System

Abstract

To provide a system that shortens the time required for conversation in a text in an in-house communication tool and accumulates and utilizes the contents of interaction as business know-how data.SOLUTION: A system includes: means for shortening conversation time in a text using a summarizing function of AI in an in-house communication tool; means for accumulating contents of in-house communication as data of business know-how; means for learning the accumulated data by AI; means for storing data received by a server in a database; means for acquiring the data from the database and preprocessing using a data analysis tool; means for inputting the preprocessed data into a generative AI model and extracting a pattern of business know-how; means for generating new business know-how on the basis of the extracted pattern and storing it in the database; and means for allowing a user to refer to the generated business know-how through a terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The challenges are to reduce the time required for text conversations in internal communication tools and to accumulate and utilize the content of those conversations as business know-how data. [Means for solving the problem]

[0005] To solve this problem, we provide a system that uses AI's summarization function to shorten the time spent on text conversations and accumulates the content of those exchanges as business know-how data. Furthermore, we use AI to learn from the accumulated data and use it to improve business operations. [Brief explanation 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. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 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. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0009] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[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 symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), 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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[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, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0023] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[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 process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. 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.

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

[0027] "Example 1"

[0028] As one embodiment of the present invention, an AI summarization function is incorporated into an internal communication tool. Specifically, when users are engaged in text conversations, the AI ​​summarizes the content in real time and displays it to the user. This allows users to save time reading long texts and obtain information efficiently.

[0029] "Example 2"

[0030] Furthermore, the content of conversations between users is stored as business know-how data. Specifically, the content of conversations is saved as text data and stored in a database. This makes it possible to refer to the content of past conversations, contributing to improved business efficiency.

[0031] "Example 3"

[0032] Furthermore, the accumulated data is learned by AI. Specifically, the AI ​​analyzes the accumulated data and extracts patterns of business know-how. For example, it learns response patterns when specific problems arise, and communication patterns for efficient business progress. This allows the AI ​​to generate new business know-how that can be used to improve business operations.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: A user opens an internal communication tool and starts a text conversation.

[0036] Step 2: The AI ​​summarizes the conversation in real time and displays it to the user. Specifically, the AI ​​analyzes the text data, extracts key information, and generates a summary.

[0037] Step 3: The user reviews the summary generated by the AI ​​and efficiently obtains the necessary information.

[0038] "Example 2"

[0039] Step 1: The conversation between users is saved as text data.

[0040] Step 2: The saved text data is stored in a database.

[0041] Step 3: The user can refer to the database for past conversations as needed.

[0042] "Example 3"

[0043] Step 1: The AI ​​analyzes the accumulated data. Specifically, the AI ​​analyzes the text data in the database and extracts patterns of business know-how.

[0044] Step 2: Generate new business know-how based on the patterns extracted by AI.

[0045] Step 3: The generated business know-how is used to improve business operations. For example, by referencing response patterns when a specific problem occurs, the company can quickly respond if a similar problem occurs.

[0046] Example 1

[0047] 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 device 14 will be referred to as a "terminal."

[0048] Conventional internal communication tools have the problem that it takes time to read long text messages, making it difficult to share information efficiently. There was also a need for a system that could accumulate the content of exchanges as business know-how and further utilize that data to improve business operations and generate new know-how.

[0049] 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.

[0050] In this invention, the server includes: means for transmitting text entered by a user from a terminal to the server; means for the server to analyze the received text using a natural language processing library; means for the server to send a prompt sentence to a generative AI model based on the analysis results; means for the generative AI model to generate a summary; means for the server to send the generated summary to the terminal; means for the terminal to display the summary to the user; means for accumulating the content of the exchange as business know-how data; and means for AI to learn from the accumulated data. This allows users to efficiently obtain information without having to read long texts. Furthermore, the accumulated data can be used to improve business operations and generate new business know-how.

[0051] An "internal communication tool" is software that allows for efficient information sharing and communication within a company or organization.

[0052] The "AI summary function" is a function that uses artificial intelligence to summarize long texts in a shorter form.

[0053] The "means for shortening text conversation time" is a means for summarizing long texts entered by a user, allowing the user to grasp the content in a short time.

[0054] The "means for transmitting text entered by a user from a terminal to a server" refers to a means for transmitting text data entered by a user into a terminal to a server via a network.

[0055] The "means for analyzing text received by the server using a natural language processing library" refers to a means for analyzing text data received by the server using a software library for natural language processing.

[0056] "Means for the server to send a prompt sentence to the generative AI model based on the analysis results" refers to means for the server to send a prompt sentence to the generative AI model to request a summary based on the text data analyzed.

[0057] The "means by which the generative AI model generates a summary" is the means by which the generative AI model generates a summary of the text based on the prompt sentence.

[0058] "Means for the server to send the generated summary to the terminal" refers to means for the server to send the summary received from the generative AI model to the user's terminal.

[0059] The "means for the terminal to display the summary to the user" refers to the means for the user's terminal to display the received summary on the screen.

[0060] "Business know-how data" refers to the accumulation of business-related knowledge and experience as data.

[0061] "Means of learning accumulated data using AI" refers to means of having artificial intelligence learn accumulated business know-how data.

[0062] "Means for business improvement" refers to the analysis of accumulated data to improve business efficiency and quality.

[0063] "Means for generating new business know-how" refers to means for creating new business knowledge and methods based on the learning results of AI.

[0064] This invention is a system that incorporates an AI summarization function into an internal communication tool. When users have a text conversation, the AI ​​summarizes the content in real time and displays it to the user, saving them the time of reading long texts and allowing them to obtain information efficiently.

[0065] Hardware and software used

[0066] Hardware:

[0067] server

[0068] Devices (PCs, smartphones, tablets, etc.)

[0069] software:

[0070] Natural language processing libraries (e.g. spaCy)

[0071] Generative AI models (e.g., GPT-4 (registered trademark))

[0072] Internal communication tools

[0073] Data processing and calculation

[0074] The user enters text

[0075] A user types text into a chat window in an internal communication tool, for example, "I'd like to discuss the agenda for our next meeting."

[0076] The device sends the text to the server

[0077] The terminal sends the text entered by the user to the server. At this time, the text data is sent as an HTTP request.

[0078] The server receives and parses the text

[0079] The server receives the text sent from the device. The received text is analyzed using a natural language processing library (e.g., spaCy). As a result of the analysis, the context of the text and important keywords are extracted.

[0080] The server sends a prompt to the generative AI model

[0081] The server generates a prompt to send to a generative AI model (e.g., GPT-4) based on the analysis results. For example, it generates a prompt such as, "Please summarize the following text: I would like to discuss the agenda for the next meeting."

[0082] A generative AI model generates a summary

[0083] The generative AI model receives the prompt sent from the server and generates a summary, for example, "I would like to discuss the meeting agenda."

[0084] The server receives the summary and sends it to the device.

[0085] The server receives the summary returned by the generative AI model, which is then sent back to the device as an HTTP response.

[0086] The terminal displays the summary to the user

[0087] The terminal displays the summary received from the server in the user's chat window, thereby saving the user the trouble of reading long texts and enabling them to obtain information efficiently.

[0088] Examples of specific examples and prompts

[0089] For example, if a user types "I'd like to discuss the agenda for our next meeting," the following happens:

[0090] 1. The user enters the text "I'd like to discuss the agenda for our next meeting."

[0091] 2. The device sends this text to the server.

[0092] 3. The server receives the text and uses spaCy to extract keywords such as "meeting," "agenda," and "discussion."

[0093] 4. The server generates a prompt sentence: "Please summarize the following text: I would like to discuss the agenda for the next meeting" and sends it to the generative AI model.

[0094] 5. The generative AI model generates a summary such as "I would like to discuss the meeting agenda."

[0095] 6. The server receives this summary and sends it to the terminal.

[0096] 7. The device displays the summary in the user's chat window.

[0097] In this way, users can obtain information efficiently without having to read long texts. Furthermore, the content of the interactions is accumulated as business know-how data, which can be used to improve business operations and generate new business know-how through AI learning.

[0098] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0099] Step 1:

[0100] The user enters text.

[0101] A user inputs text into a chat window of an internal communication tool. For example, the user inputs "I would like to discuss the agenda for the next meeting." The input text becomes the input data for the next processing step.

[0102] Step 2:

[0103] The device sends the text to the server.

[0104] The terminal sends the text entered by the user to the server as an HTTP request. The input data is the text entered by the user, and the output data is the text data sent to the server.

[0105] Step 3:

[0106] The server receives and parses the text.

[0107] The server receives the text sent from the device. The received text is analyzed using a natural language processing library (e.g., spaCy). As a result of the analysis, the context of the text and important keywords are extracted. The input data is the received text, and the output data is the analysis result.

[0108] Step 4:

[0109] The server sends a prompt to the generative AI model.

[0110] The server generates a prompt sentence to be sent to the generative AI model based on the analysis results. For example, it generates a prompt sentence such as "Please summarize the following text: I would like to discuss the agenda for the next meeting." The generated prompt sentence becomes the input data for the next processing step.

[0111] Step 5:

[0112] A generative AI model generates the summary.

[0113] The generative AI model receives a prompt sent from the server and generates a summary, for example, "I would like to discuss the meeting agenda." The input data is the prompt, and the output data is the generated summary.

[0114] Step 6:

[0115] The server receives the summary and sends it to the terminal.

[0116] The server receives the summary returned from the generative AI model. The received summary is then sent to the terminal as an HTTP response. The input data is the generated summary, and the output data is the summary sent to the terminal.

[0117] Step 7:

[0118] The terminal displays the summary to the user.

[0119] The terminal displays the summary received from the server in the user's chat window, which allows the user to obtain information efficiently without having to read long text. The input data is the summary received from the server, and the output data is the summary displayed to the user.

[0120] (Application example 1)

[0121] Next, a description will be given of Application Example 1 of Embodiment 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."

[0122] Conventional internal communication tools often involve long text exchanges, making it difficult for users to efficiently obtain information. Furthermore, in the operation management of autonomous vehicles, there was a lack of a way to efficiently grasp conversations and instructions during operation. This resulted in issues such as operational managers and passengers being unable to quickly obtain important information, resulting in reduced operational efficiency.

[0123] 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.

[0124] In this invention, the server includes: a means for shortening text conversation time using an AI summarization function in an internal communication tool; a means for accumulating the content of the exchange as business know-how data; a means for learning the accumulated data using AI; and, in an autonomous vehicle operation management system, a means for converting conversation into text using speech recognition; a means for summarizing the text using a generative AI model; and a means for converting the summarized text into speech and playing it back. This allows users to save time reading long texts and obtain information efficiently. It also improves the efficiency of communication within autonomous vehicles, enabling smoother operation management.

[0125] An "internal communication tool" is software that allows for efficient information sharing and communication within a company.

[0126] The "AI summary function" is a function that uses artificial intelligence to summarize long texts in a shorter form.

[0127] "Text conversation time-saving methods" are methods that users use to streamline and save time in text-based communication.

[0128] "Business know-how data" refers to the accumulation of business-related knowledge and experience as data.

[0129] "Storage means" refers to the method by which data is stored and made available for later use.

[0130] "Means of learning with AI" refers to a method of using artificial intelligence to analyze accumulated data and learn patterns and knowledge.

[0131] An "autonomous vehicle" is a vehicle that operates autonomously using artificial intelligence and sensor technology.

[0132] A "traffic management system" is a system for monitoring and controlling vehicle operations.

[0133] "Speech recognition" is a technology that converts speech into text.

[0134] A "generative AI model" is an artificial intelligence model trained to perform tasks such as text generation and summarization.

[0135] A "summarization tool" is a method for summarizing a long text in a short form.

[0136] "Means of converting to audio and playing" refers to a method of converting text to audio and playing it through a speaker or the like.

[0137] An embodiment of this invention will be described. First, a system is constructed that shortens text conversation time using an AI summarization function in an internal communication tool. In this system, when users have a text conversation, the AI ​​summarizes the content in real time and displays it to the user. This allows users to save time reading long texts and obtain information efficiently.

[0138] Next, the system includes a means for accumulating the content of interactions as business know-how data. The accumulated data is then learned by AI and used to improve business operations and generate new business know-how.

[0139] Furthermore, this invention has application in a fleet management system for autonomous vehicles, where the fleet management system converts conversations taking place in the vehicle into text using speech recognition, then uses a generative AI model to summarize the text, which is then converted into audio and played back to the driver or passengers.

[0140] Specifically, the server performs the following processes. First, it uses speech recognition technology to convert the conversation in the vehicle into text. For example, the speech recognition software used here can be Google's (registered trademark) speech recognition API. Next, it uses a generative AI model (e.g., OpenAI's (registered trademark) GPT-3 (registered trademark)) to summarize the converted text. For this summarization process, it uses the prompt "Please summarize the following text:" Finally, it uses the gTTS (Google Text-to-Speech) library to convert the summarized text into speech and play it back.

[0141] As a concrete example, if a dispatcher in an autonomous vehicle asks, "Where is the next stop?", speech recognition technology converts the question into text, and a generative AI model summarizes it as, "Confirm next stop." The summarized text is then converted into speech and played back to the driver or passengers.

