and extracting significant information.

[0718] A "means for inferring optimal conclusions using a generative AI model" is a method or device for using artificial intelligence technology to derive optimal conclusions from collected and analyzed data.

[0719] A "means for outputting an inferred conclusion" is a method or device for providing a user with the conclusion inferred by the generative AI model.

[0720] The present invention is directed to a system for improving the efficiency of a meeting and deriving an optimal conclusion. A specific embodiment of this system will be described below.

[0721] The server generates programs to collect, preprocess, and analyze meeting agendas, participant opinions, and past meeting results. The programs use natural language processing libraries (e.g., NLTK, spaCy) and generative AI models (e.g., GPT-4) to process and compute the data.

[0722] First, the server connects to a database and collects meeting agendas, participant opinions, and results of past meetings. For example, it obtains the minutes and participant opinions of a meeting on "New Product Launch Strategy."

[0723] The server then pre-processes the collected data, which involves cleaning the text data, tokenizing it, removing stop words, etc., making the data easier to analyze.

[0724] The server then feeds the pre-processed data into a generative AI model to extract key keywords and themes, such as "market research," "competitive analysis," and "marketing strategy."

[0725] Next, the server uses the generative AI model to predict the optimal conclusion based on the analysis results, taking into account the results of past meetings and the opinions of the participants. For example, the generative AI model is given a prompt such as, "Please predict the optimal conclusion regarding the market launch strategy for a new product."

[0726] Finally, the server outputs the inferred conclusion to the terminal. The user can confirm this conclusion through the terminal. For example, the conclusion "Strengthen market research and develop a marketing strategy based on competitive analysis" is confirmed on the screen of the terminal.

[0727] As a concrete example, consider a case where a user holds a meeting and sets the topic as "New product launch strategy." Participants express their opinions and note that similar topics have been discussed in past meetings. In this case, the server inputs the following prompt sentence into the generative AI model:

[0728] Example prompt:

[0729] "Based on the agenda and participants' opinions of a meeting about a new product launch strategy, infer the best outcome. Also take into account the results of previous meetings."

[0730] By inputting this prompt into a generative AI model, the server can infer the optimal conclusion and provide it to the user.

[0731] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0732] Step 1: Data collection

[0733] The server collects meeting agendas, participant opinions, and past meeting results by connecting to a database and retrieving relevant meeting minutes and speech records.

[0734] Input: meeting agendas, participant comments, results of past meetings

[0735] Output: Raw data collected

[0736] What happens: The server uses an SQL query to retrieve meeting minutes and participant opinions on "New Product Launch Strategy" from the database.

[0737] Step 2: Data Preprocessing

[0738] The server pre-processes the collected data, specifically cleaning the text data, tokenizing it, removing stop words, etc.

[0739] Input: Raw data collected

[0740] Output: Preprocessed data

[0741] Specific operation: The server removes unnecessary symbols and spaces from the acquired text data, tokenizes it, and removes stop words. This is done using a natural language processing library (e.g. NLTK, spaCy).

[0742] Step 3: Data analysis

[0743] The server feeds the pre-processed data into a generative AI model to extract key keywords and themes.

[0744] Input: Preprocessed data

[0745] Output: Extracted keywords and themes

[0746] How it works: The server inputs the preprocessed text data into a generative AI model (e.g., GPT-4) and extracts important keywords such as "market research," "competitive analysis," and "marketing strategy."

[0747] Step 4: Inferring conclusions

[0748] The server uses a generative AI model to infer the optimal conclusion based on the analysis results.

[0749] Input: Extracted keywords or themes

[0750] Output: Inferred conclusion

[0751] Specific operation: Based on the extracted keywords and themes, the server inputs a prompt to the generative AI model: "Please predict the optimal conclusion regarding the new product's market launch strategy." The generative AI model considers the results of past meetings and the opinions of participants and generates the conclusion: "Strengthen market research and develop a marketing strategy based on competitive analysis."

[0752] Step 5: Output the results

[0753] The server outputs the inferred conclusion to the terminal, where the user can confirm the conclusion.

[0754] Input: Inferred conclusion

[0755] Output: conclusions provided to the user

[0756] Specific operation: The server transmits the generated conclusion to the terminal, and the user confirms the conclusion "strengthen market research and develop a marketing strategy based on competitive analysis" on the terminal screen.

[0757] (Application example 2)

[0758] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the smart glasses 214 will be referred to as a "terminal".

[0759] In conventional conference systems, it was difficult to prepare the conclusion of a meeting in advance, which resulted in long meeting times and an increase in the number of meetings. In addition, it was difficult to objectively predict the optimal conclusion, which meant that it took a lot of time and effort to align the understanding within the organization.

[0760] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0761] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for acquiring the results of past meetings from a database, a means for automatically generating an optimal conclusion using a generative AI model, and a means for outputting the generated conclusion. This makes it possible to improve the efficiency of meetings and automatically generate optimal conclusions.

[0762] The "means for creating a meeting conclusion in advance" is a function for automatically generating a conclusion based on the agenda before the meeting begins.

[0763] "Means of shortening meeting times" refers to functions that make meetings more efficient and shorten the amount of time required.

[0764] "Means for reducing the number of meetings" refers to a function for evaluating the necessity of meetings and reducing unnecessary meetings.

[0765] "A function that can predict the optimal conclusion at that time from an objective perspective" is a function that automatically predicts the most appropriate conclusion based on data collected while the meeting is in progress.

[0766] The "means for acquiring the results of past meetings from a database" is a function for searching and acquiring the results of meetings that were previously held from a database.

[0767] "Means for automatically generating optimal conclusions using a generative AI model" refers to a function that uses artificial intelligence technology to automatically generate optimal conclusions based on collected data.

[0768] The "means for outputting the generated conclusion" is a function for displaying the generated conclusion to the user.

[0769] In the system for carrying out the present invention, a server, a terminal, and a user work in cooperation with each other. The server includes a means for preparing a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for acquiring the results of past meetings from a database, a means for automatically generating an optimal conclusion using a generative AI model, and a means for outputting the generated conclusion.

[0770] The server first collects the meeting agenda and the opinions of the participants. This includes the function of collecting information entered by users in real time using terminals (such as smartphones and tablets). Next, the server retrieves the results of past meetings from a database and automatically generates optimal conclusions based on this data using a generative AI model.

[0771] The generative AI model uses advanced natural language processing techniques such as OpenAI's GPT-3. The server inputs the collected topics, opinions, and past results as prompts into the generative AI model to generate the optimal conclusion. The generated conclusion is displayed to the user through the terminal.

[0772] As a concrete example, the following prompt sentence is input to the generative AI model:

[0773] Agenda: Improving production line efficiency

[0774] opinion:

[0775] Person A: We should get new machines.

[0776] Person B: We should review our work procedures.

[0777] Person C: Working hours should be adjusted.

[0778] Past results:

[0779] Reconfiguring production lines increases efficiency by 10%

[0780] New software implementation reduces error rate by 5%

[0781] Generate the best conclusion.

[0782] Based on this prompt, the generative AI model outputs the optimal conclusion, such as "Production efficiency can be further improved by combining the introduction of new machinery with a review of work procedures."

[0783] This system makes it possible to streamline meetings and automatically generate optimal conclusions, and can handle the many different views within an organization. The hardware used includes mobile devices such as smartphones and tablets, and the software uses Python, SQLite, and OpenAI API.

[0784] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0785] Step 1:

[0786] The server collects the meeting agenda and the opinions of the participants. The user inputs the meeting agenda and their opinions using a terminal (such as a smartphone or tablet). The input data is sent to the server and stored in a database. In this way, the meeting agenda and the opinions of the participants are collected.

[0787] Step 2:

[0788] The server retrieves the results of past conferences from the database. The server queries the database to search for the results of past conferences. The retrieved data is temporarily stored in the server. In this way, the results of past conferences are retrieved.

[0789] Step 3:

[0790] The server generates prompt sentences based on the collected topics, opinions, and past results. The server converts the collected data into text format and creates prompt sentences to input to the generative AI model. This generates prompt sentences to input to the generative AI model.

[0791] Step 4:

[0792] The server automatically generates an optimal conclusion using a generative AI model. The server inputs the generated prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) and generates an optimal conclusion. The generative AI model performs data calculations based on the input prompt sentence and outputs an optimal conclusion. In this way, the optimal conclusion is automatically generated.

[0793] Step 5:

[0794] The server transmits the generated conclusion to the terminal and displays it to the user. The server transmits the generated conclusion to the terminal and allows the user to view it. The user can check the generated conclusion through the terminal. Thus, the generated conclusion is displayed to the user.

[0795] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0796] "Example 1"

[0797] One embodiment of the present invention is a system that combines an emotion engine that recognizes the emotions of a user. This system includes a means for creating a meeting conclusion in advance, a means for shortening the time of the meeting, a means for reducing the number of meetings, and a function for predicting the optimal conclusion at that time from an objective point of view. The emotion engine recognizes the user's emotions, and controls the means for creating a meeting conclusion in advance based on the emotions. Specifically, if the user's emotions are positive, a meeting conclusion is created in advance in a positive direction. Conversely, if the user's emotions are negative, a meeting conclusion is created in advance in a cautious direction.

[0798] "Example 2"

[0799] The emotion engine also controls a function that recognizes the user's emotions and predicts the optimal conclusion at that time from an objective point of view based on those emotions. Specifically, if the user's emotions are positive, the optimal conclusion at that time is predicted to be in the positive direction. Conversely, if the user's emotions are negative, the optimal conclusion at that time is predicted to be in the cautious direction. In this way, by taking the user's emotions into consideration, it becomes possible to create a more appropriate meeting conclusion in advance and predict the optimal conclusion at that time.

[0800] The process flow of each embodiment will be described below.

[0801] "Example 1"

[0802] Step 1: A user starts a conference.

[0803] Step 2: The emotion engine recognizes the user's emotion.

[0804] Step 3: Pre-create a meeting conclusion based on the emotions recognized by the emotion engine.

[0805] Step 4: Present the pre-created conclusions to the user.

[0806] Step 5: The user reviews the proposed conclusions and modifies them if necessary.

[0807] "Example 2"

[0808] Step 1: A user starts a conference.

[0809] Step 2: The emotion engine recognizes the user's emotion.

[0810] Step 3: Based on the emotions identified by the emotion engine, an objective guess is made as to the best outcome at that point in time.

[0811] Step 4: Present the best guess to the user.

[0812] Step 5: The user reviews the proposed conclusions and modifies them if necessary.

[0813] Example 1

[0814] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0815] In conventional conference systems, it was difficult to efficiently reach a meeting conclusion, and meetings often dragged on. In addition, there was a tendency for the number of meetings to increase, which increased the burden on participants. Furthermore, the conclusions of meetings tended to be subjective and often influenced by the emotions of participants. There is a need to solve these problems and improve the efficiency and optimization of meetings.

[0816] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0817] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a means for recognizing the user's emotions and adjusting the meeting conclusion based on the emotions, and a function for predicting the optimal conclusion at that time from an objective point of view. This makes it possible to efficiently create a meeting conclusion, shorten the meeting time, and select only the necessary meetings. In addition, by adjusting the conclusion taking the user's emotions into account, a more objective and appropriate conclusion can be derived.

[0818] "A means of preparing meeting conclusions in advance" refers to a function that collects meeting agendas and participants' opinions, and automatically generates conclusions based on them.

[0819] "Means of shortening meeting times" refers to functions that provide scheduling and agenda management functions to make meetings more efficient.

[0820] "Means of reducing the number of meetings" refers to the ability to provide optimization functions to schedule only necessary meetings.

[0821] "Means for recognizing a user's emotions and adjusting the conclusion of the meeting based on those emotions" refers to a function for analyzing a user's emotions and adjusting the conclusion of the meeting in a positive or cautious direction depending on those emotions.

[0822] "A function that can predict the optimal conclusion at any given time from an objective perspective" refers to a function that automatically predicts the most appropriate conclusion based on collected data and user emotions.

[0823] The present invention relates to a system for improving the efficiency and optimizing a conference. A specific embodiment of the system will be described below.

[0824] A means of preparing meeting conclusions in advance

[0825] The server uses APIs of common communication tools (e.g., communication platforms and messaging applications) to collect meeting agendas and participant opinions. The collected data is stored in a database. The server then uses a generative AI model (e.g., a natural language processing model) to automatically generate a conclusion based on the collected data. Specifically, the server inputs the following prompt sentence into the generative AI model:

[0826] "The topic of the meeting is XX, and the opinions of the participants are △△. Please generate a conclusion based on this."

[0827] The generated conclusions are again stored in the database.

[0828] A way to shorten meeting times

[0829] The server optimizes meeting schedules using scheduling software (e.g., a calendar application) to automatically adjust meeting start and end times, and uses a project management tool (e.g., a task management application) to manage agendas by creating tasks for each agenda item and tracking their progress.

[0830] A means to reduce the number of meetings

[0831] The server uses machine learning algorithms to analyze past meeting data and select only necessary meetings. Specifically, it uses a Python machine learning library to build a model that evaluates the importance of meetings. This model evaluates the necessity of meetings and schedules only high-importance meetings.

[0832] A means of recognizing a user's emotions and adjusting the outcome of a meeting based on those emotions

[0833] The terminal uses an emotion analysis engine (e.g., emotion recognition API) to recognize the user's emotions. The terminal analyzes the user's speech and facial expressions to obtain emotion data. The obtained emotion data is sent to the server. The server adjusts the conclusion based on the emotion data. For example, if the user's emotion is positive, the server corrects the conclusion in a positive direction. Conversely, if the user's emotion is negative, the server corrects the conclusion in a cautious direction.

[0834] Examples

[0835] For example, if the topic of a meeting is "New product launch strategy" and the participants' opinions are "We should conduct an aggressive marketing campaign," we can input the following prompt into the generative AI model:

[0836] "The topic of the meeting should be a new product launch strategy, and the participants' input should be about an aggressive marketing campaign. Use this as a basis for generating conclusions."

[0837] Based on this prompt, the generative AI model generates the conclusion that "it is optimal to conduct an aggressive marketing campaign as a new product launch strategy." If the user's sentiment is positive, the sentiment engine sends this information to the server, which then generates a positive conclusion. For example, it generates the conclusion that "since the user's sentiment is positive, it is recommended to further strengthen the marketing campaign."

[0838] In this way, the system of the present invention realizes efficiency and optimization of meetings.

[0839] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0840] Step 1:

[0841] The server collects the meeting agenda and participant opinions.

[0842] Specifically, the server uses the communication platform's API to obtain the chat log and minutes of the meeting.

[0843] Input: Meeting chat logs, minutes

[0844] Output: Collected topics and opinion data

[0845] Step 2:

[0846] The server stores the collected topics and opinions in a database.

[0847] As a specific operation, the server executes an INSERT query on the database to insert data into the agenda table and the opinion table.

[0848] Input: Collected agenda and opinion data

[0849] Output: Topics and opinions stored in a database

[0850] Step 3:

[0851] The server creates a prompt based on the collected topics and opinions.