[0142] An example of a prompt is as follows:

[0143] "Summarize the following text: Where is the next stop?"

[0144] In this way, users can obtain information efficiently without having to read long texts, and communication within autonomous vehicles will be made more efficient, enabling smoother operation management.

[0145] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0146] Step 1:

[0147] The server uses voice recognition technology to convert conversations taking place inside the vehicle into text. Specifically, the voice data acquired from the microphone as voice input is sent to Google's voice recognition API, which then outputs it as text data. This process converts the voice data into text data.

[0148] Step 2:

[0149] The server uses a generative AI model to summarize the converted text. Specifically, it sends the text data obtained in step 1 as input to OpenAI's GPT-3 model along with the prompt "Please summarize the following text:" and obtains the summarized text as output. This process results in a short summary of the long text.

[0150] Step 3:

[0151] The server converts the summarized text into audio and plays it back. Specifically, it uses the summarized text obtained in step 2 as input and generates an audio file using the gTTS (Google Text-to-Speech) library, and plays the audio file through a speaker. This process provides the summarized information to the user as audio.

[0152] Step 4:

[0153] The user listens to the audio and obtains the necessary information. Specifically, the operation manager and passengers listen to the audio coming from the speaker and decide on the next course of action. This process allows the user to obtain information efficiently and take appropriate action.

[0154] Example 2

[0155] Next, a description will be given of 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."

[0156] With conventional internal communication tools, it was difficult to efficiently accumulate conversations between users and utilize them as business know-how. Furthermore, the process of converting voice data into text data and saving it in a database was often done manually, preventing business efficiency. Furthermore, there was a lack of a way to effectively learn from the accumulated data and generate new business know-how.

[0157] 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.

[0158] In this invention, the server includes means for capturing conversations between users as voice data, means for converting the captured voice data into text data, and means for storing the converted text data in a database, thereby enabling the conversations between users to be efficiently accumulated and utilized as business know-how.

[0159] "User" refers to an individual or group that uses the system to engage in conversation.

[0160] "Voice data" refers to data that is recorded in digital format using a voice input device such as a microphone to record the contents of a user's conversation.

[0161] "Capture" refers to the process of acquiring and recording audio data in real time.

[0162] "Text data" refers to data obtained by converting voice data into character information.

[0163] "Conversion" refers to the process of turning audio data into text data.

[0164] A "database" refers to a system for systematically storing and managing text data.

[0165] "Business know-how data" refers to knowledge and information about business obtained from the content of conversations between users.

[0166] A "generative AI model" refers to an artificial intelligence model that learns from accumulated data and generates new knowledge and information.

[0167] "Learning" refers to the process by which a generative AI model analyzes accumulated data and extracts patterns and knowledge.

[0168] "Business improvement" refers to the process of using accumulated data and the learning results of generative AI models to improve business efficiency and quality.

[0169] "New business know-how" refers to new knowledge and information obtained from the learning results of the generative AI model.

[0170] The present invention is a system for efficiently storing conversational content between users and utilizing it as business know-how. A specific embodiment of this system will be described below.

[0171] First, the user starts a business conversation. When the user starts the conversation, the device captures the voice data through the microphone. The device has voice capture software (e.g., Audacity) installed. The captured voice data is sent to the server in real time using the HTTP protocol.

[0172] The server converts the received voice data into text data using the Google Cloud Speech-to-Text API. The converted text data is used as business know-how data. The server saves the converted text data in a MySQL (registered trademark) database. When saving, the date and time of the conversation and participant information are also recorded.

[0173] Users can search and refer to past conversations through a dedicated interface, for example, by accessing the database using a web browser. This allows users to easily refer to past conversations, contributing to improved work efficiency.

[0174] For example, suppose user A and user B start talking about the progress of a project. When user A says, "Let's schedule the next meeting for next Tuesday," the device captures this voice data and sends it to the server. The server converts the voice data into text using the Google Cloud Speech-to-Text API, generating the text data, "Let's schedule the next meeting for next Tuesday." This text data is then stored in a MySQL database.

[0175] Examples of prompts to be input to a generative AI model include:

[0176] "User A and User B were talking about the progress of a project. User A said, 'Let's set up the next meeting for next Tuesday.' How can I save this conversation as text data and store it in a database?"

[0177] This system allows users to easily refer to past conversations, contributing to improved work efficiency. Additionally, by using a generative AI model to learn from the accumulated data, it becomes possible to generate new business know-how.

[0178] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0179] Step 1:

[0180] A user initiates a conversation.

[0181] Input: User's voice

[0182] Output: Audio data

[0183] What happens: User A and User B start talking about the progress of a project. User A says, "Let's schedule the next meeting for next Tuesday."

[0184] Step 2:

[0185] The device captures the audio data.

[0186] Input: User's voice

[0187] Output: Digital audio data

[0188] Specific operation: The device captures user A's speech as audio data through the microphone. Audio capture software (e.g., Audacity) records the audio data in real time.

[0189] Step 3:

[0190] The terminal transmits the voice data to the server.

[0191] Input: Digital audio data

[0192] Output: Audio data sent to the server

[0193] How it works: The device sends the recorded audio data to the server using the HTTP protocol, using the Python requests library.

[0194] Step 4:

[0195] The server converts the voice data into text data.

[0196] Input: Audio data sent to the server

[0197] Output: Text data

[0198] What happens next: The server calls the Google Cloud Speech-to-Text API to convert the voice data into text, which then becomes "Let's schedule our next meeting for next Tuesday."

[0199] Step 5:

[0200] The server stores the text data in a database.

[0201] Input: Text data

[0202] Output: Text data stored in a database

[0203] How it works: The server saves the converted text data in a MySQL database, along with the date and time of the conversation and participant information.

[0204] Step 6:

[0205] Users can view past conversations.

[0206] Input: Text data stored in a database

[0207] Output: Text data as search results

[0208] Specific operation: Users open a web browser and access the database through a dedicated interface. User A can easily search and refer to past conversations such as "Let's schedule the next meeting for next Tuesday."

[0209] (Application example 2)

[0210] 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."

[0211] In logistics centers, inefficient communication between staff can lead to delays and mistakes. Furthermore, because past conversations cannot be referenced, the same questions and confirmations are often repeated, resulting in a decline in work efficiency. To solve these issues, a system that can efficiently store and reference the conversations between staff is needed.

[0212] 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.

[0213] In this invention, the server includes means for shortening text conversation time using an AI summarization function in an internal communication tool, means for accumulating the content of the exchange as business know-how data, means for learning the accumulated data using AI, means for saving the content of the conversation as text data using voice recognition technology, means for storing the saved text data in a cloud database, and means for making the saved text data accessible. This improves the efficiency of communication between staff at the logistics center and makes it easy to refer to the content of past conversations.

[0214] "Internal communication tools" are software and platforms that enable efficient information sharing and communication within a company.

[0215] The "AI summary function" is a function that uses artificial intelligence to summarize long texts and conversations in a concise manner.

[0216] "Methods for shortening text conversation time" refers to a method for reducing the time required for text exchange by summarizing the content of the conversation.

[0217] "Business know-how data" refers to the accumulated data of knowledge and experience gained in the course of carrying out business.

[0218] "Means of using AI to learn from accumulated data" refers to a method of having artificial intelligence learn from accumulated business know-how data.

[0219] "Speech recognition technology" is a technology that converts voice into text data.

[0220] "Means for saving as text data" refers to a method for saving text data obtained using speech recognition technology.

[0221] A "cloud database" is a database that is accessible via the Internet.

[0222] "Means for making stored text data accessible" refers to a method for making stored text data easily searchable and accessible later.

[0223] The system for carrying out the present invention is designed to improve the efficiency of communication between staff members at a logistics center. A specific embodiment of this system is described below.

[0224] Hardware and software used

[0225] Hardware: Smartphone, microphone

[0226] Software: Python, SpeechRecognition library, SQLite database, cloud storage service

[0227] System configuration

[0228] 1. Speech recognition technology: An application installed on a smartphone collects staff's speech in real time through a microphone and converts it into text data using the SpeechRecognition library.

[0229] 2. Data storage: The converted text data is temporarily stored on the smartphone, and then stored in a cloud database using a cloud storage service.

[0230] 3. Database Management: The accumulated text data is managed using an SQLite database, which stores the conversation timestamp, user name, and conversation content.

[0231] 4. Data Reference: The accumulated text data is designed to be easily searchable and accessible later. Staff can search for past conversations via their smartphones and use them in their work.

[0232] Processing flow

[0233] 1. Speech Recognition: The employee launches the smartphone application and starts a conversation. The microphone collects the voice and the SpeechRecognition library converts the voice into text.

[0234] 2. Data storage: The converted text data is temporarily stored on the smartphone along with a timestamp and the user name, and then transferred to a cloud database via a cloud storage service.

[0235] 3. Data reference: Staff can use a smartphone application to search and reference past conversations from a database on the cloud.

[0236] Specific examples

[0237] For example, if a staff member at a logistics center asks, "Where is the next delivery destination?", the conversation is saved as text data. Later, when another staff member asks the same question, they can refer to the past conversation and get a quick answer.

[0238] Prompt Sentence Examples

[0239] If you ask the question "Where is the next delivery destination?" the prompt text will be as follows:

[0240] User: Where is my next delivery?

[0241] System: Your conversation has been saved.

[0242] In this way, the operational efficiency of the logistics center can be improved.

[0243] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0244] Step 1:

[0245] The user launches the application on their smartphone and starts a conversation.

[0246] Input: User's voice

[0247] Output: Audio data collected by microphone

[0248] Specific operation: The user launches an application on their smartphone and the microphone collects audio.

[0249] Step 2:

[0250] The terminal uses voice recognition technology to convert the collected voice data into text data.

[0251] Input: Audio data

[0252] Output: Text data

[0253] Specific operation: The device uses the SpeechRecognition library to convert the voice data into text data.

[0254] Step 3:

[0255] The terminal temporarily stores the converted text data.

[0256] Input: Text data

[0257] Output: Temporarily saved text data

[0258] What it does: The device temporarily stores the text data on your smartphone along with a timestamp and your username.

[0259] Step 4:

[0260] The device transfers the temporarily stored text data to a database on the cloud.

[0261] Input: Temporarily saved text data

[0262] Output: Text data stored in a cloud database

[0263] Specific operation: The device uses a cloud storage service to transfer text data to a database on the cloud.

[0264] Step 5:

[0265] The server manages the text data stored in a database on the cloud.

[0266] Input: Text data stored in a cloud database

[0267] Output: Managed text data

[0268] Specific operation: The server uses an SQLite database to manage the accumulated text data.

[0269] Step 6:

[0270] Users use a smartphone application to search and view past conversations from a database on the cloud.

[0271] Input: search query

[0272] Output: Text data as search results

[0273] How it works: A user uses a smartphone application to send a search query to a database in the cloud, and the server returns the relevant text data.

[0274] Example 3

[0275] Next, a description will be given of a third embodiment of the third embodiment. 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] Conventional internal communication tools tend to require long text conversations, which often hinders efficient work progress. Furthermore, there was a lack of effective ways to utilize accumulated business data, preventing the sharing of business know-how and business improvements. Furthermore, there was no effective method for generating new business know-how based on accumulated data. To solve these issues, a system was needed that could efficiently process and analyze data and effectively generate and share business know-how.

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

[0278] In this invention, the server includes means for a user to input business data and send it to the server, means for the server to save the received data in a database, means for the server to retrieve data from the database and preprocess it using a data analysis tool, means for the server to input the preprocessed data into a generative AI model and extract patterns of business know-how, means for the server to generate new business know-how based on the patterns extracted and save it in the database, and means for a user to refer to the generated business know-how through a terminal. This enables efficient data processing and analysis, and enables the effective generation and sharing of business know-how.

[0279] An "internal communication tool" is software that facilitates information sharing and communication within a company.

[0280] "Artificial intelligence" refers to computer systems that mimic human intelligence and can learn and reason.

[0281] The "summarization function" is a function that summarizes long texts in a short form, extracting important information and expressing it concisely.

[0282] "Business know-how data" refers to the accumulated knowledge and experience necessary for carrying out business.

[0283] A "database" is a system for efficiently storing, managing, and searching large amounts of data.

[0284] A "data analysis tool" is software used to analyze data and extract meaningful information.

[0285] A "generative AI model" is an artificial intelligence model that generates new information and patterns based on input data.

[0286] "Pattern extraction" is the process of finding common characteristics and patterns in data.

[0287] "Business know-how" refers to the knowledge and skills required to carry out business efficiently.

[0288] A "terminal" is a device such as a computer or smartphone that is operated by a user.

[0289] MODE FOR CARRYING OUT THE INVENTION

[0290] This invention is a system that shortens text conversation time using an AI summarization function in an internal communication tool, accumulates the content of that exchange as business know-how data, and further uses AI to learn from the accumulated data. This system includes: a means for a user to input business data and send it to a server; a means for the server to store the received data in a database; a means for the server to retrieve data from the database and preprocess it using a data analysis tool; a means for the server to input the preprocessed data into a generative AI model and extract patterns of business know-how; a means for the server to generate new business know-how based on the patterns extracted and store it in a database; and a means for a user to refer to the generated business know-how via a terminal.

[0291] Hardware and software used

[0292] Hardware: Servers, terminals

[0293] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), data analysis tools (e.g., Python's pandas library)

[0294] Explanation of program processing

[0295] 1. Data entry and storage

[0296] The user inputs business data from the terminal, such as details of complaint handling and records of work progress.

[0297] The terminal transmits the input data to the server.

[0298] The server stores the received data in a database, typically using a database management system such as MySQL.

[0299] 2. Data Preprocessing

[0300] The server periodically retrieves the accumulated data from the database.

[0301] The server preprocesses the acquired data using a data analysis tool (e.g., Python's pandas library), specifically cleaning the data (filling in missing values ​​and removing outliers) and standardizing the format.

[0302] 3. Data analysis using AI models

[0303] The server inputs the preprocessed data into a generative AI model (e.g., GPT-4).

[0304] The generative AI model analyzes data and extracts patterns of business know-how, such as patterns for responding to specific problems and communication patterns for efficient business progress.

[0305] 4. Generation of business know-how

[0306] The server generates new business know-how based on the patterns extracted by the generative AI model. For example, it generates specific procedures such as "When a complaint occurs, first apologize to the customer, then check the details of the problem."

[0307] The server stores the generated business know-how in a database.

[0308] 5. Preservation and provision of generated know-how

[0309] The server allows users to refer to new business know-how stored in the database.

[0310] Users can access the database through their terminals and view the generated business know-how.

[0311] Specific examples

[0312] For example, a user inputs "procedures for handling complaints" from a terminal. The terminal sends this data to a server, which stores it in a database. The server periodically retrieves this data and cleans it using the pandas library. The server then inputs the preprocessed data into GPT-4, and the generative AI model extracts patterns for handling complaints. For example, a pattern may be found that "when a complaint occurs, first apologize to the customer, then confirm the details of the problem." Based on this pattern, the server generates a new procedure for handling complaints and stores it in a database. The user can view this new procedure through their terminal and use it in their actual work.

[0313] Prompt Sentence Examples

[0314] An example of a prompt sentence to input to the generative AI model is as follows:

[0315] "Generate effective complaint handling procedures based on past complaint handling data."

[0316] By inputting this prompt sentence into the generative AI model, the model analyzes past data and generates a new procedure for handling complaints. The flow of the identification process in Example 3 will be described with reference to FIG. 15.

[0317] Step 1:

[0318] Data entry and accumulation

[0319] The user inputs business data from the terminal, such as details of complaint handling and records of work progress.

[0320] Input: Business data (e.g., complaint handling details)

[0321] The terminal transmits the input data to the server.

[0322] The server stores the received data in a database, typically using a database management system such as MySQL.

[0323] Output: Business data stored in a database

[0324] Step 2:

[0325] Data Preprocessing

[0326] The server periodically retrieves the accumulated data from the database.

[0327] Input: Business data stored in a database

[0328] The server preprocesses the acquired data using a data analysis tool (e.g., Python's pandas library), specifically cleaning the data (filling in missing values ​​and removing outliers) and standardizing the format.

[0329] Output: Preprocessed data

[0330] Step 3:

[0331] Data analysis using AI models

[0332] The server inputs the preprocessed data into a generative AI model (e.g., GPT-4).

[0333] Input: Preprocessed data

[0334] The generative AI model analyzes data and extracts patterns of business know-how, such as patterns for responding to specific problems and communication patterns for efficient business progress.

[0335] Output: Extracted business know-how patterns

[0336] Step 4:

[0337] Generation of business know-how

[0338] The server generates new business know-how based on the patterns extracted by the generative AI model. For example, it generates specific procedures such as "When a complaint occurs, first apologize to the customer, then check the details of the problem."

[0339] Input: Extracted business know-how patterns

[0340] The server stores the generated business know-how in a database.

[0341] Output: New business know-how stored in the database

[0342] Step 5:

[0343] Preservation and dissemination of generated know-how

[0344] The server allows users to refer to new business know-how stored in the database.

[0345] Input: New business know-how stored in the database

[0346] Users can access the database through their terminals and view the generated business know-how.

[0347] Output: Business know-how that can be viewed by users

[0348] (Application example 3)

[0349] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0350] In conventional factory operations, the collection and analysis of work data was often done manually, making it difficult to carry out work efficiently or respond quickly when problems occurred. In addition, there was a lack of accumulation of work know-how and the creation of new know-how, and improvements in work efficiency were required.

[0351] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for shortening text conversation time using an AI summary function in an in-house communication tool, means for accumulating the content of the exchange as business know-how data, means for AI learning from the accumulated data, means for collecting work data within the factory in real time and analyzing the data with AI, means for learning response patterns when specific problems occur and proposing optimal response methods, means for learning communication patterns for efficient work progress and issuing appropriate instructions to workers, and means for generating new business know-how and improving work efficiency. This makes it possible to efficiently collect and analyze work data within the factory, quickly respond to problems when they occur, and accumulate and generate business know-how.

[0352] An "internal communication tool" is software that allows for efficient information sharing and communication within a company.

[0353] The "AI summary function" is a function that uses artificial intelligence to summarize long pieces of text into shorter sentences.

[0354] "Text conversation time-saving methods" are methods for streamlining text-based communication and saving time.

[0355] "Business know-how data" refers to the accumulated knowledge and experience necessary for carrying out business.

[0356] "Means for AI to learn from accumulated data" refers to a method by which artificial intelligence analyzes and learns from accumulated data.

[0357] "Factory work data" refers to data related to various types of work carried out within a factory.

[0358] "Real-time collection means" refers to a method for collecting data in real time.

[0359] "The means by which the AI ​​analyzes the data" refers to the method by which the artificial intelligence analyzes the collected data.

[0360] The "response pattern when a specific problem occurs" is a pattern of response methods to be taken when a specific problem occurs.

[0361] "Means for proposing the most appropriate response method" is a method for proposing the most appropriate response method when a problem occurs.

[0362] "Communication patterns for efficient business progress" are methods of communication for efficiently progressing business.

[0363] "Means for issuing appropriate instructions to workers" refers to a method for providing appropriate instructions to workers.

[0364] "Means for generating new business know-how" refers to a method for creating new business know-how.

[0365] "Means for improving work efficiency" are methods for increasing work efficiency.

[0366] The system for implementing this invention is configured as follows: First, the server provides a means for shortening text conversation time using an AI summarization function in an internal communication tool, allowing users to communicate more efficiently.

[0367] Next, the server has the means to store the content of these interactions as business know-how data, which will later become an important source of information for the AI ​​to learn from.

[0368] Furthermore, the server provides a means for AI to learn from the accumulated data, allowing the AI ​​to learn patterns for responding to specific problems when they arise and communication patterns for efficient business operations.

[0369] The server also includes a means for collecting data on factory operations in real time, allowing the server to instantly collect data on various operations within the factory and analyze the data using AI.

[0370] The server also includes a means for learning response patterns when specific problems occur and proposing optimal response methods. This means allows the server to propose a quick and appropriate response when a problem occurs.

[0371] The server also includes a means for learning communication patterns for efficient work progress and issuing appropriate instructions to workers. This means enables the server to provide efficient instructions to workers and ensure smooth work progress.

[0372] Finally, the server also includes a means for generating new business know-how and improving work efficiency. This means enables the server to generate new business know-how and improve work efficiency.

[0373] Specifically, the server processes and calculates data using software such as Python, Pandas, Scikit-learn, and Joblib. For example, if a specific machine in a factory breaks down, the AI ​​analyzes the failure data and suggests the optimal repair method based on past data. It can also learn patterns that allow workers to communicate efficiently and issue work instructions.

[0374] An example of a prompt sentence might be:

[0375] "Please suggest the best way to repair machine A when it breaks down in the factory. Based on past data, please tell me the most efficient repair procedure."

[0376] In this way, the server can efficiently collect and analyze work data within the factory, enabling quick responses when problems arise and the accumulation and generation of business know-how.

[0377] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0378] Step 1:

[0379] The server collects users' text conversations through internal communication tools. The input is the user's text conversation, and the output is a summarized text. Specifically, it uses an AI summary function to summarize long texts into shorter ones.

[0380] Step 2:

[0381] The server accumulates the summarized text as business know-how data. The input is the summarized text, and the output is the accumulated business know-how data. Specifically, the text is stored in a database.

[0382] Step 3:

[0383] The server uses AI to learn from the accumulated data. The input is the accumulated business know-how data, and the output is a trained model. Specifically, it analyzes the data and trains the model using Python and Scikit-learn.

[0384] Step 4:

[0385] The server collects work data from within the factory in real time. The input is data from various sensors within the factory, and the output is the collected work data. Specifically, data is collected using IoT devices and sent to the server.

[0386] Step 5:

[0387] The server analyzes the collected work data using AI. The input is the collected work data, and the output is the analysis results. Specifically, the data is preprocessed using Python and Pandas, and then analyzed using Scikit-learn.

[0388] Step 6:

[0389] The server learns response patterns when specific problems occur and proposes the optimal response method. The input is the analysis results, and the output is the optimal response method. Specifically, it extracts response patterns based on past data and generates proposals.

[0390] Step 7:

[0391] The server learns communication patterns for efficient work progress and issues appropriate instructions to workers. The input is the trained model and real-time data, and the output is work instructions. Specifically, the AI ​​generates optimal communication patterns and sends instructions to workers.

[0392] Step 8:

[0393] The server generates new business know-how and improves work efficiency. The input is a trained model and real-time data, and the output is new business know-how. Specifically, the AI ​​generates new know-how and stores it in a database.

[0394] In this way, the server can efficiently collect and analyze work data within the factory, enabling quick responses when problems arise and the accumulation and generation of business know-how.

[0395] Furthermore, an emotion engine that estimates the user's emotion may be 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.

[0396] "Example 1"

[0397] One embodiment of the present invention provides a system including an emotion engine in which an AI recognizes a user's emotions. In this system, when a user has a text conversation using an internal communication tool, the AI ​​summarizes the conversation content in real time. Furthermore, the emotion engine reads emotions from the user's text and adjusts the accuracy of the summary based on the emotions. For example, if the user expresses anger, the emotion engine feeds that information back to the AI, which then reflects that information in generating the summary. This results in a more appropriate summary based on the user's emotions.

[0398] "Example 2"

[0399] Another embodiment of the present invention provides a system in which an emotion engine adjusts the learning of business know-how data based on the user's emotions. In this system, conversations between users are saved as text data, and this data is accumulated as business know-how data. The emotion engine reads the user's emotions and adjusts the AI's learning based on those emotions. For example, if the user expresses joy, the emotion engine feeds that information back to the AI, and the AI ​​reflects that information in the learning of the business know-how data. This generates more appropriate business know-how that corresponds to the user's emotions.

[0400] "Example 3"

[0401] Furthermore, as a further embodiment of the present invention, a system is provided in which an emotion engine presents business know-how to a user that is generated based on the user's emotions. In this system, an AI analyzes accumulated data and extracts patterns of business know-how. The emotion engine reads the user's emotions and presents the user with business know-how that is generated based on those emotions. For example, if the user expresses anxiety, the emotion engine feeds that information back to the AI, and the AI ​​adjusts the presentation of business know-how to the user based on that information. This allows the system to present more appropriate business know-how that is in line with the user's emotions.

[0402] The processing flow of each embodiment will be described below.

[0403] "Example 1"

[0404] Step 1: Users engage in text conversations using internal communication tools.

[0405] Step 2: The AI ​​summarizes the conversation in real time.

[0406] Step 3: The emotion engine reads the emotion from the user's text.

[0407] Step 4: The emotion engine feeds the emotion information back to the AI.

[0408] Step 5: The AI ​​uses that information to adjust the accuracy of the summary.

[0409] "Example 2"

[0410] Step 1: The content of conversations between users is saved as text data, and that data is accumulated as business know-how data.

[0411] Step 2: The emotion engine reads the user's emotions.

[0412] Step 3: The emotion engine feeds the emotion information back to the AI.

[0413] Step 4: The AI ​​reflects this information and adjusts its learning of the business know-how data.

[0414] "Example 3"

[0415] Step 1: AI analyzes the accumulated data and extracts patterns of business know-how.

[0416] Step 2: The emotion engine reads the user's emotions.

[0417] Step 3: The emotion engine feeds the emotion information back to the AI.

[0418] Step 4: The AI ​​uses this information to adjust the presentation of business know-how to the user.

[0419] Example 1

[0420] 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 device 14 will be referred to as a "terminal."

[0421] In-house communication tools are required to efficiently summarize long text messages so that users can quickly obtain information. Another challenge is to improve the quality of communication by providing summaries that take the user's emotions into account. Furthermore, it is also important to accumulate the content of these exchanges as business know-how and use it to improve business operations.

[0422] 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.

[0423] In this invention, the server includes: means for shortening text conversation time using an AI summarization function in an internal communication tool; means for accumulating the content of the exchange as business know-how data; means for learning the accumulated data using AI; means for adjusting the accuracy of the summary using an emotion engine that recognizes the user's emotions; and means for displaying the summary results on the user's terminal. This allows users to save time reading long texts and obtain information efficiently. Furthermore, since appropriate summaries are provided based on the user's emotions, the quality of communication improves. Furthermore, the accumulated data can be used to improve business operations and generate new business know-how.