[0852] Specifically, the server converts the agenda and opinion data into text format and generates prompt sentences to input into the generative AI model.

[0853] Input: Topics and opinions stored in the database

[0854] Output: Generated prompt statement

[0855] Step 4:

[0856] The server inputs a prompt sentence into the generative AI model and generates a conclusion.

[0857] Specifically, the server calls the API of the generative AI model, inputs a prompt sentence, and generates a conclusion.

[0858] Input: Generated prompt text

[0859] Output: Generated conclusions

[0860] Step 5:

[0861] The server stores the generated conclusions in a database.

[0862] As a specific operation, the server executes an INSERT query on the database to insert data into the conclusion table.

[0863] Input: Generated conclusions

[0864] Output: conclusions stored in a database

[0865] Step 6:

[0866] The server uses scheduling software to optimize the schedule of meetings.

[0867] Specifically, the server uses the calendar application's API to automatically adjust the start and end times of meetings.

[0868] Input: Meeting schedule information

[0869] Output: Optimized meeting schedule

[0870] Step 7:

[0871] The server uses a project management tool to manage the agenda.

[0872] Specifically, the server uses the API of the task management application to create tasks for each agenda item and track their progress.

[0873] Input:Agenda information

[0874] Output: Managed agenda tasks

[0875] Step 8:

[0876] The server analyzes past conference data and selects only the necessary conferences.

[0877] Specifically, the server uses a machine learning algorithm to build a model that evaluates the importance of meetings and selects only meetings with high importance.

[0878] Input: Past meeting data

[0879] Output: Select the required meeting

[0880] Step 9:

[0881] The terminal uses an emotion analysis engine to recognize the user's emotions.

[0882] Specifically, the device uses an emotion recognition API to analyze the user's statements and facial expressions and obtain emotional data.

[0883] Input: User's speech and facial expressions

[0884] Output: The acquired emotion data

[0885] Step 10:

[0886] The terminal transmits the recognized emotion data to the server.

[0887] Specifically, the device sends a POST request to the server with emotion data in JSON format.

[0888] Input: Acquired emotion data

[0889] Output: Emotion data sent to the server

[0890] Step 11:

[0891] The server adjusts the conclusion based on the emotion data.

[0892] Specifically, the server analyzes the emotion data, and if the user's emotion is positive, the server corrects the conclusion to a positive direction, and if the user's emotion is negative, the server corrects the conclusion to a more cautious direction.

[0893] Input: Emotion data sent to the server

[0894] Output: Adjusted conclusion

[0895] (Application example 1)

[0896] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0897] In conventional conference systems, it was difficult to reach a conclusion in a meeting efficiently, leading to problems such as long meetings and frequent useless meetings. In addition, the quality of the conclusions was often poor because the conclusions were reached without considering the feelings of the participants. Furthermore, production data and maintenance data within the factory could not be effectively utilized, which often led to inefficient progress in meetings.

[0898] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0899] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view using an emotion engine that recognizes the user's emotions, a means for collecting production data and maintenance data in the factory and automatically generating the optimal conclusion using AI, a means for providing a scheduling function and an agenda management function for streamlining the progress of the meeting, and a means for having an optimization function for scheduling only necessary meetings. This makes it possible to efficiently derive a meeting conclusion, shorten the meeting time, and reduce unnecessary meetings. In addition, the quality of the conclusion can be improved by drawing a conclusion that takes into account the emotions of the participants. Furthermore, the progress of the meeting can be made more efficient by effectively utilizing the production data and maintenance data in the factory.

[0900] The "means for preparing a meeting conclusion in advance" is a function for collecting the meeting agenda and the opinions of the participants, and automatically generating the meeting conclusion based on them.

[0901] "Means of shortening meeting times" refers to functions that provide scheduling and agenda management functions to make meetings more efficient.

[0902] "Means for reducing the number of meetings" refers to a feature that provides an optimization function for scheduling only necessary meetings.

[0903] The "emotion engine that recognizes the user's emotions" is a function that recognizes the user's emotions and controls a means for preparing a meeting conclusion in advance based on the emotions.

[0904] The "means for collecting production data and maintenance data within the factory" is a function for collecting data regarding production activities and maintenance activities within the factory.

[0905] "Means for AI to automatically generate optimal conclusions" refers to a function in which artificial intelligence automatically generates optimal meeting conclusions based on collected data.

[0906] The "scheduling function for making meetings more efficient" is a function for optimizing the meeting schedule and making the meeting proceed efficiently.

[0907] The "agenda management function" is a function for managing the agenda of a meeting and progressing the meeting efficiently.

[0908] The "optimization function" is a function that evaluates the necessity of meetings and generates an optimal schedule in order to schedule only necessary meetings.

[0909] The system for carrying out the present invention has a plurality of functions for preparing a meeting conclusion in advance and realizing shortening the time and number of meetings. A specific embodiment of this system will be described below.

[0910] System Configuration

[0911] The system consists of the following main components:

[0912] 1. Server

[0913] A means for preparing a meeting conclusion in advance: The server has a function for collecting the meeting agenda and the opinions of the participants, and automatically generating the meeting conclusion based on them.

[0914] Means to reduce meeting times: The server provides scheduling and agenda management functions to make meetings more efficient.

[0915] A means to reduce the number of meetings: The server has an optimization function to schedule only necessary meetings.

[0916] Emotion Engine: The server controls the means to recognize the user's emotions and pre-plan the outcome of the meeting based on those emotions.

[0917] Data collection method: The server collects production data and maintenance data within the factory.

[0918] AI conclusion generation method: The server automatically generates the optimal meeting conclusion using artificial intelligence based on the collected data.

[0919] Hardware and software used

[0920] EmotionEngine: An engine for recognizing user emotions. It uses the camera and microphone to collect emotion data.

[0921] Scheduler: Software for scheduling meetings.

[0922] ConclusionGenerator: Software for generating meeting conclusions using AI.

[0923] Data processing and calculation

[0924] 1. Data collection: The server collects production data and maintenance data. For example, it collects data such as "Production line A's operating rate has reached 90%" or "Machine B needs maintenance."

[0925] 2. Emotion Recognition: The server uses the EmotionEngine to recognize participants' emotions from the camera and microphone. For example, it collects data such as "Participant's emotion is positive."

[0926] 3. Conclusion Generation: Based on the collected data and sentiment data, the server uses the ConclusionGenerator to generate an optimal conclusion for the meeting.

[0927] 4. Meeting Scheduling: The server uses the Scheduler to schedule the optimal meeting time.

[0928] Examples

[0929] For example, consider the case where the following data is collected in a factory:

[0930] Production data: "Production line A has reached 90% utilization."

[0931] Maintenance data: "Machine B requires maintenance."

[0932] Sentiment data: "Participants' sentiment is positive."

[0933] Based on this data, the server generates the following prompt sentence and inputs it into the AI ​​conclusion generation means.

[0934] Examples of prompt statements

[0935] The utilization rate of production line A has reached 90%. Machine B needs maintenance. The participants' sentiment is positive. Based on these data, generate the optimal meeting conclusion.

[0936] Based on this prompt, the AI ​​generates the optimal meeting conclusion, and the server optimizes the meeting schedule based on that conclusion. This makes it possible to efficiently reach meeting conclusions, shorten meeting times, and reduce unnecessary meetings. In addition, by drawing conclusions that take into account the emotions of the participants, the quality of conclusions can be improved. Furthermore, by effectively utilizing production data and maintenance data from within the factory, the progress of meetings can be made more efficient.

[0937] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0938] Step 1:

[0939] The server collects production data and maintenance data. Specifically, it obtains data such as "Production line A's operating rate has reached 90%" or "Machine B requires maintenance" from sensors and databases in the factory. The input is data from sensors and databases in the factory, and the output is the collected production data and maintenance data.

[0940] Step 2:

[0941] The server uses the EmotionEngine to recognize the user's emotions. Specifically, it uses a camera and microphone to analyze the participant's facial expressions and tone of voice, and obtains emotion data such as "The participant's emotion is positive." The input is video and audio data from the camera and microphone, and the output is the recognized emotion data.

[0942] Step 3:

[0943] The server generates a prompt sentence based on the collected production data, maintenance data, and emotion data. Specifically, it combines these data to create a prompt sentence such as "Production line A's operating rate has reached 90%. Machine B needs maintenance. Participants' emotions are positive. Please generate the optimal meeting conclusion based on these data." The input is the collected data, and the output is the generated prompt sentence.

[0944] Step 4:

[0945] The server uses the ConclusionGenerator to generate an optimal meeting conclusion based on the prompt sentence. Specifically, the prompt sentence is input to the generative AI model, and the AI ​​outputs the optimal conclusion. The input is the prompt sentence, and the output is the generated meeting conclusion.

[0946] Step 5:

[0947] The server uses the Scheduler to optimize the meeting schedule: it schedules optimal meeting times based on the generated meeting outcomes. The input is the generated meeting outcomes, and the output is the optimized meeting schedule.

[0948] Step 6:

[0949] The server notifies the user of the generated meeting conclusion and schedule. Specifically, it sends the meeting conclusion and schedule to the participants using email or a notification system. The input is the generated meeting conclusion and schedule, and the output is the notification to the user.

[0950] Example 2

[0951] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0952] Conventional conference systems had the problem that it took a lot of time and effort to reach a conclusion, which reduced the efficiency of the meeting. In addition, it was difficult to reach an optimal conclusion because the conclusion was reached without fully considering the opinions and feelings of the participants. Furthermore, as the number of meetings increased, it became difficult to align the understanding within the organization, which slowed down the speed of decision-making.

[0953] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0954] In this invention, the server includes a means for preparing a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for recognizing the user's emotions and adjusting the conclusion based on the emotions, a means for analyzing data using a generative AI model and extracting important points, and a means for analyzing the user's emotions using emotion recognition software. This makes it possible to improve the efficiency of the meeting and quickly derive an optimal conclusion that takes into account the opinions and emotions of the participants.

[0955] A "means for preparing a meeting conclusion in advance" is a means for generating a conclusion in advance based on information such as the meeting agenda, the opinions of participants, and the results of past meetings.

[0956] "Means of shortening the time of meetings" are means of making the meeting proceed more efficiently and shortening the time required.

[0957] "Methods to reduce the number of meetings" are means to reduce the number of meetings and make decision-making more efficient within an organization.

[0958] "The ability to predict the optimal conclusion at any given time from an objective point of view" is the ability to objectively derive the most appropriate conclusion based on collected data.

[0959] The "means for recognizing a user's emotion and adjusting a conclusion based on the emotion" refers to a means for analyzing a user's emotion and adjusting a conclusion based on the result of the analysis.

[0960] "Means for analyzing data and extracting important points using a generative AI model" means means for using a generative AI model to analyze input data and extract important information.

[0961] "Means for analyzing a user's emotions using emotion recognition software" refers to means for analyzing a user's emotions using emotion recognition software.

[0962] This invention is a system for improving the efficiency of a meeting and quickly deriving an optimal conclusion. This system operates in cooperation with a server, a terminal, and a user.

[0963] Hardware and Software Used

[0964] Hardware: Servers, terminals (PCs, tablets, smartphones)

[0965] Software: Generative AI models (e.g. GPT-4), emotion recognition software (e.g. IBM Watson Tone Analyzer)

[0966] System Overview

[0967] 1. Data Collection

[0968] The user inputs the meeting agenda and opinions into the terminal.

[0969] The terminal transmits the input data to the server.

[0970] The server retrieves the results of past meetings from a database.

[0971] 2. Data Analysis

[0972] The server feeds a generative AI model (e.g., GPT-4) with the meeting agenda, participant opinions, and results of past meetings.

[0973] The server uses a generative AI model to analyze the input data and extract key points.

[0974] The server analyzes the user's emotions using emotion recognition software (e.g., IBM Watson Tone Analyzer).

[0975] 3. Inferring conclusions

[0976] The server uses a generative AI model to automatically generate optimal conclusions from the analysis results.

[0977] The server uses the results of emotion recognition software to adjust its conclusions depending on the user's emotions.

[0978] 4. Presentation of results

[0979] The server transmits the best guess to the terminal.

[0980] The terminal displays the optimal conclusion to the user.

[0981] Examples

[0982] For example, if the topic of the meeting is "New Product Launch Strategy", the user might enter:

[0983] Meeting Agenda: New Product Launch Strategy

[0984] Participant opinions: "I think the new product will be popular with younger generations" "I think the cost is too high"

[0985] Outcome of past meetings: "The new product was priced too high and didn't sell."

[0986] Example prompt:

[0987] The topic of the meeting is "New product launch strategy." The opinions of the participants are "I think the new product will be popular with young people" and "I think the cost is too high." The outcome of a past meeting was "The new product was priced too high and didn't sell." Based on this information, please infer the best conclusion.

[0988] The system can improve the efficiency of meetings and quickly reach optimal conclusions that take into account the opinions and feelings of participants.

[0989] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0990] Step 1:

[0991] The user inputs the meeting agenda and opinions into the terminal.

[0992] Input: Meeting topic: "New product launch strategy", participant opinions: "I think the new product will be popular with younger generations" and "Isn't the cost too high?"

[0993] Output: Data entered into the terminal

[0994] Step 2:

[0995] The terminal transmits the input data to the server.

[0996] Input: Meeting topic and comments entered by the user

[0997] Output: Data sent to the server

[0998] Step 3:

[0999] The server retrieves the results of past meetings from a database.

[1000] Input: Database query

[1001] Output: Results of past meetings: "The price of the new product was too high and it didn't sell."

[1002] Step 4:

[1003] The server feeds a generative AI model (e.g., GPT-4) with the meeting agenda, participant opinions, and results of past meetings.

[1004] Input: meeting agendas, participant comments, results of past meetings

[1005] Output: The data fed into the generative AI model

[1006] Step 5:

[1007] The server uses a generative AI model to analyze the input data and extract key points.

[1008] Input: Data fed into the generative AI model

[1009] Data processing: Generative AI models analyze data and extract key takeaways

[1010] Output: Key point: "It is likely to be popular among young people, but there are concerns about its high cost."

[1011] Step 6:

[1012] The server analyzes the user's emotions using emotion recognition software (e.g., IBM Watson Tone Analyzer).

[1013] Input: User opinion data

[1014] Data processing: Emotion recognition software analyzes user emotions

[1015] Output: User sentiment analysis result: "Positive"

[1016] Step 7:

[1017] The server uses a generative AI model to automatically generate optimal conclusions from the analysis results.

[1018] Input: Key points, user sentiment analysis results

[1019] Data processing: Generative AI models generate optimal conclusions

[1020] Output: Optimal conclusion: "Review the price of the new product and strengthen the marketing strategy for younger generations."

[1021] Step 8:

[1022] The server uses the results of emotion recognition software to adjust its conclusions depending on the user's emotions.

[1023] Input: Optimal conclusion, user sentiment analysis results

[1024] Data manipulation: Adjusting conclusions based on user sentiment

[1025] Output: Adjusted conclusion: "Review the price of the new product and strengthen the marketing strategy for younger generations (positive direction)."