[0424] An "internal communication tool" is software or a platform that facilitates information sharing and communication within a company or organization.

[0425] "Artificial intelligence summary function" is a technology that analyzes long text data, extracts important information, and generates a short summary.

[0426] A "text conversation time shortener" is a method for quickly conveying information by summarizing long text messages sent by users.

[0427] "Business know-how data" refers to the accumulated data of knowledge and experience gained in the course of business operations.

[0428] "Means of learning accumulated data using artificial intelligence" refers to a method of analyzing accumulated business know-how data using artificial intelligence to learn patterns and trends.

[0429] An "emotion engine" is a technology for analyzing and identifying a user's emotions from text data.

[0430] "Means for adjusting the accuracy of the summary" refers to a method for appropriately adjusting the content and expression of the summary based on the emotional information obtained from the emotion engine.

[0431] "Means for displaying the summary results on the user's terminal" refers to a method for displaying the generated summary on the device used by the user (such as a personal computer or smartphone).

[0432] "Means for business improvement" refers to methods for improving business processes and methods based on accumulated data and the learning results of artificial intelligence.

[0433] "Means for generating new business know-how" refers to a method for creating new business knowledge and methods by utilizing the learning results of artificial intelligence.

[0434] This invention is a system that combines an AI summarization function and an emotion recognition engine for an internal communication tool. When users have text conversations, the AI ​​summarizes the content in real time, and the emotion recognition engine recognizes the user's emotions and adjusts the accuracy of the summary.

[0435] Hardware and software used

[0436] Hardware: Server, user terminal (PC, smartphone)

[0437] Software: Internal communication tools (e.g., popular messaging platforms), artificial intelligence summarization engines (e.g., popular generative AI models), emotion recognition engines (e.g., popular emotion analysis tools)

[0438] Overview of program processing

[0439] 1. User initiates a text conversation:

[0440] A user types a text message using an internal communication tool and presses the send button.

[0441] 2. The server receives the text data:

[0442] The server receives the text message sent by the user and temporarily stores the data.

[0443] 3. The server sends the text data to the AI ​​summarization engine:

[0444] The server sends the received text data to the AI ​​summarization engine via an API.

[0445] 4. The server sends the text data to the emotion recognition engine:

[0446] The server also sends the same text data to an emotion recognition engine, also using an API.

[0447] 5. AI summarization engine summarizes text:

[0448] The AI ​​summarization engine analyzes the received text data and generates a summary, which is then temporarily saved.

[0449] 6. Emotion recognition engine analyzes emotions:

[0450] The emotion recognition engine analyzes the text data and identifies the user's emotions (e.g., anger, joy, sadness, etc.), and the analysis results are returned to the server.

[0451] 7. The server feeds back the emotion recognition results to the AI ​​summarization engine:

[0452] The server feeds back the emotion analysis results received from the emotion recognition engine to the AI ​​summarization engine, providing information for adjusting the accuracy of summarization.

[0453] 8. AI summarization engine adjusts the accuracy of summaries:

[0454] The AI ​​summarization engine adjusts the accuracy of summaries based on emotion recognition results. For example, if a user expresses anger, the summaries will reflect that information.

[0455] 9. The server sends the final summary to the user's device:

[0456] The server then sends the final adjusted summary to the user's device in real time.

[0457] 10. A summary is displayed on the user's terminal:

[0458] The final summary is displayed on the user's device, allowing the user to obtain information efficiently without having to spend time reading long texts.

[0459] Specific examples

[0460] Example user input: "I'm very frustrated with how slowly this project is progressing. Let's figure out how to move forward more efficiently."

[0461] AI Summarization Engine Output: "The project is lagging behind, so we need to find a more efficient way to do it."

[0462] Emotion recognition engine analysis result: Anger (high)

[0463] Final summary: "The project is progressing slowly and we urgently need to find a more efficient way to do it."

[0464] Prompt Sentence Examples

[0465] Prompt: "Design a system that summarizes text conversations in real time as users engage in them, and adjusts the accuracy of the summary based on the user's sentiment."

[0466] This system allows users to obtain information efficiently, saving them the time of reading long texts. It also provides appropriate summaries based on the user's emotions, improving the quality of communication. Furthermore, the accumulated data can be used to improve business operations and generate new business know-how.

[0467] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0468] Step 1:

[0469] A user initiates a text conversation.

[0470] A user types a text message using an internal communication tool and presses the send button.

[0471] Input: The text message entered by the user.

[0472] Output: A text message is sent to the server.

[0473] Step 2:

[0474] The server receives the text data.

[0475] The server receives the text message sent by the user and temporarily stores the data.

[0476] Input: The text message sent by the user.

[0477] Output: Text data is saved on the server.

[0478] Step 3:

[0479] The server sends the text data to the AI ​​summarization engine.

[0480] The server sends the received text data to the AI ​​summarization engine via an API.

[0481] Input: Text data stored on the server.

[0482] Output: The text data is sent to an AI summarization engine.

[0483] Step 4:

[0484] The server sends the text data to the emotion recognition engine.

[0485] The server also sends the same text data to an emotion recognition engine, also using an API.

[0486] Input: Text data stored on the server.

[0487] Output: The text data is sent to the emotion recognition engine.

[0488] Step 5:

[0489] An AI summarization engine summarizes the text.

[0490] The AI ​​summarization engine analyzes the received text data and generates a summary, which is then temporarily saved.

[0491] Input: Text data sent to the AI ​​summarization engine.

[0492] Output: Summarized text data.

[0493] Step 6:

[0494] The emotion recognition engine analyzes emotions.

[0495] The emotion recognition engine analyzes the text data and identifies the user's emotions (e.g., anger, joy, sadness, etc.), and the analysis results are returned to the server.

[0496] Input: Text data sent to the emotion recognition engine.

[0497] Output: Sentiment analysis results.

[0498] Step 7:

[0499] The server feeds back the emotion recognition results to the AI ​​summarization engine.

[0500] The server feeds back the emotion analysis results received from the emotion recognition engine to the AI ​​summarization engine, providing information for adjusting the accuracy of summarization.

[0501] Input: Sentiment analysis results.

[0502] Output: Sentiment analysis results are sent to an AI summarization engine.

[0503] Step 8:

[0504] The AI ​​summarization engine adjusts the accuracy of the summary.

[0505] The AI ​​summarization engine adjusts the accuracy of summaries based on emotion recognition results. For example, if a user expresses anger, the summaries will reflect that information.

[0506] Input: Sentiment analysis results.

[0507] Output: Adjusted summary text.

[0508] Step 9:

[0509] The server sends the final summary result to the user's terminal.

[0510] The server then sends the final adjusted summary to the user's device in real time.

[0511] Input: The adjusted summary text.

[0512] Output: The summary text is sent to the user's terminal.

[0513] Step 10:

[0514] A summary is displayed on the user's terminal.

[0515] The final summary is displayed on the user's device, allowing the user to obtain information efficiently without having to spend time reading long texts.

[0516] Input: Summary text.

[0517] Output: Summary text displayed on the user's terminal.

[0518] (Application example 1)

[0519] Next, a description will be given of Application Example 1 of Embodiment 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."

[0520] Conventional internal communication tools often involve long text exchanges, making it difficult for users to efficiently obtain information. Furthermore, summaries are often generated without taking the user's emotions into consideration, which can result in inappropriate summaries being provided. Furthermore, in physical stores, staff are required to communicate with customers quickly and accurately, but there has been a lack of technology to support this. To solve these issues, a system is needed that performs summaries and sentiment analysis in real time, providing appropriate summaries based on the user's emotions.

[0521] 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.

[0522] In this invention, the server includes: means for shortening text conversation time using an AI summarization function in an internal communication tool; means for accumulating the content of those exchanges as business know-how data; means for AI learning from the accumulated data; means for recognizing user emotions using an emotion engine and adjusting the accuracy of summaries based on those emotions; and means installed on a smart device for real-time summarization and emotion analysis. This allows users to save time reading long texts and obtain information efficiently. Furthermore, because appropriate summaries are provided based on the user's emotions, store staff can quickly grasp customer needs and emotions, enabling more appropriate customer service.

[0523] An "internal communication tool" is software that allows for efficient information sharing and communication within a company.

[0524] The "AI summary function" is a function that uses artificial intelligence to summarize long texts in a shorter form.

[0525] "Text conversation time reduction measures" are methods that allow users to reduce the time it takes to read long texts and obtain information efficiently.

[0526] "Business know-how data" refers to the accumulation of business-related knowledge and experience as data.

[0527] "Means of using AI to learn from accumulated data" refers to a method by which artificial intelligence learns from accumulated business know-how data.

[0528] An "emotion engine" is a system that reads emotions from a user's text and processes them based on those emotions.

[0529] "Means for recognizing user emotions" refers to a method for reading emotions from a user's text.

[0530] The "means for adjusting the accuracy of the summary" is a method for appropriately adjusting the content of the summary based on the recognized emotions.

[0531] A "smart device" is an electronic device that has Internet connectivity and can run a variety of applications.

[0532] "Means for real-time summarization and sentiment analysis" refers to a method for performing instant summarization and sentiment analysis as a user enters text.

[0533] The system for implementing this invention combines an AI summarization function, an emotion engine, and a smart device in an internal communication tool. Specifically, the server includes the following means:

[0534] First, the server uses the AI ​​summarization function of the internal communication tool to summarize the text entered by the user in real time. This summarization function is realized using OpenAI's API. When the user enters a long text, the server sends the text to OpenAI's API and receives the summarized text.

[0535] Next, the server uses an emotion engine to recognize emotions from the user's input text. The emotion engine is implemented using the emotion analysis model from the Transformers library. The server inputs the user's text into the emotion analysis model and obtains the emotion type and its score.

[0536] Furthermore, the server adjusts the accuracy of the summary based on the recognized emotion: for example, if the user expresses anger, the server will feed that information back into the summary generation process to generate a more appropriate summary.

[0537] A smart device (e.g., smart glasses) acts as an interface for executing these functions in real time. When a user inputs text through the smart device, the text is sent to the server, where it is summarized and sentiment analyzed, and the results are displayed on the smart device.

[0538] As a concrete example, consider the case where a customer says to a physical store, "This product was not what I expected. I would like to return it." In this case, the server performs the following process:

[0539] 1. The server receives the customer's text and generates a summary using OpenAI's API.

[0540] 2. The server uses an emotion engine to recognize the emotion of "anger" or "dissatisfaction" from the customer's text.

[0541] 3. The server adjusts the accuracy of the summary based on the recognized sentiment and generates a summary such as, "The customer is dissatisfied with the product and wishes to return it."

[0542] 4. This summary and the results of the sentiment analysis are displayed on the smart device, allowing staff to quickly understand the customer's needs and emotions.

[0543] An example of a prompt is as follows:

[0544] "Summarize the text below: This product was disappointing and I would like to return it."

[0545] In this way, users can obtain information efficiently without having to spend time reading long texts. In addition, by providing an appropriate summary based on the user's emotions, store staff can quickly understand the needs and emotions of customers and provide more appropriate customer service.

[0546] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0547] Step 1:

[0548] A user inputs text via a smart device.

[0549] Input: Text entered by the user (e.g., "This product was disappointing. I would like to return it.")

[0550] Output: The entered text is sent to the server.

[0551] Step 2:

[0552] The server sends the received text to OpenAI's API and generates a summary.

[0553] Input: Text entered by the user

[0554] Data processing: Send the text to OpenAI's API and create a prompt to generate a summary.

[0555] Output: Abridged text (e.g. "The customer is unhappy with the product and would like to return it.")

[0556] Step 3:

[0557] The server sends the summarized text to the emotion engine for sentiment analysis.

[0558] Input: Summarized text

[0559] Data Computing: Recognize emotions from text using the sentiment analysis model from the Transformers library.

[0560] Output: Emotion type and its score (e.g., "Anger" or "Frustrated", score: 0.85)

[0561] Step 4:

[0562] The server adjusts the accuracy of the summary based on the recognized emotions.

[0563] Input: Sentiment type and its score, summarized text

[0564] Data processing: The content of the summary is adjusted appropriately taking into account the type and score of the emotion.

[0565] Output: Tailored summary text (e.g. "The customer is unhappy with the product and would like to return it.")

[0566] Step 5:

[0567] The server sends the adjusted summary text and the results of sentiment analysis to the smart device.

[0568] Input: Adjusted summary text, sentiment analysis results

[0569] Output: Summary text and sentiment analysis results displayed on smart devices

[0570] Step 6:

[0571] Users can view the summary text and sentiment analysis results via their smart devices.

[0572] Input: Summary text displayed on a smart device and sentiment analysis results

[0573] Output: The information is provided so that users can quickly grasp it and take appropriate action.

[0574] The above processing steps allow users to obtain information efficiently, saving them the time of reading long text. In addition, by providing an appropriate summary based on the user's emotions, staff in brick-and-mortar stores can quickly grasp the needs and emotions of customers and provide more appropriate customer service.

[0575] Example 2

[0576] Next, a description will be given of 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."

[0577] Conventional internal communication tools have made it difficult to efficiently manage conversation content and accumulate it as business know-how. Furthermore, they were unable to generate business know-how that took user emotions into account, limiting the efficiency and improvement of business processes. Furthermore, simply saving conversation content as text data makes it difficult to generate appropriate business know-how that reflects emotional nuances.

[0578] 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.

[0579] In this invention, the server includes means for shortening text conversation time using an AI summarization function in an internal communication tool, means for accumulating the content of the exchange as business know-how data, means for learning the accumulated data using AI, means for converting the content of the user's conversation from voice to text data in real time, means for saving the converted text data in a database, means for sending the saved text data to an emotion analysis engine and analyzing the user's emotions, and means for adjusting the learning data of the generation AI model based on the analyzed emotion information. This makes it possible to generate more appropriate business know-how according to the user's emotions, thereby realizing efficiency and improvement of business operations.

[0580] "Internal communication tools" are software and platforms that facilitate information sharing and communication within a company or organization.

[0581] "Artificial intelligence summary function" is a technology that shortens long pieces of text or conversation content and extracts only the important information.

[0582] "Business know-how data" refers to the accumulated knowledge and experience necessary for carrying out business.

[0583] The "means for converting voice to text data" is a technology that uses voice recognition technology to convert voice information into text information.

[0584] "Means of storing data in a database" refers to the technology used to store data in a database system so that it can be efficiently managed and searched.

[0585] An "emotion analysis engine" is a technology that analyzes user emotions from text data and outputs those emotions as numerical values ​​or categories.

[0586] A "generative AI model" is an artificial intelligence model that generates new information and knowledge based on given data.

[0587] "Means for adjusting learning data" refers to a technology that optimizes the data that the generative AI model learns based on analyzed emotional information.

[0588] This invention is a system that shortens the time spent on text conversations by using an AI summary function in an internal communication tool, accumulates the content of those exchanges as business know-how data, and then uses AI to learn from the accumulated data. Specific embodiments of this system are described below.

[0589] Hardware and software used

[0590] Hardware: Servers, devices (PCs, smartphones, etc.)

[0591] Software: database management systems (e.g., MySQL), sentiment analysis engines (e.g., IBM Watson®), generative AI models (e.g., GPT-4), speech recognition software (e.g., Google Speech-to-Text)

[0592] Specific operation of the system

[0593] 1. Collecting conversation content

[0594] Users use terminals to have conversations.

[0595] The device uses voice recognition software to convert the conversation from voice to text data in real time. For example, if User A says, "The project is progressing smoothly," the device converts this voice into text data: "The project is progressing smoothly."

[0596] The terminal transmits the converted text data to the server.

[0597] 2. Data storage

[0598] The server receives the text data sent from the terminal.

[0599] The server stores the received text data in a database management system. For example, the text data "The project is progressing smoothly" is stored in the database.

[0600] 3. Emotion analysis

[0601] The server sends the stored text data to a sentiment analysis engine.

[0602] A sentiment analysis engine reads user emotions from text data. For example, it analyzes positive emotions from the text "The project is progressing smoothly."

[0603] The emotion analysis engine returns the analysis result to the server. For example, the analysis result "positive emotion" is returned to the server.

[0604] 4. Adjusting AI learning

[0605] The server adjusts the learning data for the generative AI model based on the analysis results received from the emotion analysis engine.

[0606] The server preferentially feeds back text data containing positive emotions to the generative AI model. For example, text data containing positive emotions such as "The project is progressing smoothly" is fed back to the generative AI model.

[0607] The generative AI model learns from the business know-how data based on the feedback information, thereby generating more appropriate business know-how in response to the user's emotions.

[0608] Specific examples

[0609] Collection and storage of conversations

[0610] User A and User B are having a conversation about the progress of a project.

[0611] The device converts the conversation "The project is progressing smoothly" into text data and sends it to the server.

[0612] The server stores this text data in a database.

[0613] Sentiment analysis and AI learning adjustments

[0614] The sentiment analysis engine detects positive sentiment from the text "Everything is going well."

[0615] The server feeds this positive emotional information back into the generative AI model.

[0616] Based on this information, the generative AI model prioritizes learning business know-how data that contains positive emotions.

[0617] Prompt Sentence Examples

[0618] "Please explain in detail the processing steps of a system that stores conversations between users as text data and adjusts learning from that data using a sentiment analysis engine."

[0619] "If the user expresses happiness, please explain, with specific examples, how to feed that information back to the AI ​​and reflect it in the learning of business know-how data."

[0620] This system generates more appropriate business know-how based on the user's emotions, leading to improved and more efficient business operations.

[0621] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0622] Step 1:

[0623] Collection of conversation content

[0624] Users use terminals to have conversations.

[0625] The device uses voice recognition software to convert conversations from voice to text data in real time.

[0626] Input: User's voice data

[0627] Data processing: Speech recognition software converts the voice data into text data.

[0628] Output: Text data

[0629] Specific operation: For example, when user A says, "The project is progressing smoothly," the device converts this speech into text data, "The project is progressing smoothly."

[0630] Step 2:

[0631] Data transmission and storage

[0632] The terminal transmits the converted text data to the server.

[0633] The server receives the text data sent from the terminal.

[0634] The server stores the received text data in a database management system.

[0635] Input: Text data

[0636] Data processing: Save the text data in a database.

[0637] Output: Text data stored in a database

[0638] Specific operation: For example, text data such as "The project is progressing smoothly" is stored in the database.

[0639] Step 3:

[0640] Emotion analysis

[0641] The server sends the stored text data to a sentiment analysis engine.

[0642] The sentiment analysis engine reads user emotions from text data.

[0643] The sentiment analysis engine returns the analysis results to the server.

[0644] Input: Text data stored in a database

[0645] Data processing: The sentiment analysis engine analyzes the text data and generates sentiment information.

[0646] Output: Emotional information

[0647] Specific operation: For example, positive emotions are analyzed from the text "The project is progressing smoothly," and the analysis result "positive emotions" is returned to the server.

[0648] Step 4:

[0649] AI learning adjustments

[0650] The server adjusts the learning data for the generative AI model based on the analysis results received from the emotion analysis engine.

[0651] The server prioritizes text data containing positive emotions and feeds it back to the generative AI model.

[0652] The generative AI model learns business know-how data based on the feedback information.

[0653] Input: Emotional information and text data

[0654] Data processing: Adjusting the learning data of the generative AI model based on emotional information.

[0655] Output: Refine training data

[0656] Specific operation: For example, text data containing positive emotions such as "The project is progressing smoothly" is fed back to the generative AI model, and the generative AI model uses this information to learn business know-how data.

[0657] In this way, more appropriate business know-how is generated in accordance with the user's feelings, and business efficiency and improvement can be realized.

[0658] (Application example 2)

[0659] 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."

[0660] Conventional internal communication tools can accumulate conversation content as business know-how data, but they do not take user emotions into account when learning data or recommend content based on emotions, which means that they do not sufficiently improve business efficiency or user satisfaction.

[0661] 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.

[0662] In this invention, the server includes means for shortening text conversation time using an AI summarization function in an internal communication tool, means for accumulating the content of the exchange as business know-how data, means for learning the accumulated data using an AI, means for adjusting the learning of the business know-how data using an emotion engine that analyzes user emotions, and means for recommending optimal content based on the user emotions. This makes it possible to learn data taking user emotions into consideration and recommend content based on emotions.

[0663] "Internal communication tools" are software and platforms that enable efficient information sharing and communication within a company or organization.

[0664] The "AI summary function" is a function that uses artificial intelligence to summarize long texts in a short form.

[0665] "Means to shorten text conversation time" refers to methods that efficiently summarize conversation content and allow users to obtain the necessary information in a short amount of time.

[0666] "Business know-how data" refers to the accumulation of business-related knowledge and experience as data.

[0667] "Storage means" refers to the method by which data is stored and made available for later reference.

[0668] "Means of learning with AI" refers to a method of using artificial intelligence to analyze accumulated data and learn new knowledge and patterns.

[0669] An "emotion engine" is software that analyzes the user's emotions and adjusts the system's behavior based on the results.

[0670] The "means for adjusting the learning of business know-how data" is a method for optimizing the data learning process based on the user's emotions using an emotion engine.

[0671] "Content recommendation methods" are methods that suggest optimal content based on a user's emotions and past behavior.

[0672] The following system configuration will be described as an embodiment of the present invention.

[0673] Server provides a means to shorten text conversation times by using an AI summary function in internal communication tools. This means that it uses artificial intelligence (AI) to summarize long texts entered by users, allowing them to obtain the necessary information in a short amount of time. Specifically, it uses natural language processing (NLP) technology to analyze the text and extract important parts.

[0674] Next, the server provides a means to store the content of these exchanges as business know-how data. This means saves the content of conversations between users as text data and stores it in a database. This makes it possible to refer to past conversations, contributing to improved business efficiency.

[0675] Furthermore, the server provides a means for AI-based learning of the accumulated data. This means analyzing the accumulated business know-how data using artificial intelligence and learning new knowledge and patterns. This allows the quality of business know-how to be improved.

[0676] The server also provides a means for adjusting the learning of business know-how data using an emotion engine that analyzes user emotions. This means analyzes user emotions and optimizes the data learning process based on the results. Specifically, the emotion engine reads the user's emotions and adjusts the AI ​​learning based on those emotions.

[0677] Furthermore, the server provides a means for recommending optimal content based on the user's emotions. This means proposes optimal content based on the user's emotions and past behavior. Specifically, the emotion engine analyzes the user's emotions and recommends content based on the results.

[0678] The hardware used includes servers, databases, and user devices (smartphones, PCs, etc.). The software used includes natural language processing (NLP) libraries, sentiment analysis engines, database management systems (DBMS), etc. Specific software examples include TextBlob (NLP library) and SQLite (DBMS).

[0679] For example, if a user says, "I had so much fun today!", a past conversation such as "This movie was great" will be recommended based on that emotion. An example of this prompt is as follows:

[0680] User ID: user123

[0681] Conversation: Today was so much fun!

[0682] In this way, it becomes possible to learn data that takes user emotions into account and recommend content based on those emotions.

[0683] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0684] Step 1:

[0685] A user has a conversation using an internal communication tool. The text data entered by the user is sent from the terminal to the server. The input is the content of the user's conversation, and the output is the text data sent to the server.

[0686] Step 2:

[0687] The server analyzes the received text data using an AI summarization function. Specifically, it uses a natural language processing (NLP) library to analyze the text and extract important parts. The input is the text data of the user's conversation, and the output is the summarized text data.

[0688] Step 3:

[0689] The server stores the summarized text data in a database as business know-how data. Specifically, the data is saved using a database management system (DBMS) such as SQLite. The input is the summarized text data, and the output is the business know-how data saved in the database.

[0690] Step 4:

[0691] The server uses AI to learn from the accumulated business know-how data. Specifically, it analyzes the data using machine learning algorithms and learns new knowledge and patterns. The input is the business know-how data stored in the database, and the output is the learning results.

[0692] Step 5:

[0693] The server uses an emotion engine to analyze the user's emotions. Specifically, it uses an emotion analysis library such as TextBlob to analyze the user's emotions. The input is the text data of the user's conversation, and the output is the analyzed emotion data.

[0694] Step 6:

[0695] The server uses an emotion engine to adjust the learning of business know-how data. Specifically, it optimizes the AI ​​learning process based on the user's emotions. The input is the analyzed emotion data and business know-how data, and the output is the adjusted learning process.

[0696] Step 7:

[0697] The server recommends optimal content based on the user's emotions. Specifically, it selects optimal content from past conversations based on emotional data analyzed by the emotion engine. The input is the analyzed emotional data and past conversations, and the output is recommended content.

[0698] Step 8:

[0699] The server sends the recommended content to the user terminal, and the user can receive and view the recommended content on the terminal. The input is the recommended content, and the output is the content displayed on the user terminal.

[0700] Example 3

[0701] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0702] With conventional internal communication tools, conversations tended to take a long time via text, which often hindered efficient work progress. Furthermore, there was a lack of effective ways to utilize accumulated business data, and work know-how was not shared or improved sufficiently. Furthermore, it was difficult to provide appropriate business know-how that reflected the user's feelings, which meant that users' anxiety and stress could not be alleviated.

[0703] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes means for shortening the time of text conversations using an AI summarization function in an internal communication tool, means for accumulating the content of the exchanges as business know-how data, means for learning the accumulated data using AI, means for analyzing user emotions, means for generating business know-how based on the user emotions, and means for presenting the generated business know-how to the user. This enables efficient communication and effective sharing of business know-how, and further enables the provision of appropriate business know-how according to the user's emotions.

[0704] "Internal communication tools" are software and platforms that enable efficient information sharing and communication within a company or organization.

[0705] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and perform functions such as learning, reasoning, recognition, and decision-making.

[0706] The "summary function" is a function that shortens the content of long text or conversations and extracts and presents only the important information.

[0707] "Business know-how data" refers to the accumulation of knowledge and experience related to business progress and problem solving.