[1026] Step 9:

[1027] The server transmits the best guess to the terminal.

[1028] Input: Adjusted conclusion

[1029] Output: conclusion sent to terminal

[1030] Step 10:

[1031] The terminal displays the optimal conclusion to the user.

[1032] Input: The conclusion sent by the server

[1033] Output: Conclusion displayed to the user: "Review the price of the new product and strengthen the marketing strategy for younger generations."

[1034] In this way, the system analyzes meeting agendas, opinions, and past results, and takes into account the user's emotions to arrive at optimal conclusions.

[1035] (Application example 2)

[1036] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the smart glasses 214 will be referred to as a "terminal".

[1037] With conventional conference systems, it was difficult to prepare a meeting's conclusion in advance, which often resulted in lengthy meetings. In addition, there was a problem that efficient management became difficult as the number of meetings increased. Furthermore, in the manufacturing process, it was difficult to collect and analyze data from each step and propose optimal manufacturing procedures and improvements, and adjustments to work plans were not made that took into account the emotions of workers. To solve these problems, a system that could simultaneously improve meeting efficiency and optimize the manufacturing process was needed.

[1038] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1039] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for collecting and analyzing data on each step in the manufacturing process and proposing optimal manufacturing procedures and improvements, and a means for recognizing the emotions of workers and adjusting the work plan based on the emotions. This makes it possible to improve the efficiency of meetings and optimize the manufacturing process.

[1040] A "means for preparing meeting conclusions in advance" is a method for analyzing the meeting agenda, the opinions of participants, and the results of past meetings to generate optimal conclusions in advance.

[1041] "Means of shortening the time of meetings" are methods for making meetings more efficient and shortening the time required for meetings.

[1042] "Methods to reduce the number of meetings" are methods for evaluating the necessity of meetings and reducing unnecessary meetings.

[1043] "A function that can predict the optimal conclusion at any given time from an objective point of view" refers to a function that enables a meeting to reach an optimal conclusion based on collected data while the meeting is in progress.

[1044] "A means of collecting and analyzing data from each step in the manufacturing process and proposing optimal manufacturing procedures and improvements" is a method for proposing optimal manufacturing procedures and improvements by collecting and analyzing data generated at each step of the manufacturing line.

[1045] A "means for recognizing worker emotions and adjusting a work plan based on the emotions" is a method for recognizing a worker's emotional state and adjusting a work plan based on that information.

[1046] The system for carrying out the present invention is capable of simultaneously improving the efficiency of meetings and optimizing the manufacturing process. A specific embodiment of this system will be described below.

[1047] Hardware and Software Used

[1048] Hardware

[1049] Factory robots: Robots used in manufacturing lines (e.g. general-purpose robot arms)

[1050] Emotion recognition camera: A camera to recognize the emotions of workers (e.g. high-precision camera)

[1051] Data collection sensors: Sensors for collecting data at each step of the manufacturing process (e.g. IoT sensors)

[1052] software

[1053] AI Models: AI models for data analysis and optimization (e.g. TensorFlow, PyTorch)

[1054] Emotion recognition software: Software to analyze the emotions of workers (e.g. Microsoft Azure Emotion API)

[1055] Data analysis tools: Tools for pre-processing and analyzing data (e.g. Apache Spark)

[1056] System Operation

[1057] Data collection

[1058] The server uses IoT sensors to collect data generated at each step of the production line (time, error rate, worker performance, etc.) and also collects worker emotion data using an emotion recognition camera.

[1059] Data analysis

[1060] The server preprocesses the collected data using Apache Spark and inputs it into an AI model built using TensorFlow and PyTorch to optimize the manufacturing process.

[1061] emotion recognition

[1062] The server uses the Microsoft Azure Emotion API to analyze the emotion data of workers and adjusts the work plan based on the analysis results.

[1063] Optimization suggestions

[1064] The server then proposes optimal manufacturing procedures and improvements based on the AI ​​model, adjusting the suggestions according to the worker's emotional state.

[1065] Examples

[1066] For example, if there is a bottleneck on a production line, the server might do the following:

[1067] Collect data from sensors to identify at which step delays are occurring.

[1068] Emotion-recognition cameras check workers' stress levels.

[1069] The AI ​​model suggests optimal improvement measures (for example, automating certain steps or adjusting worker break times).

[1070] Examples of prompt statements

[1071] "Collect data from the production line and analyze the efficiency of each step. Collect emotional data from workers and adjust work plans according to their stress levels. Suggest optimal production procedures and areas for improvement."

[1072] In this way, a system is created that simultaneously improves meeting efficiency and optimizes the manufacturing process.

[1073] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1074] Step 1:

[1075] The server uses IoT sensors to collect data (time, error rate, worker performance, etc.) generated at each step of the production line. The input is the sensor data for each step, and the output is a set of collected data. Specifically, the server obtains data from the sensors in real time and stores it in a database.

[1076] Step 2:

[1077] The server collects the workers' emotional data using an emotion recognition camera. The input is the camera footage, and the output is the analyzed emotional data. Specifically, the camera footage is captured in real time, and the emotional state is analyzed using emotion recognition software.

[1078] Step 3:

[1079] The server preprocesses the collected data using Apache Spark. The input is sensor data and emotion data, and the output is a preprocessed dataset. Specifically, it fills in missing values ​​in the data, removes outliers, and converts it into a format suitable for AI models.

[1080] Step 4:

[1081] The server inputs the preprocessed data into an AI model to optimize the manufacturing process. The input is the preprocessed data set, and the output is the optimal manufacturing procedure or suggestions for improvements. Specifically, the data is input into an AI model built using TensorFlow and PyTorch to generate the optimization results.

[1082] Step 5:

[1083] The server analyzes the worker's emotional data using the Microsoft Azure Emotion API. The input is the emotional data, and the output is the evaluation result of the emotional state. Specifically, the server sends the emotional data to the API and obtains the evaluation result in return.

[1084] Step 6:

[1085] The server proposes optimal manufacturing procedures and improvements generated by the AI ​​model. The input is the optimization results and the evaluation results of the emotional state, and the output is an adjusted work plan. Specifically, the server adjusts the work plan based on the optimization results and the emotional state and presents it to the worker.

[1086] Step 7:

[1087] The user executes the manufacturing process based on the work plan presented by the server. The input is the adjusted work plan, and the output is the result of the executed manufacturing process. Specifically, the user operates the manufacturing line according to the work plan and feeds back the results to the server.

[1088] 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.

[1089] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. 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 is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1090] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1091] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1092] [Third embodiment]

[1093] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1094] 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.

[1095] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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 wide area network (WAN) and / or a local area network (LAN).

[1096] 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.

[1097] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, 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.

[1098] 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 surroundings of user 20 (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).

[1099] 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. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1100] Fig. 6 shows an example of 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.

[1101] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1102] 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.

[1103] In the headset type terminal 314, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1104] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1105] "Example 1"

[1106] The system of the present invention is provided with a means for preparing a meeting conclusion in advance, a means for shortening the meeting time, and a means for reducing the number of meetings themselves. Specifically, as a means for preparing a meeting conclusion in advance, the system has a function for collecting meeting agendas and participant opinions and automatically generating a conclusion based on these. In addition, as a means for shortening meeting time, the system has a scheduling function and agenda management function for making the progress of meetings more efficient. Furthermore, as a means for reducing the number of meetings themselves, the system has an optimization function for scheduling only necessary meetings.

[1107] "Example 2"

[1108] As a function that can predict the optimal conclusion at that time from an objective point of view, it has the function of analyzing the meeting agenda, the opinions of participants, the results of past meetings, etc., and predicting the optimal conclusion based on the results. A specific example would be a function that uses AI technology to analyze the meeting agenda and the opinions of participants, and automatically generates the optimal conclusion based on the results.

[1109] The process flow of each embodiment will be described below.

[1110] "Example 1"

[1111] Step 1: Collect the meeting agenda and participants' opinions. This will be the basis for formulating the meeting conclusions in advance.

[1112] Step 2: Automatically generate meeting conclusions based on the collected agenda and opinions, which can shorten the meeting time.

[1113] Step 3: Use scheduling and agenda management features to streamline the meeting, further shortening the meeting time.

[1114] Step 4: Use optimization features to schedule only the meetings you need, which can reduce the number of meetings you have.

[1115] "Example 2"

[1116] Step 1: Collect meeting agendas, participant opinions, past meeting results, etc. This will provide the basic data to objectively estimate the optimal conclusion at that time.

[1117] Step 2: Analyze the collected data using AI technology. This analysis will predict the optimal conclusion at that point in time.

[1118] Step 3: Based on the inferred conclusion, the conclusion of the meeting is automatically generated, which makes it possible to shorten the meeting time and reduce the number of meetings.

[1119] Example 1

[1120] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1121] In the modern business environment, meetings are important places for decision-making, but they often take too long, have vague conclusions, or are unnecessary. This reduces work efficiency and wastes resources. Therefore, there is a need for a system that can quickly and accurately make meeting conclusions, shorten meeting times, and reduce unnecessary meetings.

[1122] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1123] In this invention, the server includes a means for collecting meeting agendas and participant opinions and automatically generating a conclusion based on them, a means having a scheduling function and an agenda management function for making the meeting proceed efficiently, and a means having an optimization function for scheduling only necessary meetings. This makes it possible to quickly and accurately create a meeting conclusion, shorten the meeting time, and reduce unnecessary meetings.

[1124] A "meeting agenda" is the specific themes or topics to be discussed at a meeting.

[1125] "Participant input" refers to ideas, suggestions, and feedback provided by members attending the meeting.

[1126] "Means for automatically generating conclusions" refers to a function that uses artificial intelligence and algorithms to automatically create optimal conclusions based on collected topics and opinions.

[1127] The "scheduling function" refers to the function that optimizes meeting dates and times and participant schedules to set up meetings efficiently.

[1128] The "agenda management function" refers to the function of organizing the topics to be discussed in a meeting and managing the progress.

[1129] "Optimization function" refers to a function for evaluating the necessity of meetings and reducing duplicate or unnecessary meetings.

[1130] A "function that can make inferences from an objective perspective" is a function that uses data and algorithms to derive optimal conclusions without relying on subjectivity.

[1131] The present invention is a system for optimizing the efficiency of a conference, and is realized by a server, a terminal, and a user each fulfilling their respective roles. A specific embodiment of this system will be described below.

[1132] 1. A way to prepare meeting conclusions in advance

[1133] The server uses Google Calendar API and Microsoft Outlook API to collect meeting agendas and participant opinions. This allows it to obtain the agenda for the next meeting. It also collects participant opinions from communication tools such as Slack and Microsoft Teams.

[1134] Examples:

[1135] The server calls the Google Calendar API to get the agenda for the next meeting.

[1136] The server uses the Slack API to collect participant opinions from the meeting channel.

[1137] Based on the collected data, the server inputs prompts into a generative AI model (e.g., OpenAI's GPT-4), which generates a conclusion based on the input agenda and opinions.

[1138] Examples:

[1139] Prompt: The topic of the meeting is "Marketing strategy for a new product," and the opinions of the participants are "We should strengthen social media advertising," "We should also consider TV commercials," and "We have a limited budget, so we should choose an efficient method." Please generate a conclusion based on these.

[1140] The generated conclusions are stored in a database by the server and made accessible to the user.

[1141] 2. Ways to shorten meeting times

[1142] To streamline meetings, the server optimizes meeting schedules using Google Calendar API and Microsoft Outlook API, and manages agendas using task management tools such as Trello and Asana.

[1143] Examples:

[1144] The server calls the Google Calendar API to get the upcoming meeting schedule.

[1145] The server proposes an optimal schedule taking into account the free time of the participants.

[1146] The server calls the Trello API and creates the meeting agenda as a card.

[1147] The server provides real-time updates on the progress of the agenda.

[1148] 3. Ways to reduce the number of meetings

[1149] The server retrieves and analyzes existing meeting schedules using Google Calendar API and Microsoft Outlook API, detects duplicates and unnecessary meetings, and uses a generative AI model to evaluate the necessity of meetings and propose optimal schedules.

[1150] Examples:

[1151] The server calls the Google Calendar API to get the meeting schedule for the next week.

[1152] The server inputs prompt sentences into the generative AI model to assess the need for a meeting.

[1153] Prompt: Please optimize your meeting schedule for the next week. The current schedule is as follows: Monday: Meeting A, Tuesday: Meeting B, Wednesday: Meeting C. Please reduce overlapping and unnecessary meetings.

[1154] The generative AI model generates suggestions for reducing unnecessary meetings, and the server updates the schedule based on the suggestions.

[1155] This system makes it possible to quickly and accurately draw up meeting conclusions, shorten meeting times, and reduce unnecessary meetings.

[1156] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1157] Step 1:

[1158] The server calls the Google Calendar API or Microsoft Outlook API to get the meeting agenda. As input, it provides the schedule information of the upcoming meeting. The server saves the agenda information obtained from the API in a database.

[1159] Specific behavior:

[1160] The server calls the Google Calendar API to get the agenda for the next meeting.

[1161] The obtained agenda information is stored in a database.

[1162] Step 2:

[1163] The server uses APIs of Slack and Microsoft Teams to collect participants' opinions. As input, it provides the channel information of the meeting. The server stores the opinion information obtained from the API in a database.

[1164] Specific behavior:

[1165] The server uses the Slack API to collect participant opinions from the meeting channel.

[1166] The obtained opinion information is stored in a database.

[1167] Step 3:

[1168] The server inputs the collected topics and opinions into the generative AI model. As input, it provides text data of the topics and opinions. The generative AI model generates a conclusion based on the input data and outputs it to the server.

[1169] Specific behavior:

[1170] The server converts the agenda and opinions into text format and inputs them as prompts to the generative AI model.

[1171] The generative AI model analyzes the prompt and generates an optimal conclusion.

[1172] The server receives the generated conclusions and stores them in a database.

[1173] Step 4:

[1174] The server uses Google Calendar API and Microsoft Outlook API to optimize meeting schedules. As input, you provide the schedule information of the participants. The server calculates the optimal schedule and proposes it as output.

[1175] Specific behavior:

[1176] The server calls the Google Calendar API to obtain the participants' schedule information.

[1177] Based on the acquired schedule information, the optimal meeting schedule is calculated.

[1178] The server proposes an optimal schedule and stores it in a database.

[1179] Step 5:

[1180] The server uses Trello or Asana API to manage the agenda. As input, we provide the meeting agenda information. The server creates the agenda as cards and manages the progress.

[1181] Specific behavior:

[1182] The server calls the Trello API and creates the meeting agenda as a card.

[1183] The server provides real-time updates on the progress of the agenda.

[1184] Step 6:

[1185] The server uses Google Calendar API and Microsoft Outlook API to analyze the existing meeting schedule. As input, you provide the meeting schedule information for the next week. The server detects overlapping and unnecessary meetings and suggests an optimized schedule as output.

[1186] Specific behavior:

[1187] The server calls the Google Calendar API to get the meeting schedule for the next week.

[1188] The server analyzes the schedule to detect overlapping and unnecessary meetings.

[1189] The server inputs prompt sentences into the generative AI model to assess the need for a meeting.

[1190] A generative AI model generates suggestions to cut down on unnecessary meetings.

[1191] The server updates the schedule based on the suggestions.

[1192] (Application example 1)

[1193] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1194] Meetings and discussions in factories are important for improving productivity, but they often take too much time and there are many pointless meetings. It is also difficult to efficiently collect opinions from each department and reach optimal conclusions. To solve these problems, there is a need to streamline and optimize meetings.

[1195] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the time of the meeting, a means for reducing the number of meetings, a means for collecting agendas and opinions from each department in the factory and automatically generating a conclusion using a generative AI model, a means for optimizing the meeting schedule and efficiently managing the agenda, and a means for scheduling only necessary meetings and reducing unnecessary meetings. This makes it possible to make meetings and discussions in the factory more efficient and improve productivity.

[1196] "A means of preparing meeting conclusions in advance" is a function that collects meeting agendas and participants' opinions, and automatically generates conclusions based on them.

[1197] "Means of shortening meeting times" refer to scheduling and agenda management functions to make meetings more efficient.

[1198] "A means to reduce the number of meetings" refers to an optimization function that schedules only necessary meetings.

[1199] "A function that can predict the optimal conclusion at any given time from an objective perspective" is a function that automatically derives the optimal conclusion based on collected information.

[1200] "Means of collecting topics and opinions from each department within the factory" refers to a function that visits each department within the factory and collects opinions using voice recognition technology.

[1201] "Means for automatically generating a conclusion using a generative AI model" refers to a function that automatically generates a conclusion using a generative AI model based on collected topics and opinions.

[1202] "Means for optimizing meeting schedules and efficiently managing agendas" refers to a function for optimizing meeting schedules and efficiently managing agendas using scheduling software.

[1203] "A means of scheduling only necessary meetings and reducing unnecessary meetings" is a function that uses AI to evaluate the necessity of meetings and reduce unnecessary meetings.

[1204] The system for carrying out the present invention is a tool for making meetings and conferences in a factory more efficient and improving productivity. A specific embodiment of this system will be described below.

[1205] Hardware and Software Used

[1206] Hardware: Factory robots, servers, network equipment

[1207] Software: Generative AI models (e.g. OpenAI GPT-4), database management systems (e.g. MySQL), scheduling software (e.g. Google Calendar API)

[1208] Data processing and calculation

[1209] Agenda collection

[1210] The factory robot travels around each department in the factory and collects opinions using voice recognition technology. The collected data is sent to a server and stored in a database. This allows opinions from each department to be efficiently collected.

[1211] Automatic conclusion generation

[1212] The server automatically generates conclusions using a generative AI model (e.g. GPT-4) based on the collected agenda and opinions. The generated conclusions are stored in a database and notified to each department as necessary. This allows the conclusions of meetings to be generated quickly.

[1213] Scheduling and Agenda Management

[1214] The server optimizes the meeting schedule using scheduling software (e.g., Google Calendar API). It also efficiently manages the agenda for each meeting using the agenda management function, allowing the meetings to proceed smoothly.

[1215] Optimizing the number of meetings

[1216] The server uses AI to evaluate the necessity of meetings and schedules only the necessary meetings, thus reducing unnecessary meetings.

[1217] Examples

[1218] For example, if a meeting is held within a factory to introduce a new product line, the process may look like this:

[1219] 1. Gather input from each department about the new product line.

[1220] 2. Based on the collected opinions, the generative AI model automatically generates a conclusion.

[1221] 3. Use scheduling software to schedule the best possible meeting.

[1222] 4. Schedule only the meetings you need and cut down on the unnecessary ones.

[1223] Examples of prompt statements

[1224] Here is an example of a prompt to be input to the generative AI model:

[1225] You have collected opinions regarding the introduction of a new product line. Generate a conclusion based on the opinions below.

[1226] Opinion 1: We should install new machines to improve the efficiency of our production line.

[1227] Opinion 2: It is better to improve the existing machine to reduce costs.

[1228] Statement 3: The introduction of a new product line requires employee training.

[1229] Use these opinions to generate the best conclusion.

[1230] In this way, factory meetings can be made more efficient and productivity can be improved.

[1231] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1232] Step 1:

[1233] The factory robot travels around each department in the factory and collects opinions using voice recognition technology. The input is the voice opinions from the staff in each department, and the output is the opinion data in text format. The robot uses voice recognition software to convert the voice into text and sends it to the server.

[1234] Step 2:

[1235] The server stores the opinion data sent from the robot in a database. The input is the opinion data in text format, and the output is the opinion data stored in the database. The server stores the data using a database management system (e.g., MySQL).

[1236] Step 3:

[1237] The server automatically generates a conclusion using a generative AI model (e.g. GPT-4) based on the opinion data stored in the database. The input is the opinion data obtained from the database, and the output is the generated conclusion. The server inputs a prompt sentence into the generative AI model to generate a conclusion.

[1238] Step 4:

[1239] The server stores the generated conclusions in a database and notifies each department as necessary. The input is the generated conclusion, and the output is the conclusion stored in the database and the notified conclusion. The server sends the conclusions to each department using a notification system.

[1240] Step 5:

[1241] The server optimizes the meeting schedule using scheduling software (e.g. Google Calendar API). The input is the meeting agenda and attendee information, and the output is the optimized meeting schedule. The server uses the scheduling software to set the schedule.

[1242] Step 6:

[1243] The server efficiently manages the agenda of each meeting through the agenda management function. The input is the meeting agenda information, and the output is the managed agenda information. The server manages the agenda using the agenda management software.

[1244] Step 7:

[1245] The server uses AI to assess the need for meetings and schedule only those that are necessary. The input is meeting agenda and participant information, and the output is an optimized meeting schedule. The server uses AI models to assess the need for meetings and reduce unnecessary meetings.

[1246] Example 2

[1247] Next, a second embodiment of the second form will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1248] In conventional conference systems, it was difficult to prepare a meeting's conclusion in advance, and meetings often dragged on. In addition, as the number of meetings increased, the burden on participants increased, making efficient decision-making difficult. Furthermore, there was a demand for a system that could objectively analyze meeting topics and participants' opinions to arrive at optimal conclusions.

[1249] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1250] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a means for collecting, preprocessing, and analyzing meeting agendas, participants' opinions, and results of past meetings, a means for predicting an optimal conclusion using a generative AI model, and a means for outputting the predicted conclusion, thereby making it possible to improve the efficiency of meetings and derive optimal conclusions.

[1251] A "means for preparing a meeting conclusion in advance" is a method or device for preparing a conclusion based on existing information before the meeting begins.

[1252] A "means for shortening the duration of a meeting" is a method or device for making the meeting proceed more efficiently and shortening the time required for the meeting.

[1253] A "means for realizing a reduction in the number of meetings" is a method or device for reducing the number of necessary meetings and reducing the overall number of meetings.

[1254] A "means for collecting meeting agendas, participant opinions, and results of past meetings" is a method or device for collecting information related to meetings.

[1255] A "preprocessing means" is a method or device for preparing collected data in a form that is easy to analyze.

[1256] An "analyzing means" is a method or device for analyzing the pre-processed data and extracting significant information.

[1257] A "means for inferring optimal conclusions using a generative AI model" is a method or device for using artificial intelligence technology to derive optimal conclusions from collected and analyzed data.

[1258] A "means for outputting an inferred conclusion" is a method or device for providing a user with the conclusion inferred by the generative AI model.

[1259] The present invention is directed to a system for improving the efficiency of a meeting and deriving an optimal conclusion. A specific embodiment of this system will be described below.

[1260] The server generates programs to collect, preprocess, and analyze meeting agendas, participant opinions, and past meeting results. The programs use natural language processing libraries (e.g., NLTK, spaCy) and generative AI models (e.g., GPT-4) to process and compute the data.

[1261] First, the server connects to a database and collects meeting agendas, participant opinions, and results of past meetings. For example, it obtains the minutes and participant opinions of a meeting on "New Product Launch Strategy."

[1262] The server then pre-processes the collected data, which involves cleaning the text data, tokenizing it, removing stop words, etc., making the data easier to analyze.

[1263] The server then feeds the pre-processed data into a generative AI model to extract key keywords and themes, such as "market research," "competitive analysis," and "marketing strategy."

[1264] Next, the server uses the generative AI model to predict the optimal conclusion based on the analysis results, taking into account the results of past meetings and the opinions of the participants. For example, the generative AI model is given a prompt such as, "Please predict the optimal conclusion regarding the market launch strategy for a new product."

[1265] Finally, the server outputs the inferred conclusion to the terminal. The user can confirm this conclusion through the terminal. For example, the conclusion "Strengthen market research and develop a marketing strategy based on competitive analysis" is confirmed on the screen of the terminal.

[1266] As a concrete example, consider a case where a user holds a meeting and sets the topic as "New product launch strategy." Participants express their opinions and note that similar topics have been discussed in past meetings. In this case, the server inputs the following prompt sentence into the generative AI model:

[1267] Example prompt:

[1268] "Based on the agenda and participants' opinions of a meeting about a new product launch strategy, infer the best outcome. Also take into account the results of previous meetings."

[1269] By inputting this prompt into a generative AI model, the server can infer the optimal conclusion and provide it to the user.

[1270] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1271] Step 1: Data collection

[1272] The server collects meeting agendas, participant opinions, and past meeting results by connecting to a database and retrieving relevant meeting minutes and speech records.

[1273] Input: meeting agendas, participant comments, results of past meetings

[1274] Output: Raw data collected

[1275] What happens: The server uses an SQL query to retrieve meeting minutes and participant opinions on "New Product Launch Strategy" from the database.

[1276] Step 2: Data Preprocessing

[1277] The server pre-processes the collected data, specifically cleaning the text data, tokenizing it, removing stop words, etc.

[1278] Input: Raw data collected

[1279] Output: Preprocessed data

[1280] Specific operation: The server removes unnecessary symbols and spaces from the acquired text data, tokenizes it, and removes stop words. This is done using a natural language processing library (e.g. NLTK, spaCy).

[1281] Step 3: Data analysis

[1282] The server feeds the pre-processed data into a generative AI model to extract key keywords and themes.

[1283] Input: Preprocessed data

[1284] Output: Extracted keywords and themes

[1285] How it works: The server inputs the preprocessed text data into a generative AI model (e.g., GPT-4) and extracts important keywords such as "market research," "competitive analysis," and "marketing strategy."

[1286] Step 4: Inferring conclusions

[1287] The server uses a generative AI model to infer the optimal conclusion based on the analysis results.

[1288] Input: Extracted keywords or themes

[1289] Output: Inferred conclusion

[1290] Specific operation: Based on the extracted keywords and themes, the server inputs a prompt to the generative AI model: "Please predict the optimal conclusion regarding the new product's market launch strategy." The generative AI model considers the results of past meetings and the opinions of participants and generates the conclusion: "Strengthen market research and develop a marketing strategy based on competitive analysis."

[1291] Step 5: Output the results

[1292] The server outputs the inferred conclusion to the terminal, where the user can confirm the conclusion.

[1293] Input: Inferred conclusion

[1294] Output: conclusions provided to the user

[1295] Specific operation: The server transmits the generated conclusion to the terminal, and the user confirms the conclusion "strengthen market research and develop a marketing strategy based on competitive analysis" on the terminal screen.

[1296] (Application example 2)

[1297] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1298] In conventional conference systems, it was difficult to prepare the conclusion of a meeting in advance, which resulted in long meeting times and an increase in the number of meetings. In addition, it was difficult to objectively predict the optimal conclusion, which meant that it took a lot of time and effort to align the understanding within the organization.

[1299] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1300] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for acquiring the results of past meetings from a database, a means for automatically generating an optimal conclusion using a generative AI model, and a means for outputting the generated conclusion. This makes it possible to improve the efficiency of meetings and automatically generate optimal conclusions.

[1301] The "means for creating a meeting conclusion in advance" is a function for automatically generating a conclusion based on the agenda before the meeting begins.

[1302] "Means of shortening meeting times" refers to functions that make meetings more efficient and shorten the amount of time required.

[1303] "Means for reducing the number of meetings" refers to a function for evaluating the necessity of meetings and reducing unnecessary meetings.

[1304] "A function that can predict the optimal conclusion at that time from an objective perspective" is a function that automatically predicts the most appropriate conclusion based on data collected while the meeting is in progress.

[1305] The "means for acquiring the results of past meetings from a database" is a function for searching and acquiring the results of meetings that were previously held from a database.

[1306] "Means for automatically generating optimal conclusions using a generative AI model" refers to a function that uses artificial intelligence technology to automatically generate optimal conclusions based on collected data.

[1307] The "means for outputting the generated conclusion" is a function for displaying the generated conclusion to the user.

[1308] In the system for carrying out the present invention, a server, a terminal, and a user work in cooperation with each other. The server includes a means for preparing a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for acquiring the results of past meetings from a database, a means for automatically generating an optimal conclusion using a generative AI model, and a means for outputting the generated conclusion.

[1309] The server first collects the meeting agenda and the opinions of the participants. This includes the function of collecting information entered by users in real time using terminals (such as smartphones and tablets). Next, the server retrieves the results of past meetings from a database and automatically generates optimal conclusions based on this data using a generative AI model.

[1310] The generative AI model uses advanced natural language processing techniques such as OpenAI's GPT-3. The server inputs the collected topics, opinions, and past results as prompts into the generative AI model to generate the optimal conclusion. The generated conclusion is displayed to the user through the terminal.

[1311] As a concrete example, the following prompt sentence is input to the generative AI model:

[1312] Agenda: Improving production line efficiency

[1313] opinion:

[1314] Person A: We should get new machines.

[1315] Person B: We should review our work procedures.

[1316] Person C: Working hours should be adjusted.

[1317] Past results:

[1318] Reconfiguring production lines increases efficiency by 10%

[1319] New software implementation reduces error rate by 5%

[1320] Generate the best conclusion.

[1321] Based on this prompt, the generative AI model outputs the optimal conclusion, such as "Production efficiency can be further improved by combining the introduction of new machinery with a review of work procedures."

[1322] This system makes it possible to streamline meetings and automatically generate optimal conclusions, and can handle the many different views within an organization. The hardware used includes mobile devices such as smartphones and tablets, and the software uses Python, SQLite, and OpenAI API.

[1323] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1324] Step 1:

[1325] The server collects the meeting agenda and the opinions of the participants. The user inputs the meeting agenda and their opinions using a terminal (such as a smartphone or tablet). The input data is sent to the server and stored in a database. In this way, the meeting agenda and the opinions of the participants are collected.

[1326] Step 2:

[1327] The server retrieves the results of past conferences from the database. The server queries the database to search for the results of past conferences. The retrieved data is temporarily stored in the server. In this way, the results of past conferences are retrieved.

[1328] Step 3:

[1329] The server generates prompt sentences based on the collected topics, opinions, and past results. The server converts the collected data into text format and creates prompt sentences to input to the generative AI model. This generates prompt sentences to input to the generative AI model.