[0708] "Accumulated data" refers to records of past business operations and communications stored in a database or similar.

[0709] The "means of learning" is the process by which artificial intelligence analyzes accumulated data, extracts patterns and knowledge, and learns.

[0710] "Means for analyzing emotions" refers to technology that reads emotions from a user's text or voice and identifies those emotions.

[0711] "Means for generating business know-how" refers to the process of creating new business know-how based on data learned by artificial intelligence and user emotions.

[0712] The "means for presenting business know-how" is a method for providing the generated business know-how to the user visually or audibly.

[0713] MODE FOR CARRYING OUT THE INVENTION

[0714] This invention is a system that shortens text conversation time using an AI summarization function in an internal communication tool, accumulates the content of the exchange as business know-how data, and further uses AI to learn from the accumulated data.In addition, it includes functions to analyze user emotions, generate business know-how based on those emotions, and present the generated business know-how to the user.

[0715] Hardware and software used

[0716] The server stores business data using a database (e.g., MySQL or PostgreSQL) and analyzes the data using an artificial intelligence model (e.g., TENSORFLOW (registered trademark) or PyTorch). For sentiment analysis, an emotion engine (e.g., IBM Watson or Microsoft (registered trademark) Azure (registered trademark) sentiment analysis API) is used. The terminal is a device (e.g., a PC or smartphone) that provides a user interface and receives user input.

[0717] Program processing

[0718] The server periodically collects business data from the database and inputs it into the AI ​​model for analysis. Specifically, the server executes the SQL query "SELECT FROM project_logs WHERE date >= CURDATE()" to collect data for the current day. The collected data is input into the AI ​​model, which extracts patterns of business know-how. For example, the AI ​​model learns "how to respond when a project is delayed" and saves the pattern.

[0719] The device uses an emotion engine to analyze the user's emotions in real time. When a user types "I'm anxious about moving forward with a new project" into the device, the device sends the text to the emotion engine and obtains emotion data. The emotion engine analyzes the emotion "anxiety" and returns the result to the device.

[0720] The server feeds the user's emotional data obtained from the emotion engine back to the AI. The AI ​​generates business know-how based on the user's emotions. Specifically, if the user is feeling anxious, the AI ​​extracts business know-how from past data that will give the user a sense of security.

[0721] The device presents the generated business know-how to the user. For example, the device screen might display a message such as, "If you are worried about the progress of a project, take the following steps: 1. Communicate regularly with your team members. 2. Use tools to visualize progress. 3. Take immediate action if a problem occurs."

[0722] Examples of specific examples and prompts

[0723] As a concrete example, consider a case where a user is feeling anxious about progressing with a new project. The emotion engine detects the user's anxiety and feeds that information back to the AI. The AI ​​then uses past data to extract successful project progression methods in similar situations and presents specific steps and communication methods to the user.

[0724] Example prompt sentence:

[0725] "I'm nervous about starting a new project. Can you tell me how to proceed based on past success stories?"

[0726] In this way, the server, the terminal, and the user work together to provide business know-how based on emotions. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0727] Step 1: Data collection

[0728] The server collects business data from the database. Specifically, the server executes the SQL query "SELECT FROM project_logs WHERE date >= CURDATE()" to retrieve the data for the current day. This data includes the progress of the project, how to respond when problems occur, communication logs, etc. The input is the query result from the database, and the output is the collected business data.

[0729] Step 2: Data analysis

[0730] The server inputs the collected business data into an artificial intelligence model and performs data analysis. Specifically, the server uses TensorFlow and PyTorch to extract patterns of business know-how. For example, the AI ​​model learns "how to respond when a project is delayed" and saves it as a pattern. The input is the collected business data, and the output is the extracted business know-how pattern.

[0731] Step 3: Sentiment Analysis

[0732] The device uses an emotion engine to analyze the user's emotions in real time. When the user types "I'm anxious about moving forward with a new project" into the device, the device sends the text to the emotion engine and obtains emotion data. The emotion engine analyzes the emotion "anxiety" and returns the result to the device. The input is the user's text input, and the output is the analyzed emotion data.

[0733] Step 4: Generate business know-how

[0734] The server feeds the user's emotional data obtained from the emotion engine back to the AI. The AI ​​generates business know-how based on the user's emotions. Specifically, if the user feels anxious, the AI ​​extracts business know-how from past data that will give the user a sense of security. The input is emotional data and past business know-how data, and the output is the generated business know-how.

[0735] Step 5: Presentation of business know-how

[0736] The terminal presents the generated business know-how to the user. Specifically, the terminal screen displays the following message: "If you are worried about the progress of a project, take the following steps: 1. Communicate regularly with your team members. 2. Use tools to visualize progress. 3. Take immediate action if a problem occurs." The input is the generated business know-how, and the output is what is presented to the user.

[0737] In this way, the server, terminal, and user work together to provide emotion-based business know-how.

[0738] (Application example 3)

[0739] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0740] Conventional work support systems present work know-how without considering the emotions of workers, which means they are unable to reduce worker stress and anxiety. Furthermore, data analysis to generate efficient work know-how is insufficient, limiting the effectiveness of work improvement. This can lead to a decline in worker productivity and work efficiency.

[0741] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0742] In this invention, the server includes means for shortening text conversation time using an AI summarization function in an internal communication tool, means for accumulating the content of the exchange as business know-how data, means for learning the accumulated data using AI, means for reading the user's emotions using an emotion recognition engine, and means for presenting business know-how generated based on the user's emotions. This allows for the provision of appropriate business know-how in accordance with the emotions of workers, enabling efficient business improvement while reducing stress and anxiety.

[0743] "Internal communication tools" are software and platforms that facilitate information sharing and communication within a company.

[0744] The "AI summary function" is a function that uses artificial intelligence to summarize long pieces of text into shorter sentences.

[0745] "Text conversation time-saving methods" are methods and techniques for streamlining and saving time in text-based communication.

[0746] "Business know-how data" refers to the accumulation of knowledge and experience related to business progress and problem solving.

[0747] "Means of learning from accumulated data using AI" refers to a method of analyzing accumulated data using artificial intelligence to extract patterns and knowledge.

[0748] An "emotion recognition engine" is technology or software that can read emotions from a user's facial expressions, tone of voice, etc.

[0749] The "means for presenting business know-how generated based on the user's emotions" refers to a method or technology for providing optimal business know-how according to the user's emotional state.

[0750] As an embodiment of the present invention, an emotion-responsive business support system is constructed. A specific embodiment of the system is shown below.

[0751] System Configuration

[0752] The system consists of the following main components:

[0753] 1. Internal communication tools: Software that facilitates information sharing and communication within a company.

[0754] 2. AI summarization: An artificial intelligence function that summarizes long texts in a concise manner.

[0755] 3. Business know-how database: A database that accumulates knowledge and experience related to business progress and problem solving.

[0756] 4. Emotion recognition engine: Technology that reads emotions from the user's facial expressions, tone of voice, etc.

[0757] 5. Business know-how presentation engine: An engine that provides optimal business know-how according to the user's emotional state.

[0758] Program processing explanation

[0759] Hardware used

[0760] Factory robots: Physical robots used to perform tasks.

[0761] Emotion-aware camera: A camera that captures the user's facial expressions and voice in real time.

[0762] Software used

[0763] Python: A programming language used to implement the program.

[0764] scikit-learn: A library used for data analysis (KMeans clustering).

[0765] EmotionRecognizer library: A library used for emotion recognition.

[0766] AIKnowledgeBase Library: A library used to manage business know-how.

[0767] Data processing and calculation

[0768] 1. Data accumulation: Text data collected through internal communication tools is accumulated in a business know-how database.

[0769] 2. Data analysis: Analyze the accumulated data using scikit-learn's KMeans clustering to extract efficient work patterns.

[0770] 3. Emotion Recognition: Using the EmotionRecognizer library, we analyze the data obtained from the emotion recognition camera and recognize the user's emotions in real time.

[0771] 4. Presentation of business know-how: Based on the recognized emotions, appropriate business know-how is retrieved from the AIKnowledgeBase and presented to the user.

[0772] Specific examples

[0773] For example, if a worker in a factory feels anxious, the emotion recognition camera will recognize that emotion. The emotion recognition engine will then feed that information back to the AI, which will then suggest a relaxing work method from the AI ​​Knowledge Base. This will reduce worker stress and enable more efficient work.

[0774] Prompt Sentence Examples

[0775] Design a system where an emotion-recognition camera reads the emotions of workers in real time, and AI suggests optimal work know-how based on those emotions. For example, if a worker is feeling anxious, it suggests a relaxing work method, and if a worker is feeling stressed, it suggests an efficient procedure.

[0776] The above is an embodiment of the present invention.

[0777] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0778] Step 1:

[0779] The server receives text data collected through internal communication tools and stores it in a business know-how database. The input is text data, and the output is the accumulated business know-how data. Specifically, the server analyzes the text data, extracts important information, and stores it in the database.

[0780] Step 2:

[0781] The server analyzes the accumulated data using scikit-learn's KMeans clustering to extract efficient work patterns. The input is the accumulated business know-how data, and the output is the extracted work patterns. Specifically, the server inputs the data into the clustering algorithm and calculates the center point of each cluster.

[0782] Step 3:

[0783] The emotion recognition camera captures the user's facial expressions and voice in real time and analyzes the data using the EmotionRecognizer library. The input is the user's facial and voice data, and the output is the recognized emotion. Specifically, the camera captures the user's face and voice and sends the data to the emotion recognition engine.

[0784] Step 4:

[0785] The server retrieves appropriate business know-how from the AIKnowledgeBase based on the recognized emotions and presents it to the user. The input is the recognized emotions and extracted work patterns, and the output is the business know-how presented to the user. Specifically, the server searches for the most appropriate business know-how based on the emotion data and displays it to the user.

[0786] Step 5:

[0787] The user performs a task based on the presented business know-how and sends the results as feedback to the server. The input is the user's work result, and the output is feedback data. In concrete terms, the user completes the task and inputs the result to the system.

[0788] Step 6:

[0789] The server stores the feedback data from the user in the business know-how database again and uses it for the next data analysis. The input is the feedback data and the output is the updated business know-how data. Specifically, the server saves the feedback data in the database and prepares it for the next analysis.

[0790] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0791] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0792] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0793] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0794] [Second embodiment]

[0795] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0796] 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.

[0797] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0798] 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.

[0799] 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 audio in accordance with instructions from the processor 46.

[0800] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0801] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0802] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0803] 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.

[0804] 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.

[0805] In the smart glasses 214, the processor 46 performs the reception output process. 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.

[0806] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0807] "Example 1"

[0808] As one embodiment of the present invention, an AI summarization function is incorporated into an internal communication tool. Specifically, when users are engaged in text conversations, the AI ​​summarizes the content in real time and displays it to the user. This allows users to save time reading long texts and obtain information efficiently.

[0809] "Example 2"

[0810] Furthermore, the content of conversations between users is stored as business know-how data. Specifically, the content of conversations is saved as text data and stored in a database. This makes it possible to refer to the content of past conversations, contributing to improved business efficiency.

[0811] "Example 3"

[0812] Furthermore, the accumulated data is learned by AI. Specifically, the AI ​​analyzes the accumulated data and extracts patterns of business know-how. For example, it learns response patterns when specific problems arise, and communication patterns for efficient business progress. This allows the AI ​​to generate new business know-how that can be used to improve business operations.

[0813] The processing flow of each embodiment will be described below.

[0814] "Example 1"

[0815] Step 1: A user opens an internal communication tool and starts a text conversation.

[0816] Step 2: The AI ​​summarizes the conversation in real time and displays it to the user. Specifically, the AI ​​analyzes the text data, extracts key information, and generates a summary.

[0817] Step 3: The user reviews the summary generated by the AI ​​and efficiently obtains the necessary information.

[0818] "Example 2"

[0819] Step 1: The conversation between users is saved as text data.

[0820] Step 2: The saved text data is stored in a database.

[0821] Step 3: The user can refer to the database for past conversations as needed.

[0822] "Example 3"

[0823] Step 1: The AI ​​analyzes the accumulated data. Specifically, the AI ​​analyzes the text data in the database and extracts patterns of business know-how.

[0824] Step 2: Generate new business know-how based on the patterns extracted by AI.

[0825] Step 3: The generated business know-how is used to improve business operations. For example, by referencing response patterns when a specific problem occurs, the company can quickly respond if a similar problem occurs.

[0826] Example 1

[0827] 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."

[0828] Conventional internal communication tools have the problem that it takes time to read long text messages, making it difficult to share information efficiently. There was also a need for a system that could accumulate the content of exchanges as business know-how and further utilize that data to improve business operations and generate new know-how.

[0829] 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.

[0830] In this invention, the server includes: means for transmitting text entered by a user from a terminal to the server; means for the server to analyze the received text using a natural language processing library; means for the server to send a prompt sentence to a generative AI model based on the analysis results; means for the generative AI model to generate a summary; means for the server to send the generated summary to the terminal; means for the terminal to display the summary to the user; means for accumulating the content of the exchange as business know-how data; and means for AI to learn from the accumulated data. This allows users to efficiently obtain information without having to read long texts. Furthermore, the accumulated data can be used to improve business operations and generate new business know-how.