[1330] Step 4:

[1331] The server automatically generates an optimal conclusion using a generative AI model. The server inputs the generated prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) and generates an optimal conclusion. The generative AI model performs data calculations based on the input prompt sentence and outputs an optimal conclusion. In this way, the optimal conclusion is automatically generated.

[1332] Step 5:

[1333] The server transmits the generated conclusion to the terminal and displays it to the user. The server transmits the generated conclusion to the terminal and allows the user to view it. The user can check the generated conclusion through the terminal. Thus, the generated conclusion is displayed to the user.

[1334] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1335] "Example 1"

[1336] One embodiment of the present invention is a system that combines an emotion engine that recognizes the emotions of a user. This system includes a means for creating a meeting conclusion in advance, a means for shortening the time of the meeting, a means for reducing the number of meetings, and a function for predicting the optimal conclusion at that time from an objective point of view. The emotion engine recognizes the user's emotions, and controls the means for creating a meeting conclusion in advance based on the emotions. Specifically, if the user's emotions are positive, a meeting conclusion is created in advance in a positive direction. Conversely, if the user's emotions are negative, a meeting conclusion is created in advance in a cautious direction.

[1337] "Example 2"

[1338] The emotion engine also controls a function that recognizes the user's emotions and predicts the optimal conclusion at that time from an objective point of view based on those emotions. Specifically, if the user's emotions are positive, the optimal conclusion at that time is predicted to be in the positive direction. Conversely, if the user's emotions are negative, the optimal conclusion at that time is predicted to be in the cautious direction. In this way, by taking the user's emotions into consideration, it becomes possible to create a more appropriate meeting conclusion in advance and predict the optimal conclusion at that time.

[1339] The process flow of each embodiment will be described below.

[1340] "Example 1"

[1341] Step 1: A user starts a conference.

[1342] Step 2: The emotion engine recognizes the user's emotion.

[1343] Step 3: Pre-create a meeting conclusion based on the emotions recognized by the emotion engine.

[1344] Step 4: Present the pre-created conclusions to the user.

[1345] Step 5: The user reviews the proposed conclusions and modifies them if necessary.

[1346] "Example 2"

[1347] Step 1: A user starts a conference.

[1348] Step 2: The emotion engine recognizes the user's emotion.

[1349] Step 3: Based on the emotions identified by the emotion engine, an objective guess is made as to the best outcome at that point in time.

[1350] Step 4: Present the best guess to the user.

[1351] Step 5: The user reviews the proposed conclusions and modifies them if necessary.

[1352] Example 1

[1353] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1354] In conventional conference systems, it was difficult to efficiently reach a meeting conclusion, and meetings often dragged on. In addition, there was a tendency for the number of meetings to increase, which increased the burden on participants. Furthermore, the conclusions of meetings tended to be subjective and often influenced by the emotions of participants. There is a need to solve these problems and improve the efficiency and optimization of meetings.

[1355] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1356] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a means for recognizing the user's emotions and adjusting the meeting conclusion based on the emotions, and a function for predicting the optimal conclusion at that time from an objective point of view. This makes it possible to efficiently create a meeting conclusion, shorten the meeting time, and select only the necessary meetings. In addition, by adjusting the conclusion taking the user's emotions into account, a more objective and appropriate conclusion can be derived.

[1357] "A means of preparing meeting conclusions in advance" refers to a function that collects meeting agendas and participants' opinions, and automatically generates conclusions based on them.

[1358] "Means of shortening meeting times" refers to functions that provide scheduling and agenda management functions to make meetings more efficient.

[1359] "Means of reducing the number of meetings" refers to the ability to provide optimization functions to schedule only necessary meetings.

[1360] "Means for recognizing a user's emotions and adjusting the conclusion of the meeting based on those emotions" refers to a function for analyzing a user's emotions and adjusting the conclusion of the meeting in a positive or cautious direction depending on those emotions.

[1361] "A function that can predict the optimal conclusion at any given time from an objective perspective" refers to a function that automatically predicts the most appropriate conclusion based on collected data and user emotions.

[1362] The present invention relates to a system for improving the efficiency and optimizing a conference. A specific embodiment of the system will be described below.

[1363] A means of preparing meeting conclusions in advance

[1364] The server uses APIs of common communication tools (e.g., communication platforms and messaging applications) to collect meeting agendas and participant opinions. The collected data is stored in a database. The server then uses a generative AI model (e.g., a natural language processing model) to automatically generate a conclusion based on the collected data. Specifically, the server inputs the following prompt sentence into the generative AI model:

[1365] "The topic of the meeting is XX, and the opinions of the participants are △△. Please generate a conclusion based on this."

[1366] The generated conclusions are again stored in the database.

[1367] A way to shorten meeting times

[1368] The server optimizes meeting schedules using scheduling software (e.g., a calendar application) to automatically adjust meeting start and end times, and uses a project management tool (e.g., a task management application) to manage agendas by creating tasks for each agenda item and tracking their progress.

[1369] A means to reduce the number of meetings

[1370] The server uses machine learning algorithms to analyze past meeting data and select only necessary meetings. Specifically, it uses a Python machine learning library to build a model that evaluates the importance of meetings. This model evaluates the necessity of meetings and schedules only high-importance meetings.

[1371] A means of recognizing a user's emotions and adjusting the outcome of a meeting based on those emotions

[1372] The terminal uses an emotion analysis engine (e.g., emotion recognition API) to recognize the user's emotions. The terminal analyzes the user's speech and facial expressions to obtain emotion data. The obtained emotion data is sent to the server. The server adjusts the conclusion based on the emotion data. For example, if the user's emotion is positive, the server corrects the conclusion in a positive direction. Conversely, if the user's emotion is negative, the server corrects the conclusion in a cautious direction.

[1373] Examples

[1374] For example, if the topic of a meeting is "New product launch strategy" and the participants' opinions are "We should conduct an aggressive marketing campaign," we can input the following prompt into the generative AI model:

[1375] "The topic of the meeting should be a new product launch strategy, and the participants' input should be about an aggressive marketing campaign. Use this as a basis for generating conclusions."

[1376] Based on this prompt, the generative AI model generates the conclusion that "it is optimal to conduct an aggressive marketing campaign as a new product launch strategy." If the user's sentiment is positive, the sentiment engine sends this information to the server, which then generates a positive conclusion. For example, it generates the conclusion that "since the user's sentiment is positive, it is recommended to further strengthen the marketing campaign."

[1377] In this way, the system of the present invention realizes efficiency and optimization of meetings.

[1378] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1379] Step 1:

[1380] The server collects the meeting agenda and participant opinions.

[1381] Specifically, the server uses the communication platform's API to obtain the chat log and minutes of the meeting.

[1382] Input: Meeting chat logs, minutes

[1383] Output: Collected topics and opinion data

[1384] Step 2:

[1385] The server stores the collected topics and opinions in a database.

[1386] As a specific operation, the server executes an INSERT query on the database to insert data into the agenda table and the opinion table.

[1387] Input: Collected agenda and opinion data

[1388] Output: Topics and opinions stored in a database

[1389] Step 3:

[1390] The server creates a prompt based on the collected topics and opinions.

[1391] Specifically, the server converts the agenda and opinion data into text format and generates prompt sentences to input into the generative AI model.

[1392] Input: Topics and opinions stored in the database

[1393] Output: Generated prompt statement

[1394] Step 4:

[1395] The server inputs a prompt sentence into the generative AI model and generates a conclusion.

[1396] Specifically, the server calls the API of the generative AI model, inputs a prompt sentence, and generates a conclusion.

[1397] Input: Generated prompt text

[1398] Output: Generated conclusions

[1399] Step 5:

[1400] The server stores the generated conclusions in a database.

[1401] As a specific operation, the server executes an INSERT query on the database to insert data into the conclusion table.

[1402] Input: Generated conclusions

[1403] Output: conclusions stored in a database

[1404] Step 6:

[1405] The server uses scheduling software to optimize the schedule of meetings.

[1406] Specifically, the server uses the calendar application's API to automatically adjust the start and end times of meetings.

[1407] Input: Meeting schedule information

[1408] Output: Optimized meeting schedule

[1409] Step 7:

[1410] The server uses a project management tool to manage the agenda.

[1411] Specifically, the server uses the API of the task management application to create tasks for each agenda item and track their progress.

[1412] Input:Agenda information

[1413] Output: Managed agenda tasks

[1414] Step 8:

[1415] The server analyzes past conference data and selects only the necessary conferences.

[1416] Specifically, the server uses a machine learning algorithm to build a model that evaluates the importance of meetings and selects only meetings with high importance.

[1417] Input: Past meeting data

[1418] Output: Select the required meeting

[1419] Step 9:

[1420] The terminal uses an emotion analysis engine to recognize the user's emotions.

[1421] Specifically, the device uses an emotion recognition API to analyze the user's statements and facial expressions and obtain emotional data.

[1422] Input: User's speech and facial expressions

[1423] Output: The acquired emotion data

[1424] Step 10:

[1425] The terminal transmits the recognized emotion data to the server.

[1426] Specifically, the device sends a POST request to the server with emotion data in JSON format.

[1427] Input: Acquired emotion data

[1428] Output: Emotion data sent to the server

[1429] Step 11:

[1430] The server adjusts the conclusion based on the emotion data.

[1431] Specifically, the server analyzes the emotion data, and if the user's emotion is positive, the server corrects the conclusion to a positive direction, and if the user's emotion is negative, the server corrects the conclusion to a more cautious direction.

[1432] Input: Emotion data sent to the server

[1433] Output: Adjusted conclusion

[1434] (Application example 1)

[1435] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1436] In conventional conference systems, it was difficult to reach a conclusion in a meeting efficiently, leading to problems such as long meetings and frequent useless meetings. In addition, the quality of the conclusions was often poor because the conclusions were reached without considering the feelings of the participants. Furthermore, production data and maintenance data within the factory could not be effectively utilized, which often led to inefficient progress in meetings.

[1437] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1438] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view using an emotion engine that recognizes the user's emotions, a means for collecting production data and maintenance data in the factory and automatically generating the optimal conclusion using AI, a means for providing a scheduling function and an agenda management function for streamlining the progress of the meeting, and a means for having an optimization function for scheduling only necessary meetings. This makes it possible to efficiently derive a meeting conclusion, shorten the meeting time, and reduce unnecessary meetings. In addition, the quality of the conclusion can be improved by drawing a conclusion that takes into account the emotions of the participants. Furthermore, the progress of the meeting can be made more efficient by effectively utilizing the production data and maintenance data in the factory.

[1439] The "means for preparing a meeting conclusion in advance" is a function for collecting the meeting agenda and the opinions of the participants, and automatically generating the meeting conclusion based on them.

[1440] "Means of shortening meeting times" refers to functions that provide scheduling and agenda management functions to make meetings more efficient.

[1441] "Means for reducing the number of meetings" refers to a feature that provides an optimization function for scheduling only necessary meetings.

[1442] The "emotion engine that recognizes the user's emotions" is a function that recognizes the user's emotions and controls a means for preparing a meeting conclusion in advance based on the emotions.

[1443] The "means for collecting production data and maintenance data within the factory" is a function for collecting data regarding production activities and maintenance activities within the factory.

[1444] "Means for AI to automatically generate optimal conclusions" refers to a function in which artificial intelligence automatically generates optimal meeting conclusions based on collected data.

[1445] The "scheduling function for making meetings more efficient" is a function for optimizing the meeting schedule and making the meeting proceed efficiently.

[1446] The "agenda management function" is a function for managing the agenda of a meeting and progressing the meeting efficiently.

[1447] The "optimization function" is a function that evaluates the necessity of meetings and generates an optimal schedule in order to schedule only necessary meetings.

[1448] The system for carrying out the present invention has a plurality of functions for preparing a meeting conclusion in advance and realizing shortening the time and number of meetings. A specific embodiment of this system will be described below.

[1449] System Configuration

[1450] The system consists of the following main components:

[1451] 1. Server

[1452] A means for preparing a meeting conclusion in advance: The server has a function for collecting the meeting agenda and the opinions of the participants, and automatically generating the meeting conclusion based on them.

[1453] Means to reduce meeting times: The server provides scheduling and agenda management functions to make meetings more efficient.

[1454] A means to reduce the number of meetings: The server has an optimization function to schedule only necessary meetings.

[1455] Emotion Engine: The server controls the means to recognize the user's emotions and pre-plan the outcome of the meeting based on those emotions.

[1456] Data collection method: The server collects production data and maintenance data within the factory.

[1457] AI conclusion generation method: The server automatically generates the optimal meeting conclusion using artificial intelligence based on the collected data.

[1458] Hardware and software used

[1459] EmotionEngine: An engine for recognizing user emotions. It uses the camera and microphone to collect emotion data.

[1460] Scheduler: Software for scheduling meetings.

[1461] ConclusionGenerator: Software for generating meeting conclusions using AI.

[1462] Data processing and calculation

[1463] 1. Data collection: The server collects production data and maintenance data. For example, it collects data such as "Production line A's operating rate has reached 90%" or "Machine B needs maintenance."

[1464] 2. Emotion Recognition: The server uses the EmotionEngine to recognize participants' emotions from the camera and microphone. For example, it collects data such as "Participant's emotion is positive."

[1465] 3. Conclusion Generation: Based on the collected data and sentiment data, the server uses the ConclusionGenerator to generate an optimal conclusion for the meeting.

[1466] 4. Meeting Scheduling: The server uses the Scheduler to schedule the optimal meeting time.

[1467] Examples

[1468] For example, consider the case where the following data is collected in a factory:

[1469] Production data: "Production line A has reached 90% utilization."

[1470] Maintenance data: "Machine B requires maintenance."

[1471] Sentiment data: "Participants' sentiment is positive."

[1472] Based on this data, the server generates the following prompt sentence and inputs it into the AI ​​conclusion generation means.

[1473] Examples of prompt statements

[1474] The utilization rate of production line A has reached 90%. Machine B needs maintenance. The participants' sentiment is positive. Based on these data, generate the optimal meeting conclusion.

[1475] Based on this prompt, the AI ​​generates the optimal meeting conclusion, and the server optimizes the meeting schedule based on that conclusion. This makes it possible to efficiently reach meeting conclusions, shorten meeting times, and reduce unnecessary meetings. In addition, by drawing conclusions that take into account the emotions of the participants, the quality of conclusions can be improved. Furthermore, by effectively utilizing production data and maintenance data from within the factory, the progress of meetings can be made more efficient.

[1476] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1477] Step 1:

[1478] The server collects production data and maintenance data. Specifically, it obtains data such as "Production line A's operating rate has reached 90%" or "Machine B requires maintenance" from sensors and databases in the factory. The input is data from sensors and databases in the factory, and the output is the collected production data and maintenance data.

[1479] Step 2:

[1480] The server uses the EmotionEngine to recognize the user's emotions. Specifically, it uses a camera and microphone to analyze the participant's facial expressions and tone of voice, and obtains emotion data such as "The participant's emotion is positive." The input is video and audio data from the camera and microphone, and the output is the recognized emotion data.

[1481] Step 3:

[1482] The server generates a prompt sentence based on the collected production data, maintenance data, and emotion data. Specifically, it combines these data to create a prompt sentence such as "Production line A's operating rate has reached 90%. Machine B needs maintenance. Participants' emotions are positive. Please generate the optimal meeting conclusion based on these data." The input is the collected data, and the output is the generated prompt sentence.

[1483] Step 4:

[1484] The server uses the ConclusionGenerator to generate an optimal meeting conclusion based on the prompt sentence. Specifically, the prompt sentence is input to the generative AI model, and the AI ​​outputs the optimal conclusion. The input is the prompt sentence, and the output is the generated meeting conclusion.

[1485] Step 5:

[1486] The server uses the Scheduler to optimize the meeting schedule: it schedules optimal meeting times based on the generated meeting outcomes. The input is the generated meeting outcomes, and the output is the optimized meeting schedule.

[1487] Step 6:

[1488] The server notifies the user of the generated meeting conclusion and schedule. Specifically, it sends the meeting conclusion and schedule to the participants using email or a notification system. The input is the generated meeting conclusion and schedule, and the output is the notification to the user.

[1489] Example 2

[1490] Next, a second embodiment of the second form will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1491] Conventional conference systems had the problem that it took a lot of time and effort to reach a conclusion, which reduced the efficiency of the meeting. In addition, it was difficult to reach an optimal conclusion because the conclusion was reached without fully considering the opinions and feelings of the participants. Furthermore, as the number of meetings increased, it became difficult to align the understanding within the organization, which slowed down the speed of decision-making.

[1492] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1493] In this invention, the server includes a means for preparing a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for recognizing the user's emotions and adjusting the conclusion based on the emotions, a means for analyzing data using a generative AI model and extracting important points, and a means for analyzing the user's emotions using emotion recognition software. This makes it possible to improve the efficiency of the meeting and quickly derive an optimal conclusion that takes into account the opinions and emotions of the participants.

[1494] A "means for preparing a meeting conclusion in advance" is a means for generating a conclusion in advance based on information such as the meeting agenda, the opinions of participants, and the results of past meetings.

[1495] "Means of shortening the time of meetings" are means of making the meeting proceed more efficiently and shortening the time required.

[1496] "Methods to reduce the number of meetings" are means to reduce the number of meetings and make decision-making more efficient within an organization.

[1497] "The ability to predict the optimal conclusion at any given time from an objective point of view" is the ability to objectively derive the most appropriate conclusion based on collected data.

[1498] The "means for recognizing a user's emotion and adjusting a conclusion based on the emotion" refers to a means for analyzing a user's emotion and adjusting a conclusion based on the result of the analysis.

[1499] "Means for analyzing data and extracting important points using a generative AI model" means means for using a generative AI model to analyze input data and extract important information.

[1500] "Means for analyzing a user's emotions using emotion recognition software" refers to means for analyzing a user's emotions using emotion recognition software.

[1501] This invention is a system for improving the efficiency of a meeting and quickly deriving an optimal conclusion. This system operates in cooperation with a server, a terminal, and a user.

[1502] Hardware and Software Used

[1503] Hardware: Servers, terminals (PCs, tablets, smartphones)

[1504] Software: Generative AI models (e.g. GPT-4), emotion recognition software (e.g. IBM Watson Tone Analyzer)

[1505] System Overview

[1506] 1. Data Collection

[1507] The user inputs the meeting agenda and opinions into the terminal.

[1508] The terminal transmits the input data to the server.

[1509] The server retrieves the results of past meetings from a database.

[1510] 2. Data Analysis

[1511] The server feeds a generative AI model (e.g., GPT-4) with the meeting agenda, participant opinions, and results of past meetings.

[1512] The server uses a generative AI model to analyze the input data and extract key points.

[1513] The server analyzes the user's emotions using emotion recognition software (e.g., IBM Watson Tone Analyzer).

[1514] 3. Inferring conclusions

[1515] The server uses a generative AI model to automatically generate optimal conclusions from the analysis results.

[1516] The server uses the results of emotion recognition software to adjust its conclusions depending on the user's emotions.

[1517] 4. Presentation of results

[1518] The server transmits the best guess to the terminal.

[1519] The terminal displays the optimal conclusion to the user.

[1520] Examples

[1521] For example, if the topic of the meeting is "New Product Launch Strategy", the user might enter:

[1522] Meeting Agenda: New Product Launch Strategy

[1523] Participant opinions: "I think the new product will be popular with younger generations" "I think the cost is too high"

[1524] Outcome of past meetings: "The new product was priced too high and didn't sell."

[1525] Example prompt:

[1526] The topic of the meeting is "New product launch strategy." The opinions of the participants are "I think the new product will be popular with young people" and "I think the cost is too high." The outcome of a past meeting was "The new product was priced too high and didn't sell." Based on this information, please infer the best conclusion.

[1527] The system can improve the efficiency of meetings and quickly reach optimal conclusions that take into account the opinions and feelings of participants.

[1528] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1529] Step 1:

[1530] The user inputs the meeting agenda and opinions into the terminal.

[1531] Input: Meeting topic: "New product launch strategy", participant opinions: "I think the new product will be popular with younger generations" and "Isn't the cost too high?"

[1532] Output: Data entered into the terminal

[1533] Step 2:

[1534] The terminal transmits the input data to the server.

[1535] Input: Meeting topic and comments entered by the user

[1536] Output: Data sent to the server

[1537] Step 3:

[1538] The server retrieves the results of past meetings from a database.

[1539] Input: Database query

[1540] Output: Results of past meetings: "The price of the new product was too high and it didn't sell."

[1541] Step 4:

[1542] The server feeds a generative AI model (e.g., GPT-4) with the meeting agenda, participant opinions, and results of past meetings.

[1543] Input: meeting agendas, participant comments, results of past meetings

[1544] Output: The data fed into the generative AI model

[1545] Step 5:

[1546] The server uses a generative AI model to analyze the input data and extract key points.

[1547] Input: Data fed into the generative AI model

[1548] Data processing: Generative AI models analyze data and extract key takeaways

[1549] Output: Key point: "It is likely to be popular among young people, but there are concerns about its high cost."

[1550] Step 6:

[1551] The server analyzes the user's emotions using emotion recognition software (e.g., IBM Watson Tone Analyzer).

[1552] Input: User opinion data

[1553] Data processing: Emotion recognition software analyzes user emotions

[1554] Output: User sentiment analysis result: "Positive"

[1555] Step 7:

[1556] The server uses a generative AI model to automatically generate optimal conclusions from the analysis results.

[1557] Input: Key points, user sentiment analysis results

[1558] Data processing: Generative AI models generate optimal conclusions

[1559] Output: Optimal conclusion: "Review the price of the new product and strengthen the marketing strategy for younger generations."

[1560] Step 8:

[1561] The server uses the results of emotion recognition software to adjust its conclusions depending on the user's emotions.

[1562] Input: Optimal conclusion, user sentiment analysis results

[1563] Data manipulation: Adjusting conclusions based on user sentiment

[1564] Output: Adjusted conclusion: "Review the price of the new product and strengthen the marketing strategy for younger generations (positive direction)."

[1565] Step 9:

[1566] The server transmits the best guess to the terminal.

[1567] Input: Adjusted conclusion

[1568] Output: conclusion sent to terminal

[1569] Step 10:

[1570] The terminal displays the optimal conclusion to the user.

[1571] Input: The conclusion sent by the server

[1572] Output: Conclusion displayed to the user: "Review the price of the new product and strengthen the marketing strategy for younger generations."

[1573] In this way, the system analyzes meeting agendas, opinions, and past results, and takes into account the user's emotions to arrive at optimal conclusions.

[1574] (Application example 2)

[1575] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1576] With conventional conference systems, it was difficult to prepare a meeting's conclusion in advance, which often resulted in lengthy meetings. In addition, there was a problem that efficient management became difficult as the number of meetings increased. Furthermore, in the manufacturing process, it was difficult to collect and analyze data from each step and propose optimal manufacturing procedures and improvements, and adjustments to work plans were not made that took into account the emotions of workers. To solve these problems, a system that could simultaneously improve meeting efficiency and optimize the manufacturing process was needed.

[1577] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1578] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for collecting and analyzing data on each step in the manufacturing process and proposing optimal manufacturing procedures and improvements, and a means for recognizing the emotions of workers and adjusting the work plan based on the emotions. This makes it possible to improve the efficiency of meetings and optimize the manufacturing process.

[1579] A "means for preparing meeting conclusions in advance" is a method for analyzing the meeting agenda, the opinions of participants, and the results of past meetings to generate optimal conclusions in advance.

[1580] "Means of shortening the time of meetings" are methods for making meetings more efficient and shortening the time required for meetings.

[1581] "Methods to reduce the number of meetings" are methods for evaluating the necessity of meetings and reducing unnecessary meetings.

[1582] "A function that can predict the optimal conclusion at any given time from an objective point of view" refers to a function that enables a meeting to reach an optimal conclusion based on collected data while the meeting is in progress.

[1583] "A means of collecting and analyzing data from each step in the manufacturing process and proposing optimal manufacturing procedures and improvements" is a method for proposing optimal manufacturing procedures and improvements by collecting and analyzing data generated at each step of the manufacturing line.

[1584] A "means for recognizing worker emotions and adjusting a work plan based on the emotions" is a method for recognizing a worker's emotional state and adjusting a work plan based on that information.

[1585] The system for carrying out the present invention is capable of simultaneously improving the efficiency of meetings and optimizing the manufacturing process. A specific embodiment of this system will be described below.

[1586] Hardware and Software Used

[1587] Hardware

[1588] Factory robots: Robots used in manufacturing lines (e.g. general-purpose robot arms)

[1589] Emotion recognition camera: A camera to recognize the emotions of workers (e.g. high-precision camera)

[1590] Data collection sensors: Sensors for collecting data at each step of the manufacturing process (e.g. IoT sensors)

[1591] software

[1592] AI Models: AI models for data analysis and optimization (e.g. TensorFlow, PyTorch)

[1593] Emotion recognition software: Software to analyze the emotions of workers (e.g. Microsoft Azure Emotion API)

[1594] Data analysis tools: Tools for pre-processing and analyzing data (e.g. Apache Spark)

[1595] System Operation

[1596] Data collection

[1597] The server uses IoT sensors to collect data generated at each step of the production line (time, error rate, worker performance, etc.) and also collects worker emotion data using an emotion recognition camera.

[1598] Data analysis

[1599] The server preprocesses the collected data using Apache Spark and inputs it into an AI model built using TensorFlow and PyTorch to optimize the manufacturing process.

[1600] emotion recognition

[1601] The server uses the Microsoft Azure Emotion API to analyze the emotion data of workers and adjusts the work plan based on the analysis results.

[1602] Optimization suggestions

[1603] The server then proposes optimal manufacturing procedures and improvements based on the AI ​​model, adjusting the suggestions according to the worker's emotional state.

[1604] Examples

[1605] For example, if there is a bottleneck on a production line, the server might do the following:

[1606] Collect data from sensors to identify at which step delays are occurring.

[1607] Emotion-recognition cameras check workers' stress levels.

[1608] The AI ​​model suggests optimal improvement measures (for example, automating certain steps or adjusting worker break times).

[1609] Examples of prompt statements

[1610] "Collect data from the production line and analyze the efficiency of each step. Collect emotional data from workers and adjust work plans according to their stress levels. Suggest optimal production procedures and areas for improvement."

[1611] In this way, a system is created that simultaneously improves meeting efficiency and optimizes the manufacturing process.

[1612] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1613] Step 1:

[1614] The server uses IoT sensors to collect data (time, error rate, worker performance, etc.) generated at each step of the production line. The input is the sensor data for each step, and the output is a set of collected data. Specifically, the server obtains data from the sensors in real time and stores it in a database.

[1615] Step 2:

[1616] The server collects the workers' emotional data using an emotion recognition camera. The input is the camera footage, and the output is the analyzed emotional data. Specifically, the camera footage is captured in real time, and the emotional state is analyzed using emotion recognition software.

[1617] Step 3:

[1618] The server preprocesses the collected data using Apache Spark. The input is sensor data and emotion data, and the output is a preprocessed dataset. Specifically, it fills in missing values ​​in the data, removes outliers, and converts it into a format suitable for AI models.

[1619] Step 4:

[1620] The server inputs the preprocessed data into an AI model to optimize the manufacturing process. The input is the preprocessed data set, and the output is the optimal manufacturing procedure or suggestions for improvements. Specifically, the data is input into an AI model built using TensorFlow and PyTorch to generate the optimization results.

[1621] Step 5:

[1622] The server analyzes the worker's emotional data using the Microsoft Azure Emotion API. The input is the emotional data, and the output is the evaluation result of the emotional state. Specifically, the server sends the emotional data to the API and obtains the evaluation result in return.

[1623] Step 6:

[1624] The server proposes optimal manufacturing procedures and improvements generated by the AI ​​model. The input is the optimization results and the evaluation results of the emotional state, and the output is an adjusted work plan. Specifically, the server adjusts the work plan based on the optimization results and the emotional state and presents it to the worker.

[1625] Step 7:

[1626] The user executes the manufacturing process based on the work plan presented by the server. The input is the adjusted work plan, and the output is the result of the executed manufacturing process. Specifically, the user operates the manufacturing line according to the work plan and feeds back the results to the server.

[1627] 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.

[1628] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. 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 is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1629] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1630] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1631] [Fourth embodiment]

[1632] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1633] 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.

[1634] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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 wide area network (WAN) and / or a local area network (LAN).

[1635] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1636] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, 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.

[1637] 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 surroundings of user 20 (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).

[1638] 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. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1639] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. 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.

[1640] Fig. 8 shows an example of 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.

[1641] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1642] 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.

[1643] In the robot 414, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1644] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1645] "Example 1"

[1646] The system of the present invention is provided with a means for preparing a meeting conclusion in advance, a means for shortening the meeting time, and a means for reducing the number of meetings themselves. Specifically, as a means for preparing a meeting conclusion in advance, the system has a function for collecting meeting agendas and participant opinions and automatically generating a conclusion based on them. In addition, as a means for shortening meeting time, the system has a scheduling function and agenda management function for making the meeting progress more efficient. Furthermore, as a means for reducing the number of meetings themselves, the system has an optimization function for scheduling only necessary meetings.

[1647] "Example 2"

[1648] As a function that can predict the optimal conclusion at that time from an objective point of view, it has the function of analyzing the meeting agenda, the opinions of participants, the results of past meetings, etc., and predicting the optimal conclusion based on the results. A specific example would be a function that uses AI technology to analyze the meeting agenda and the opinions of participants, and automatically generates the optimal conclusion based on the results.

[1649] The process flow of each embodiment will be described below.

[1650] "Example 1"

[1651] Step 1: Collect the meeting agenda and participants' opinions. This will be the basis for formulating the meeting conclusions in advance.

[1652] Step 2: Automatically generate meeting conclusions based on the collected agenda and opinions, which can shorten the meeting time.

[1653] Step 3: Use scheduling and agenda management features to streamline the meeting, further shortening the meeting time.