[0831] An "internal communication tool" is software that allows for efficient information sharing and communication within a company or organization.

[0832] The "AI summary function" is a function that uses artificial intelligence to summarize long texts in a shorter form.

[0833] The "means for shortening text conversation time" is a means for summarizing long texts entered by a user, allowing the user to grasp the content in a short time.

[0834] The "means for transmitting text entered by a user from a terminal to a server" refers to a means for transmitting text data entered by a user into a terminal to a server via a network.

[0835] The "means for analyzing text received by the server using a natural language processing library" refers to a means for analyzing text data received by the server using a software library for natural language processing.

[0836] "Means for the server to send a prompt sentence to the generative AI model based on the analysis results" refers to means for the server to send a prompt sentence to the generative AI model to request a summary based on the text data analyzed.

[0837] The "means by which the generative AI model generates a summary" is the means by which the generative AI model generates a summary of the text based on the prompt sentence.

[0838] "Means for the server to send the generated summary to the terminal" refers to means for the server to send the summary received from the generative AI model to the user's terminal.

[0839] The "means for the terminal to display the summary to the user" refers to the means for the user's terminal to display the received summary on the screen.

[0840] "Business know-how data" refers to the accumulation of business-related knowledge and experience as data.

[0841] "Means of learning accumulated data using AI" refers to means of having artificial intelligence learn accumulated business know-how data.

[0842] "Means for business improvement" refers to the analysis of accumulated data to improve business efficiency and quality.

[0843] "Means for generating new business know-how" refers to means for creating new business knowledge and methods based on the learning results of AI.

[0844] This invention is a system that incorporates an AI summarization function into an internal communication tool. When users have a text conversation, the AI ​​summarizes the content in real time and displays it to the user, saving them the time of reading long texts and allowing them to obtain information efficiently.

[0845] Hardware and software used

[0846] Hardware:

[0847] server

[0848] Devices (PCs, smartphones, tablets, etc.)

[0849] software:

[0850] Natural language processing libraries (e.g. spaCy)

[0851] Generative AI models (e.g., GPT-4)

[0852] Internal communication tools

[0853] Data processing and calculation

[0854] The user enters text

[0855] A user types text into a chat window in an internal communication tool, for example, "I'd like to discuss the agenda for our next meeting."

[0856] The device sends the text to the server

[0857] The terminal sends the text entered by the user to the server. At this time, the text data is sent as an HTTP request.

[0858] The server receives and parses the text

[0859] The server receives the text sent from the device. The received text is analyzed using a natural language processing library (e.g., spaCy). As a result of the analysis, the context of the text and important keywords are extracted.

[0860] The server sends a prompt to the generative AI model

[0861] The server generates a prompt to send to a generative AI model (e.g., GPT-4) based on the analysis results. For example, it generates a prompt such as, "Please summarize the following text: I would like to discuss the agenda for the next meeting."

[0862] A generative AI model generates a summary

[0863] The generative AI model receives the prompt sent from the server and generates a summary, for example, "I would like to discuss the meeting agenda."

[0864] The server receives the summary and sends it to the device.

[0865] The server receives the summary returned by the generative AI model, which is then sent back to the device as an HTTP response.

[0866] The terminal displays the summary to the user

[0867] The terminal displays the summary received from the server in the user's chat window, thereby saving the user the trouble of reading long texts and enabling them to obtain information efficiently.

[0868] Examples of specific examples and prompts

[0869] For example, if a user types "I'd like to discuss the agenda for our next meeting," the following happens:

[0870] 1. The user enters the text "I'd like to discuss the agenda for our next meeting."

[0871] 2. The device sends this text to the server.

[0872] 3. The server receives the text and uses spaCy to extract keywords such as "meeting," "agenda," and "discussion."

[0873] 4. The server generates a prompt sentence: "Please summarize the following text: I would like to discuss the agenda for the next meeting" and sends it to the generative AI model.

[0874] 5. The generative AI model generates a summary such as "I would like to discuss the meeting agenda."

[0875] 6. The server receives this summary and sends it to the terminal.

[0876] 7. The device displays the summary in the user's chat window.

[0877] In this way, users can obtain information efficiently without having to read long texts. Furthermore, the content of the interactions is accumulated as business know-how data, which can be used to improve business operations and generate new business know-how through AI learning.

[0878] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0879] Step 1:

[0880] The user enters text.

[0881] A user inputs text into a chat window of an internal communication tool. For example, the user inputs "I would like to discuss the agenda for the next meeting." The input text becomes the input data for the next processing step.

[0882] Step 2:

[0883] The device sends the text to the server.

[0884] The terminal sends the text entered by the user to the server as an HTTP request. The input data is the text entered by the user, and the output data is the text data sent to the server.

[0885] Step 3:

[0886] The server receives and parses the text.

[0887] The server receives the text sent from the device. The received text is analyzed using a natural language processing library (e.g., spaCy). As a result of the analysis, the context of the text and important keywords are extracted. The input data is the received text, and the output data is the analysis result.

[0888] Step 4:

[0889] The server sends a prompt to the generative AI model.

[0890] The server generates a prompt sentence to be sent to the generative AI model based on the analysis results. For example, it generates a prompt sentence such as "Please summarize the following text: I would like to discuss the agenda for the next meeting." The generated prompt sentence becomes the input data for the next processing step.

[0891] Step 5:

[0892] A generative AI model generates the summary.

[0893] The generative AI model receives a prompt sent from the server and generates a summary, for example, "I would like to discuss the meeting agenda." The input data is the prompt, and the output data is the generated summary.

[0894] Step 6:

[0895] The server receives the summary and sends it to the terminal.

[0896] The server receives the summary returned from the generative AI model. The received summary is then sent to the terminal as an HTTP response. The input data is the generated summary, and the output data is the summary sent to the terminal.

[0897] Step 7:

[0898] The terminal displays the summary to the user.

[0899] The terminal displays the summary received from the server in the user's chat window, which allows the user to obtain information efficiently without having to read long text. The input data is the summary received from the server, and the output data is the summary displayed to the user.

[0900] (Application example 1)

[0901] 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."

[0902] Conventional internal communication tools often involve long text exchanges, making it difficult for users to efficiently obtain information. Furthermore, in the operation management of autonomous vehicles, there was a lack of a way to efficiently grasp conversations and instructions during operation. This resulted in issues such as operational managers and passengers being unable to quickly obtain important information, resulting in reduced operational efficiency.

[0903] 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.

[0904] In this invention, the server includes: a means for shortening text conversation time using an AI summarization function in an internal communication tool; a means for accumulating the content of the exchange as business know-how data; a means for learning the accumulated data using AI; and, in an autonomous vehicle operation management system, a means for converting conversation into text using speech recognition; a means for summarizing the text using a generative AI model; and a means for converting the summarized text into speech and playing it back. This allows users to save time reading long texts and obtain information efficiently. It also improves the efficiency of communication within autonomous vehicles, enabling smoother operation management.

[0905] An "internal communication tool" is software that allows for efficient information sharing and communication within a company.

[0906] The "AI summary function" is a function that uses artificial intelligence to summarize long texts in a shorter form.

[0907] "Text conversation time-saving methods" are methods that users use to streamline and save time in text-based communication.

[0908] "Business know-how data" refers to the accumulation of business-related knowledge and experience as data.

[0909] "Storage means" refers to the method by which data is stored and made available for later use.

[0910] "Means of learning with AI" refers to a method of using artificial intelligence to analyze accumulated data and learn patterns and knowledge.

[0911] An "autonomous vehicle" is a vehicle that operates autonomously using artificial intelligence and sensor technology.

[0912] A "traffic management system" is a system for monitoring and controlling vehicle operations.

[0913] "Speech recognition" is a technology that converts speech into text.

[0914] A "generative AI model" is an artificial intelligence model trained to perform tasks such as text generation and summarization.

[0915] A "summarization tool" is a method for summarizing a long text in a short form.

[0916] "Means of converting to audio and playing" refers to a method of converting text to audio and playing it through a speaker or the like.

[0917] An embodiment of this invention will be described. First, a system is constructed that shortens text conversation time using an AI summarization function in an internal communication tool. In this system, when users have a text conversation, the AI ​​summarizes the content in real time and displays it to the user. This allows users to save time reading long texts and obtain information efficiently.

[0918] Next, the system includes a means for accumulating the content of interactions as business know-how data. The accumulated data is then learned by AI and used to improve business operations and generate new business know-how.

[0919] Furthermore, this invention has application in a fleet management system for autonomous vehicles, where the fleet management system converts conversations taking place in the vehicle into text using speech recognition, then uses a generative AI model to summarize the text, which is then converted into audio and played back to the driver or passengers.

[0920] Specifically, the server performs the following processes: First, it uses speech recognition technology to convert the conversation in the vehicle into text. For example, the speech recognition software used for this purpose is Google's speech recognition API. Next, it uses a generative AI model (e.g., OpenAI's GPT-3) to summarize the converted text. For this summarization process, it uses the prompt "Please summarize the following text:" Finally, it uses the gTTS (Google Text-to-Speech) library to convert the summarized text into speech and play it back.

[0921] As a concrete example, if a dispatcher in an autonomous vehicle asks, "Where is the next stop?", speech recognition technology converts the question into text, and a generative AI model summarizes it as, "Confirm next stop." The summarized text is then converted into speech and played back to the driver or passengers.

[0922] An example of a prompt is as follows:

[0923] "Summarize the following text: Where is the next stop?"

[0924] In this way, users can obtain information efficiently without having to read long texts, and communication within autonomous vehicles will be made more efficient, enabling smoother operation management.

[0925] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0926] Step 1:

[0927] The server uses voice recognition technology to convert conversations taking place inside the vehicle into text. Specifically, the voice data acquired from the microphone as voice input is sent to Google's voice recognition API, which then outputs it as text data. This process converts the voice data into text data.

[0928] Step 2:

[0929] The server uses a generative AI model to summarize the converted text. Specifically, it sends the text data obtained in step 1 as input to OpenAI's GPT-3 model along with the prompt "Please summarize the following text:" and obtains the summarized text as output. This process results in a short summary of the long text.

[0930] Step 3:

[0931] The server converts the summarized text into audio and plays it back. Specifically, it uses the summarized text obtained in step 2 as input and generates an audio file using the gTTS (Google Text-to-Speech) library, and plays the audio file through a speaker. This process provides the summarized information to the user as audio.

[0932] Step 4:

[0933] The user listens to the audio and obtains the necessary information. Specifically, the operation manager and passengers listen to the audio coming from the speaker and decide on the next course of action. This process allows the user to obtain information efficiently and take appropriate action.

[0934] Example 2

[0935] Next, a description will be given of 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."

[0936] With conventional internal communication tools, it was difficult to efficiently accumulate conversations between users and utilize them as business know-how. Furthermore, the process of converting voice data into text data and saving it in a database was often done manually, preventing business efficiency. Furthermore, there was a lack of a way to effectively learn from the accumulated data and generate new business know-how.

[0937] 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.

[0938] In this invention, the server includes means for capturing conversations between users as voice data, means for converting the captured voice data into text data, and means for storing the converted text data in a database, thereby enabling the conversations between users to be efficiently accumulated and utilized as business know-how.

[0939] "User" refers to an individual or group that uses the system to engage in conversation.

[0940] "Voice data" refers to data that is recorded in digital format using a voice input device such as a microphone to record the contents of a user's conversation.

[0941] "Capture" refers to the process of acquiring and recording audio data in real time.

[0942] "Text data" refers to data obtained by converting voice data into character information.

[0943] "Conversion" refers to the process of turning audio data into text data.

[0944] A "database" refers to a system for systematically storing and managing text data.

[0945] "Business know-how data" refers to knowledge and information about business obtained from the content of conversations between users.

[0946] A "generative AI model" refers to an artificial intelligence model that learns from accumulated data and generates new knowledge and information.

[0947] "Learning" refers to the process by which a generative AI model analyzes accumulated data and extracts patterns and knowledge.

[0948] "Business improvement" refers to the process of using accumulated data and the learning results of generative AI models to improve business efficiency and quality.

[0949] "New business know-how" refers to new knowledge and information obtained from the learning results of the generative AI model.

[0950] The present invention is a system for efficiently storing conversational content between users and utilizing it as business know-how. A specific embodiment of this system will be described below.

[0951] First, the user starts a business conversation. When the user starts the conversation, the device captures the voice data through the microphone. The device has voice capture software (e.g., Audacity) installed. The captured voice data is sent to the server in real time using the HTTP protocol.

[0952] The server converts the received voice data into text data using the Google Cloud Speech-to-Text API. The converted text data is used as business know-how data. The server then saves the converted text data in a MySQL database. When saving, the date and time of the conversation and participant information are also recorded.

[0953] Users can search and refer to past conversations through a dedicated interface, for example, by accessing the database using a web browser. This allows users to easily refer to past conversations, contributing to improved work efficiency.