[1654] Step 4: Use optimization features to schedule only the meetings you need, which can reduce the number of meetings you have.

[1655] "Example 2"

[1656] Step 1: Collect meeting agendas, participant opinions, past meeting results, etc. This will provide the basic data to objectively estimate the optimal conclusion at that time.

[1657] Step 2: Analyze the collected data using AI technology. This analysis will predict the optimal conclusion at that point in time.

[1658] Step 3: Based on the inferred conclusion, the conclusion of the meeting is automatically generated, which makes it possible to shorten the meeting time and reduce the number of meetings.

[1659] Example 1

[1660] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1661] In the modern business environment, meetings are important places for decision-making, but they often take too long, have vague conclusions, or are unnecessary. This reduces work efficiency and wastes resources. Therefore, there is a need for a system that can quickly and accurately make meeting conclusions, shorten meeting times, and reduce unnecessary meetings.

[1662] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1663] In this invention, the server includes a means for collecting meeting agendas and participant opinions and automatically generating a conclusion based on them, a means having a scheduling function and an agenda management function for making the meeting proceed efficiently, and a means having an optimization function for scheduling only necessary meetings. This makes it possible to quickly and accurately create a meeting conclusion, shorten the meeting time, and reduce unnecessary meetings.

[1664] A "meeting agenda" is the specific themes or topics to be discussed at a meeting.

[1665] "Participant input" refers to ideas, suggestions, and feedback provided by members attending the meeting.

[1666] "Means for automatically generating conclusions" refers to a function that uses artificial intelligence and algorithms to automatically create optimal conclusions based on collected topics and opinions.

[1667] The "scheduling function" refers to the function that optimizes meeting dates and times and participant schedules to set up meetings efficiently.

[1668] The "agenda management function" refers to the function of organizing the topics to be discussed in a meeting and managing the progress.

[1669] "Optimization function" refers to a function for evaluating the necessity of meetings and reducing duplicate or unnecessary meetings.

[1670] A "function that can make inferences from an objective perspective" is a function that uses data and algorithms to derive optimal conclusions without relying on subjectivity.

[1671] The present invention is a system for optimizing the efficiency of a conference, and is realized by a server, a terminal, and a user each fulfilling their respective roles. A specific embodiment of this system will be described below.

[1672] 1. A way to prepare meeting conclusions in advance

[1673] The server uses Google Calendar API and Microsoft Outlook API to collect meeting agendas and participant opinions. This allows it to obtain the agenda for the next meeting. It also collects participant opinions from communication tools such as Slack and Microsoft Teams.

[1674] Examples:

[1675] The server calls the Google Calendar API to get the agenda for the next meeting.

[1676] The server uses the Slack API to collect participant opinions from the meeting channel.

[1677] Based on the collected data, the server inputs prompts into a generative AI model (e.g., OpenAI's GPT-4), which generates a conclusion based on the input agenda and opinions.

[1678] Examples:

[1679] Prompt: The topic of the meeting is "Marketing strategy for a new product," and the opinions of the participants are "We should strengthen social media advertising," "We should also consider TV commercials," and "We have a limited budget, so we should choose an efficient method." Please generate a conclusion based on these.

[1680] The generated conclusions are stored in a database by the server and made accessible to the user.

[1681] 2. Ways to shorten meeting times

[1682] To streamline meetings, the server optimizes meeting schedules using Google Calendar API and Microsoft Outlook API, and manages agendas using task management tools such as Trello and Asana.

[1683] Examples:

[1684] The server calls the Google Calendar API to get the upcoming meeting schedule.

[1685] The server proposes an optimal schedule taking into account the free time of the participants.

[1686] The server calls the Trello API and creates the meeting agenda as a card.

[1687] The server provides real-time updates on the progress of the agenda.

[1688] 3. Ways to reduce the number of meetings

[1689] The server retrieves and analyzes existing meeting schedules using Google Calendar API and Microsoft Outlook API, detects duplicates and unnecessary meetings, and uses a generative AI model to evaluate the necessity of meetings and propose optimal schedules.

[1690] Examples:

[1691] The server calls the Google Calendar API to get the meeting schedule for the next week.

[1692] The server inputs prompt sentences into the generative AI model to assess the need for a meeting.

[1693] Prompt: Please optimize your meeting schedule for the next week. The current schedule is as follows: Monday: Meeting A, Tuesday: Meeting B, Wednesday: Meeting C. Please reduce overlapping and unnecessary meetings.

[1694] The generative AI model generates suggestions for reducing unnecessary meetings, and the server updates the schedule based on the suggestions.

[1695] This system makes it possible to quickly and accurately draw up meeting conclusions, shorten meeting times, and reduce unnecessary meetings.

[1696] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1697] Step 1:

[1698] The server calls the Google Calendar API or Microsoft Outlook API to get the meeting agenda. As input, it provides the schedule information of the upcoming meeting. The server saves the agenda information obtained from the API in a database.

[1699] Specific behavior:

[1700] The server calls the Google Calendar API to get the agenda for the next meeting.

[1701] The obtained agenda information is stored in a database.

[1702] Step 2:

[1703] The server uses APIs of Slack and Microsoft Teams to collect participants' opinions. As input, it provides the channel information of the meeting. The server stores the opinion information obtained from the API in a database.

[1704] Specific behavior:

[1705] The server uses the Slack API to collect participant opinions from the meeting channel.

[1706] The obtained opinion information is stored in a database.

[1707] Step 3:

[1708] The server inputs the collected topics and opinions into the generative AI model. As input, it provides text data of the topics and opinions. The generative AI model generates a conclusion based on the input data and outputs it to the server.

[1709] Specific behavior:

[1710] The server converts the agenda and opinions into text format and inputs them as prompts to the generative AI model.

[1711] The generative AI model analyzes the prompt and generates an optimal conclusion.

[1712] The server receives the generated conclusions and stores them in a database.

[1713] Step 4:

[1714] The server uses Google Calendar API and Microsoft Outlook API to optimize meeting schedules. As input, you provide the schedule information of the participants. The server calculates the optimal schedule and proposes it as output.

[1715] Specific behavior:

[1716] The server calls the Google Calendar API to obtain the participants' schedule information.

[1717] Based on the acquired schedule information, the optimal meeting schedule is calculated.

[1718] The server proposes an optimal schedule and stores it in a database.

[1719] Step 5:

[1720] The server uses Trello or Asana API to manage the agenda. As input, we provide the meeting agenda information. The server creates the agenda as cards and manages the progress.

[1721] Specific behavior:

[1722] The server calls the Trello API and creates the meeting agenda as a card.

[1723] The server provides real-time updates on the progress of the agenda.

[1724] Step 6:

[1725] The server uses Google Calendar API and Microsoft Outlook API to analyze the existing meeting schedule. As input, you provide the meeting schedule information for the next week. The server detects overlapping and unnecessary meetings and suggests an optimized schedule as output.

[1726] Specific behavior:

[1727] The server calls the Google Calendar API to get the meeting schedule for the next week.

[1728] The server analyzes the schedule to detect overlapping and unnecessary meetings.

[1729] The server inputs prompt sentences into the generative AI model to assess the need for a meeting.

[1730] A generative AI model generates suggestions to cut down on unnecessary meetings.

[1731] The server updates the schedule based on the suggestions.

[1732] (Application example 1)

[1733] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1734] Meetings and discussions in factories are important for improving productivity, but they often take too much time and there are many pointless meetings. It is also difficult to efficiently collect opinions from each department and reach optimal conclusions. To solve these problems, there is a need to streamline and optimize meetings.

[1735] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the time of the meeting, a means for reducing the number of meetings, a means for collecting agendas and opinions from each department in the factory and automatically generating a conclusion using a generative AI model, a means for optimizing the meeting schedule and efficiently managing the agenda, and a means for scheduling only necessary meetings and reducing unnecessary meetings. This makes it possible to make meetings and discussions in the factory more efficient and improve productivity.

[1736] "A means of preparing meeting conclusions in advance" is a function that collects meeting agendas and participants' opinions, and automatically generates conclusions based on them.

[1737] "Means of shortening meeting times" refer to scheduling and agenda management functions to make meetings more efficient.

[1738] "A means to reduce the number of meetings" refers to an optimization function that schedules only necessary meetings.

[1739] "A function that can predict the optimal conclusion at any given time from an objective perspective" is a function that automatically derives the optimal conclusion based on collected information.

[1740] "Means of collecting topics and opinions from each department within the factory" refers to a function that visits each department within the factory and collects opinions using voice recognition technology.

[1741] "Means for automatically generating a conclusion using a generative AI model" refers to a function that automatically generates a conclusion using a generative AI model based on collected topics and opinions.

[1742] "Means for optimizing meeting schedules and efficiently managing agendas" refers to a function for optimizing meeting schedules and efficiently managing agendas using scheduling software.

[1743] "A means of scheduling only necessary meetings and reducing unnecessary meetings" is a function that uses AI to evaluate the necessity of meetings and reduce unnecessary meetings.

[1744] The system for carrying out the present invention is a tool for making meetings and conferences in a factory more efficient and improving productivity. A specific embodiment of this system will be described below.

[1745] Hardware and Software Used

[1746] Hardware: Factory robots, servers, network equipment

[1747] Software: Generative AI models (e.g. OpenAI GPT-4), database management systems (e.g. MySQL), scheduling software (e.g. Google Calendar API)

[1748] Data processing and calculation

[1749] Agenda collection

[1750] The factory robot travels around each department in the factory and collects opinions using voice recognition technology. The collected data is sent to a server and stored in a database. This allows opinions from each department to be efficiently collected.

[1751] Automatic conclusion generation

[1752] The server automatically generates conclusions using a generative AI model (e.g. GPT-4) based on the collected agenda and opinions. The generated conclusions are stored in a database and notified to each department as necessary. This allows the conclusions of meetings to be generated quickly.

[1753] Scheduling and Agenda Management

[1754] The server optimizes the meeting schedule using scheduling software (e.g., Google Calendar API). It also efficiently manages the agenda for each meeting using the agenda management function, allowing the meetings to proceed smoothly.

[1755] Optimizing the number of meetings

[1756] The server uses AI to evaluate the necessity of meetings and schedules only the necessary meetings, thus reducing unnecessary meetings.

[1757] Examples

[1758] For example, if a meeting is held within a factory to introduce a new product line, the process may look like this:

[1759] 1. Gather input from each department about the new product line.

[1760] 2. Based on the collected opinions, the generative AI model automatically generates a conclusion.

[1761] 3. Use scheduling software to schedule the best possible meeting.

[1762] 4. Schedule only the meetings you need and cut down on the unnecessary ones.

[1763] Examples of prompt statements

[1764] Here is an example of a prompt to be input to the generative AI model:

[1765] You have collected opinions regarding the introduction of a new product line. Generate a conclusion based on the opinions below.

[1766] Opinion 1: We should install new machines to improve the efficiency of our production line.

[1767] Opinion 2: It is better to improve the existing machine to reduce costs.

[1768] Statement 3: The introduction of a new product line requires employee training.

[1769] Use these opinions to generate the best conclusion.

[1770] In this way, factory meetings can be made more efficient and productivity can be improved.

[1771] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1772] Step 1:

[1773] The factory robot travels around each department in the factory and collects opinions using voice recognition technology. The input is the voice opinions from the staff in each department, and the output is the opinion data in text format. The robot uses voice recognition software to convert the voice into text and sends it to the server.

[1774] Step 2:

[1775] The server stores the opinion data sent from the robot in a database. The input is the opinion data in text format, and the output is the opinion data stored in the database. The server stores the data using a database management system (e.g., MySQL).

[1776] Step 3:

[1777] The server automatically generates a conclusion using a generative AI model (e.g. GPT-4) based on the opinion data stored in the database. The input is the opinion data obtained from the database, and the output is the generated conclusion. The server inputs a prompt sentence into the generative AI model to generate a conclusion.

[1778] Step 4:

[1779] The server stores the generated conclusions in a database and notifies each department as necessary. The input is the generated conclusion, and the output is the conclusion stored in the database and the notified conclusion. The server sends the conclusions to each department using a notification system.

[1780] Step 5:

[1781] The server optimizes the meeting schedule using scheduling software (e.g. Google Calendar API). The input is the meeting agenda and attendee information, and the output is the optimized meeting schedule. The server uses the scheduling software to set the schedule.

[1782] Step 6:

[1783] The server efficiently manages the agenda of each meeting through the agenda management function. The input is the meeting agenda information, and the output is the managed agenda information. The server manages the agenda using the agenda management software.

[1784] Step 7:

[1785] The server uses AI to assess the need for meetings and schedule only those that are necessary. The input is meeting agenda and participant information, and the output is an optimized meeting schedule. The server uses AI models to assess the need for meetings and reduce unnecessary meetings.

[1786] Example 2

[1787] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1788] In conventional conference systems, it was difficult to prepare a meeting's conclusion in advance, and meetings often dragged on. In addition, as the number of meetings increased, the burden on participants increased, making efficient decision-making difficult. Furthermore, there was a demand for a system that could objectively analyze meeting topics and participants' opinions to arrive at optimal conclusions.

[1789] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1790] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a means for collecting, preprocessing, and analyzing meeting agendas, participants' opinions, and results of past meetings, a means for predicting an optimal conclusion using a generative AI model, and a means for outputting the predicted conclusion, thereby making it possible to improve the efficiency of meetings and derive optimal conclusions.

[1791] A "means for preparing a meeting conclusion in advance" is a method or device for preparing a conclusion based on existing information before the meeting begins.

[1792] A "means for shortening the duration of a meeting" is a method or device for making the meeting proceed more efficiently and shortening the time required for the meeting.

[1793] A "means for realizing a reduction in the number of meetings" is a method or device for reducing the number of necessary meetings and reducing the overall number of meetings.

[1794] A "means for collecting meeting agendas, participant opinions, and results of past meetings" is a method or device for collecting information related to meetings.

[1795] A "preprocessing means" is a method or device for preparing collected data in a form that is easy to analyze.

[1796] An "analyzing means" is a method or device for analyzing the pre-processed data and extracting significant information.

[1797] A "means for inferring optimal conclusions using a generative AI model" is a method or device for using artificial intelligence technology to derive optimal conclusions from collected and analyzed data.

[1798] A "means for outputting an inferred conclusion" is a method or device for providing a user with the conclusion inferred by the generative AI model.

[1799] The present invention is directed to a system for improving the efficiency of a meeting and deriving an optimal conclusion. A specific embodiment of this system will be described below.

[1800] The server generates programs to collect, preprocess, and analyze meeting agendas, participant opinions, and past meeting results. The programs use natural language processing libraries (e.g., NLTK, spaCy) and generative AI models (e.g., GPT-4) to process and compute the data.

[1801] First, the server connects to a database and collects meeting agendas, participant opinions, and results of past meetings. For example, it obtains the minutes and participant opinions of a meeting on "New Product Launch Strategy."

[1802] The server then pre-processes the collected data, which involves cleaning the text data, tokenizing it, removing stop words, etc., making the data easier to analyze.

[1803] The server then feeds the pre-processed data into a generative AI model to extract key keywords and themes, such as "market research," "competitive analysis," and "marketing strategy."

[1804] Next, the server uses the generative AI model to predict the optimal conclusion based on the analysis results, taking into account the results of past meetings and the opinions of the participants. For example, the generative AI model is given a prompt such as, "Please predict the optimal conclusion regarding the market launch strategy for a new product."

[1805] Finally, the server outputs the inferred conclusion to the terminal. The user can confirm this conclusion through the terminal. For example, the conclusion "Strengthen market research and develop a marketing strategy based on competitive analysis" is confirmed on the screen of the terminal.

[1806] As a concrete example, consider a case where a user holds a meeting and sets the topic as "New product launch strategy." Participants express their opinions and note that similar topics have been discussed in past meetings. In this case, the server inputs the following prompt sentence into the generative AI model:

[1807] Example prompt:

[1808] "Based on the agenda and participants' opinions of a meeting about a new product launch strategy, infer the best outcome. Also take into account the results of previous meetings."

[1809] By inputting this prompt into a generative AI model, the server can infer the optimal conclusion and provide it to the user.

[1810] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1811] Step 1: Data collection

[1812] The server collects meeting agendas, participant opinions, and past meeting results by connecting to a database and retrieving relevant meeting minutes and speech records.

[1813] Input: meeting agendas, participant comments, results of past meetings

[1814] Output: Raw data collected

[1815] What happens: The server uses an SQL query to retrieve meeting minutes and participant opinions on "New Product Launch Strategy" from the database.

[1816] Step 2: Data Preprocessing

[1817] The server pre-processes the collected data, specifically cleaning the text data, tokenizing it, removing stop words, etc.

[1818] Input: Raw data collected

[1819] Output: Preprocessed data

[1820] Specific operation: The server removes unnecessary symbols and spaces from the acquired text data, tokenizes it, and removes stop words. This is done using a natural language processing library (e.g. NLTK, spaCy).

[1821] Step 3: Data analysis

[1822] The server feeds the pre-processed data into a generative AI model to extract key keywords and themes.

[1823] Input: Preprocessed data

[1824] Output: Extracted keywords and themes

[1825] How it works: The server inputs the preprocessed text data into a generative AI model (e.g., GPT-4) and extracts important keywords such as "market research," "competitive analysis," and "marketing strategy."

[1826] Step 4: Inferring conclusions

[1827] The server uses a generative AI model to infer the optimal conclusion based on the analysis results.

[1828] Input: Extracted keywords or themes

[1829] Output: Inferred conclusion

[1830] Specific operation: Based on the extracted keywords and themes, the server inputs a prompt to the generative AI model: "Please predict the optimal conclusion regarding the new product's market launch strategy." The generative AI model considers the results of past meetings and the opinions of participants and generates the conclusion: "Strengthen market research and develop a marketing strategy based on competitive analysis."

[1831] Step 5: Output the results

[1832] The server outputs the inferred conclusion to the terminal, where the user can confirm the conclusion.

[1833] Input: Inferred conclusion

[1834] Output: conclusions provided to the user

[1835] Specific operation: The server transmits the generated conclusion to the terminal, and the user confirms the conclusion "strengthen market research and develop a marketing strategy based on competitive analysis" on the terminal screen.

[1836] (Application example 2)

[1837] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1838] In conventional conference systems, it was difficult to prepare the conclusion of a meeting in advance, which resulted in long meeting times and an increase in the number of meetings. In addition, it was difficult to objectively predict the optimal conclusion, which meant that it took a lot of time and effort to align the understanding within the organization.

[1839] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1840] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for acquiring the results of past meetings from a database, a means for automatically generating an optimal conclusion using a generative AI model, and a means for outputting the generated conclusion. This makes it possible to improve the efficiency of meetings and automatically generate optimal conclusions.

[1841] The "means for creating a meeting conclusion in advance" is a function for automatically generating a conclusion based on the agenda before the meeting begins.

[1842] "Means of shortening meeting times" refers to functions that make meetings more efficient and shorten the amount of time required.

[1843] "Means for reducing the number of meetings" refers to a function for evaluating the necessity of meetings and reducing unnecessary meetings.

[1844] "A function that can predict the optimal conclusion at that time from an objective perspective" is a function that automatically predicts the most appropriate conclusion based on data collected while the meeting is in progress.

[1845] The "means for acquiring the results of past meetings from a database" is a function for searching and acquiring the results of meetings that were previously held from a database.

[1846] "Means for automatically generating optimal conclusions using a generative AI model" refers to a function that uses artificial intelligence technology to automatically generate optimal conclusions based on collected data.

[1847] The "means for outputting the generated conclusion" is a function for displaying the generated conclusion to the user.

[1848] In the system for carrying out the present invention, a server, a terminal, and a user work in cooperation with each other. The server includes a means for preparing a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a function for predicting the optimal conclusion at that time from an objective point of view, a means for acquiring the results of past meetings from a database, a means for automatically generating an optimal conclusion using a generative AI model, and a means for outputting the generated conclusion.

[1849] The server first collects the meeting agenda and the opinions of the participants. This includes the function of collecting information entered by users in real time using terminals (such as smartphones and tablets). Next, the server retrieves the results of past meetings from a database and automatically generates optimal conclusions based on this data using a generative AI model.

[1850] The generative AI model uses advanced natural language processing techniques such as OpenAI's GPT-3. The server inputs the collected topics, opinions, and past results as prompts into the generative AI model to generate the optimal conclusion. The generated conclusion is displayed to the user through the terminal.

[1851] As a concrete example, the following prompt sentence is input to the generative AI model:

[1852] Agenda: Improving production line efficiency

[1853] opinion:

[1854] Person A: We should get new machines.

[1855] Person B: We should review our work procedures.

[1856] Person C: Working hours should be adjusted.

[1857] Past results:

[1858] Reconfiguring production lines increases efficiency by 10%

[1859] New software implementation reduces error rate by 5%

[1860] Generate the best conclusion.

[1861] Based on this prompt, the generative AI model outputs the optimal conclusion, such as "Production efficiency can be further improved by combining the introduction of new machinery with a review of work procedures."

[1862] This system makes it possible to streamline meetings and automatically generate optimal conclusions, and can handle the many different views within an organization. The hardware used includes mobile devices such as smartphones and tablets, and the software uses Python, SQLite, and OpenAI API.

[1863] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1864] Step 1:

[1865] The server collects the meeting agenda and the opinions of the participants. The user inputs the meeting agenda and their opinions using a terminal (such as a smartphone or tablet). The input data is sent to the server and stored in a database. In this way, the meeting agenda and the opinions of the participants are collected.

[1866] Step 2:

[1867] The server retrieves the results of past conferences from the database. The server queries the database to search for the results of past conferences. The retrieved data is temporarily stored in the server. In this way, the results of past conferences are retrieved.

[1868] Step 3:

[1869] The server generates prompt sentences based on the collected topics, opinions, and past results. The server converts the collected data into text format and creates prompt sentences to input to the generative AI model. This generates prompt sentences to input to the generative AI model.

[1870] Step 4:

[1871] The server automatically generates an optimal conclusion using a generative AI model. The server inputs the generated prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) and generates an optimal conclusion. The generative AI model performs data calculations based on the input prompt sentence and outputs an optimal conclusion. In this way, the optimal conclusion is automatically generated.

[1872] Step 5:

[1873] The server transmits the generated conclusion to the terminal and displays it to the user. The server transmits the generated conclusion to the terminal and allows the user to view it. The user can check the generated conclusion through the terminal. Thus, the generated conclusion is displayed to the user.

[1874] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1875] "Example 1"

[1876] One embodiment of the present invention is a system that combines an emotion engine that recognizes the emotions of a user. This system includes a means for creating a meeting conclusion in advance, a means for shortening the time of the meeting, a means for reducing the number of meetings, and a function for predicting the optimal conclusion at that time from an objective point of view. The emotion engine recognizes the user's emotions, and controls the means for creating a meeting conclusion in advance based on the emotions. Specifically, if the user's emotions are positive, a meeting conclusion is created in advance in a positive direction. Conversely, if the user's emotions are negative, a meeting conclusion is created in advance in a cautious direction.

[1877] "Example 2"

[1878] The emotion engine also controls a function that recognizes the user's emotions and predicts the optimal conclusion at that time from an objective point of view based on those emotions. Specifically, if the user's emotions are positive, the optimal conclusion at that time is predicted to be in the positive direction. Conversely, if the user's emotions are negative, the optimal conclusion at that time is predicted to be in the cautious direction. In this way, by taking the user's emotions into consideration, it becomes possible to create a more appropriate meeting conclusion in advance and predict the optimal conclusion at that time.

[1879] The process flow of each embodiment will be described below.

[1880] "Example 1"

[1881] Step 1: A user starts a conference.

[1882] Step 2: The emotion engine recognizes the user's emotion.

[1883] Step 3: Pre-create a meeting conclusion based on the emotions recognized by the emotion engine.

[1884] Step 4: Present the pre-created conclusions to the user.

[1885] Step 5: The user reviews the proposed conclusions and modifies them if necessary.

[1886] "Example 2"

[1887] Step 1: A user starts a conference.

[1888] Step 2: The emotion engine recognizes the user's emotion.

[1889] Step 3: Based on the emotions identified by the emotion engine, an objective guess is made as to the best outcome at that point in time.

[1890] Step 4: Present the best guess to the user.

[1891] Step 5: The user reviews the proposed conclusions and modifies them if necessary.

[1892] Example 1

[1893] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1894] In conventional conference systems, it was difficult to efficiently reach a meeting conclusion, and meetings often dragged on. In addition, there was a tendency for the number of meetings to increase, which increased the burden on participants. Furthermore, the conclusions of meetings tended to be subjective and often influenced by the emotions of participants. There is a need to solve these problems and improve the efficiency and optimization of meetings.

[1895] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1896] In this invention, the server includes a means for creating a meeting conclusion in advance, a means for shortening the meeting time, a means for reducing the number of meetings, a means for recognizing the user's emotions and adjusting the meeting conclusion based on the emotions, and a function for predicting the optimal conclusion at that time from an objective point of view. This makes it possible to efficiently create a meeting conclusion, shorten the meeting time, and select only the necessary meetings. In addition, by adjusting the conclusion taking the user's emotions into account, a more objective and appropriate conclusion can be derived.

[1897] "A means of preparing meeting conclusions in advance" refers to a function that collects meeting agendas and participants' opinions, and automatically generates conclusions based on them.

[1898] "Means of shortening meeting times" refers to functions that provide scheduling and agenda management functions to make meetings more efficient.

[1899] "Means of reducing the number of meetings" refers to the ability to provide optimization functions to schedule only necessary meetings.

[1900] "Means for recognizing a user's emotions and adjusting the conclusion of the meeting based on those emotions" refers to a function for analyzing a user's emotions and adjusting the conclusion of the meeting in a positive or cautious direction depending on those emotions.

[1901] "A function that can predict the optimal conclusion at any given time from an objective perspective" refers to a function that automatically predicts the most appropriate conclusion based on collected data and user emotions.

[1902] The present invention relates to a system for improving the efficiency and optimizing a conference. A specific embodiment of the system will be described below.

[1903] A means of preparing meeting conclusions in advance

[1904] The server uses APIs of common communication tools (e.g., communication platforms and messaging applications) to collect meeting agendas and participant opinions. The collected data is stored in a database. The server then uses a generative AI model (e.g., a natural language processing model) to automatically generate a conclusion based on the collected data. Specifically, the server inputs the following prompt sentence into the generative AI model:

[1905] "The topic of the meeting is XX, and the opinions of the participants are △△. Please generate a conclusion based on this."

[1906] The generated conclusions are again stored in the database.

[1907] A way to shorten meeting times

[1908] The server optimizes meeting schedules using scheduling software (e.g., a calendar application) to automatically adjust meeting start and end times, and uses a project management tool (e.g., a task management application) to manage agendas by creating tasks for each agenda item and tracking their progress.

[1909] A means to reduce the number of meetings

[1910] The server uses machine learning algorithms to analyze past meeting data and select only necessary meetings. Specifically, it uses a Python machine learning library to build a model that evaluates the importance of meetings. This model evaluates the necessity of meetings and schedules only high-importance meetings.

[1911] A means of recognizing a user's emotions and adjusting the outcome of a meeting based on those emotions

[1912] The terminal uses an emotion analysis engine (e.g., emotion recognition API) to recognize the user's emotions. The terminal analyzes the user's speech and facial expressions to obtain emotion data. The obtained emotion data is sent to the server. The server adjusts the conclusion based on the emotion data. For example, if the user's emotion is positive, the server corrects the conclusion in a positive direction. Conversely, if the user's emotion is negative, the server corrects the conclusion in a cautious direction.

[1913] Examples

[1914] For example, if the topic of a meeting is "New product launch strategy" and the participants' opinions are "We should conduct an aggressive marketing campaign," we can input the following prompt into the generative AI model:

[1915] "The topic of the meeting should be a new product launch strategy, and the participants' input should be about an aggressive marketing campaign. Use this as a basis for generating conclusions."

[1916] Based on this prompt, the generative AI model generates the conclusion that "it is optimal to conduct an aggressive marketing campaign as a new product launch strategy." If the user's sentiment is positive, the sentiment engine sends this information to the server, which then generates a positive conclusion. For example, it generates the conclusion that "since the user's sentiment is positive, it is recommended to further strengthen the marketing campaign."

[1917] In this way, the system of the present invention realizes efficiency and optimization of meetings.

[1918] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1919] Step 1:

[1920] The server collects the meeting agenda and participant opinions.

[1921] Specifically, the server uses the communication platform's API to obtain the chat log and minutes of the meeting.

[1922] Input: Meeting chat logs, minutes

[1923] Output: Collected topics and opinion data

[1924] Step 2:

[1925] The server stores the collected topics and opinions in a database.

[1926] As a specific operation, the server executes an INSERT query on the database to insert data into the agenda table and the opinion table.

[1927] Input: Collected agenda and opinion data

[1928] Output: Topics and opinions stored in a database

[1929] Step 3:

[1930] The...

Claims

1. a first means for collecting meeting agendas and opinions of participants in said meeting; A second means for retrieving results of past meetings from a database; a third means for generating a prompt sentence for outputting an optimal conclusion of the meeting based on the agenda of the meeting, the opinions of the participants, and the results of the past meetings; A fourth means for inputting the generated prompt sentence into a generative AI model to generate an optimal conclusion for the meeting; A fifth means for transmitting the generated optimal outcome of the conference to a user terminal; A system including:

2. a sixth means for acquiring emotion data of the user from utterances and facial expressions of the user using an emotion analysis engine; The third means adjusts the prompt sentence based on emotion data of the user. The system of claim 1 .

3. The fourth means modifies the optimal conclusion of the conference to be generated in a positive direction when the emotion data of the user indicates a positive emotion, and modifies the optimal conclusion of the conference to be generated in a cautious direction when the emotion data of the user indicates a negative emotion. The system of claim 2.

Images