[0954] For example, suppose user A and user B start talking about the progress of a project. When user A says, "Let's schedule the next meeting for next Tuesday," the device captures this voice data and sends it to the server. The server converts the voice data into text using the Google Cloud Speech-to-Text API, generating the text data, "Let's schedule the next meeting for next Tuesday." This text data is then stored in a MySQL database.

[0955] Examples of prompts to be input to a generative AI model include:

[0956] "User A and User B were talking about the progress of a project. User A said, 'Let's set up the next meeting for next Tuesday.' How can I save this conversation as text data and store it in a database?"

[0957] This system allows users to easily refer to past conversations, contributing to improved work efficiency. Additionally, by using a generative AI model to learn from the accumulated data, it becomes possible to generate new business know-how.

[0958] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0959] Step 1:

[0960] A user initiates a conversation.

[0961] Input: User's voice

[0962] Output: Audio data

[0963] What happens: User A and User B start talking about the progress of a project. User A says, "Let's schedule the next meeting for next Tuesday."

[0964] Step 2:

[0965] The device captures the audio data.

[0966] Input: User's voice

[0967] Output: Digital audio data

[0968] Specific operation: The device captures user A's speech as audio data through the microphone. Audio capture software (e.g., Audacity) records the audio data in real time.

[0969] Step 3:

[0970] The terminal transmits the voice data to the server.

[0971] Input: Digital audio data

[0972] Output: Audio data sent to the server

[0973] How it works: The device sends the recorded audio data to the server using the HTTP protocol, using the Python requests library.

[0974] Step 4:

[0975] The server converts the voice data into text data.

[0976] Input: Audio data sent to the server

[0977] Output: Text data

[0978] What happens next: The server calls the Google Cloud Speech-to-Text API to convert the voice data into text, which then becomes "Let's schedule our next meeting for next Tuesday."

[0979] Step 5:

[0980] The server stores the text data in a database.

[0981] Input: Text data

[0982] Output: Text data stored in a database

[0983] How it works: The server saves the converted text data in a MySQL database, along with the date and time of the conversation and participant information.

[0984] Step 6:

[0985] Users can view past conversations.

[0986] Input: Text data stored in a database

[0987] Output: Text data as search results

[0988] Specific operation: Users open a web browser and access the database through a dedicated interface. User A can easily search and refer to past conversations such as "Let's schedule the next meeting for next Tuesday."

[0989] (Application example 2)

[0990] 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."

[0991] In logistics centers, inefficient communication between staff can lead to delays and mistakes. Furthermore, because past conversations cannot be referenced, the same questions and confirmations are often repeated, resulting in a decline in work efficiency. To solve these issues, a system that can efficiently store and reference the conversations between staff is needed.

[0992] 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.

[0993] In this invention, the server includes means for shortening text conversation time using an AI summarization function in an internal communication tool, means for accumulating the content of the exchange as business know-how data, means for learning the accumulated data using AI, means for saving the content of the conversation as text data using voice recognition technology, means for storing the saved text data in a cloud database, and means for making the saved text data accessible. This improves the efficiency of communication between staff at the logistics center and makes it easy to refer to the content of past conversations.

[0994] "Internal communication tools" are software and platforms that enable efficient information sharing and communication within a company.

[0995] The "AI summary function" is a function that uses artificial intelligence to summarize long texts and conversations in a concise manner.

[0996] "Methods for shortening text conversation time" refers to a method for reducing the time required for text exchange by summarizing the content of the conversation.

[0997] "Business know-how data" refers to the accumulated data of knowledge and experience gained in the course of carrying out business.

[0998] "Means of using AI to learn from accumulated data" refers to a method of having artificial intelligence learn from accumulated business know-how data.

[0999] "Speech recognition technology" is a technology that converts voice into text data.

[1000] "Means for saving as text data" refers to a method for saving text data obtained using speech recognition technology.

[1001] A "cloud database" is a database that is accessible via the Internet.

[1002] "Means for making stored text data accessible" refers to a method for making stored text data easily searchable and accessible later.

[1003] The system for carrying out the present invention is designed to improve the efficiency of communication between staff members at a logistics center. A specific embodiment of this system is described below.

[1004] Hardware and software used

[1005] Hardware: Smartphone, microphone

[1006] Software: Python, SpeechRecognition library, SQLite database, cloud storage service

[1007] System configuration

[1008] 1. Speech recognition technology: An application installed on a smartphone collects staff's speech in real time through a microphone and converts it into text data using the SpeechRecognition library.

[1009] 2. Data storage: The converted text data is temporarily stored on the smartphone, and then stored in a cloud database using a cloud storage service.

[1010] 3. Database Management: The accumulated text data is managed using an SQLite database, which stores the conversation timestamp, user name, and conversation content.

[1011] 4. Data Reference: The accumulated text data is designed to be easily searchable and accessible later. Staff can search for past conversations via their smartphones and use them in their work.

[1012] Processing flow

[1013] 1. Speech Recognition: The employee launches the smartphone application and starts a conversation. The microphone collects the voice and the SpeechRecognition library converts the voice into text.

[1014] 2. Data storage: The converted text data is temporarily stored on the smartphone along with a timestamp and the user name, and then transferred to a cloud database via a cloud storage service.

[1015] 3. Data reference: Staff can use a smartphone application to search and reference past conversations from a database on the cloud.

[1016] Specific examples

[1017] For example, if a staff member at a logistics center asks, "Where is the next delivery destination?", the conversation is saved as text data. Later, when another staff member asks the same question, they can refer to the past conversation and get a quick answer.

[1018] Prompt Sentence Examples

[1019] If you ask the question "Where is the next delivery destination?" the prompt text will be as follows:

[1020] User: Where is my next delivery?

[1021] System: Your conversation has been saved.

[1022] In this way, the operational efficiency of the logistics center can be improved.

[1023] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1024] Step 1:

[1025] The user launches the application on their smartphone and starts a conversation.

[1026] Input: User's voice

[1027] Output: Audio data collected by microphone

[1028] Specific operation: The user launches an application on their smartphone and the microphone collects audio.

[1029] Step 2:

[1030] The terminal uses voice recognition technology to convert the collected voice data into text data.

[1031] Input: Audio data

[1032] Output: Text data

[1033] Specific operation: The device uses the SpeechRecognition library to convert the voice data into text data.

[1034] Step 3:

[1035] The terminal temporarily stores the converted text data.

[1036] Input: Text data

[1037] Output: Temporarily saved text data

[1038] What it does: The device temporarily stores the text data on your smartphone along with a timestamp and your username.

[1039] Step 4:

[1040] The device transfers the temporarily stored text data to a database on the cloud.

[1041] Input: Temporarily saved text data

[1042] Output: Text data stored in a cloud database

[1043] Specific operation: The device uses a cloud storage service to transfer text data to a database on the cloud.

[1044] Step 5:

[1045] The server manages the text data stored in a database on the cloud.

[1046] Input: Text data stored in a cloud database

[1047] Output: Managed text data

[1048] Specific operation: The server uses an SQLite database to manage the accumulated text data.

[1049] Step 6:

[1050] Users use a smartphone application to search and view past conversations from a database on the cloud.

[1051] Input: search query

[1052] Output: Text data as search results

[1053] How it works: A user uses a smartphone application to send a search query to a database in the cloud, and the server returns the relevant text data.

[1054] Example 3

[1055] Next, a description will be given of Example 3 of Form Example 3. 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."

[1056] Conventional internal communication tools tend to require long text conversations, which often hinders efficient work progress. Furthermore, there was a lack of effective ways to utilize accumulated business data, preventing the sharing of business know-how and business improvements. Furthermore, there was no effective method for generating new business know-how based on accumulated data. To solve these issues, a system was needed that could efficiently process and analyze data and effectively generate and share business know-how.

[1057] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1058] In this invention, the server includes means for a user to input business data and send it to the server, means for the server to save the received data in a database, means for the server to retrieve data from the database and preprocess it using a data analysis tool, means for the server to input the preprocessed data into a generative AI model and extract patterns of business know-how, means for the server to generate new business know-how based on the patterns extracted and save it in the database, and means for a user to refer to the generated business know-how through a terminal. This enables efficient data processing and analysis, and enables the effective generation and sharing of business know-how.

[1059] An "internal communication tool" is software that facilitates information sharing and communication within a company.

[1060] "Artificial intelligence" refers to computer systems that mimic human intelligence and can learn and reason.

[1061] The "summarization function" is a function that summarizes long texts in a short form, extracting important information and expressing it concisely.

[1062] "Business know-how data" refers to the accumulated knowledge and experience necessary for carrying out business.

[1063] A "database" is a system for efficiently storing, managing, and searching large amounts of data.

[1064] A "data analysis tool" is software used to analyze data and extract meaningful information.

[1065] A "generative AI model" is an artificial intelligence model that generates new information and patterns based on input data.

[1066] "Pattern extraction" is the process of finding common characteristics and patterns in data.

[1067] "Business know-how" refers to the knowledge and skills required to carry out business efficiently.

[1068] A "terminal" is a device such as a computer or smartphone that is operated by a user.

[1069] MODE FOR CARRYING OUT THE INVENTION

[1070] This invention is a system that shortens text conversation time using an AI summarization function in an internal communication tool, accumulates the content of that exchange as business know-how data, and further uses AI to learn from the accumulated data. This system includes: a means for a user to input business data and send it to a server; a means for the server to store the received data in a database; a means for the server to retrieve data from the database and preprocess it using a data analysis tool; a means for the server to input the preprocessed data into a generative AI model and extract patterns of business know-how; a means for the server to generate new business know-how based on the patterns extracted and store it in a database; and a means for a user to refer to the generated business know-how via a terminal.

[1071] Hardware and software used

[1072] Hardware: Servers, terminals

[1073] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), data analysis tools (e.g., Python's pandas library)

[1074] Explanation of program processing

[1075] 1. Data entry and storage

[1076] The user inputs business data from the terminal, such as details of complaint handling and records of work progress.

[1077] The terminal transmits the input data to the server.

[1078] The server stores the received data in a database, typically using a database management system such as MySQL.

[1079] 2. Data Preprocessing

[1080] The server periodically retrieves the accumulated data from the database.

[1081] The server preprocesses the acquired data using a data analysis tool (e.g., Python's pandas library), specifically cleaning the data (filling in missing values ​​and removing outliers) and standardizing the format.

[1082] 3. Data analysis using AI models

[1083] The server inputs the preprocessed data into a generative AI model (e.g., GPT-4).

[1084] The generative AI model analyzes data and extracts patterns of business know-how, such as patterns for responding to specific problems and communication patterns for efficient business progress.

[1085] 4. Generation of business know-how

[1086] The server generates new business know-how based on the patterns extracted by the generative AI model. For example, it generates specific procedures such as "When a complaint occurs, first apologize to the customer, then check the details of the problem."

[1087] The server stores the generated business know-how in a database.

[1088] 5. Preservation and provision of generated know-how

[1089] The server allows users to refer to new business know-how stored in the database.

[1090] Users can access the database through their terminals and view the generated business know-how.

[1091] Specific examples

[1092] For example, a user inputs "procedures for handling complaints" from a terminal. The terminal sends this data to a server, which stores it in a database. The server periodically retrieves this data and cleans it using the pandas library. The server then inputs the preprocessed data into GPT-4, and the generative AI model extracts patterns for handling complaints. For example, a pattern may be found that "when a complaint occurs, first apologize to the customer, then confirm the details of the problem." Based on this pattern, the server generates a new procedure for handling complaints and stores it in a database. The user can view this new procedure through their terminal and use it in their actual work.

[1093] Prompt Sentence Examples

[1094] An example of a prompt sentence to input to the generative AI model is as follows:

[1095] "Generate effective complaint handling procedures based on past complaint handling data."

[1096] By inputting this prompt sentence into the generative AI model, the model analyzes past data and generates a new procedure for handling complaints. The flow of the identification process in Example 3 will be described with reference to FIG. 15.

[1097] Step 1:

[1098] Data entry and accumulation

[1099] The user inputs business data from the terminal, such as details of complaint handling and records of work progress.

[1100] Input: Business data (e.g., complaint handling details)

[1101] The terminal transmits the input data to the server.

[1102] The server stores the received data in a database, typically using a database management system such as MySQL.

[1103] Output: Business data stored in a database

[1104] Step 2:

[1105] Data Preprocessing

[1106] The server periodically retrieves the accumulated data from the database.

[1107] Input: Business data stored in a database

[1108] The server preprocesses the acquired data using a data analysis tool (e.g., Python's pandas library), specifically cleaning the data (filling in missing values ​​and removing outliers) and standardizing the format.

[1109] Output: Preprocessed data

[1110] Step 3:

[1111] Data analysis using AI models

[1112] The server inputs the preprocessed data into a generative AI model (e.g., GPT-4).

[1113] Input: Preprocessed data

[1114] The generative AI model analyzes data and extracts patterns of business know-how, such as patterns for responding to specific problems and communication patterns for efficient business progress.

[1115] Output: Extracted business know-how patterns

[1116] Step 4:

[1117] Generation of business know-how

[1118] The server generates new business know-how based on the patterns extracted by the generative AI model. For example, it generates specific procedures such as "When a complaint occurs, first apologize to the customer, then check the details of the problem."

[1119] Input: Extracted business know-how patterns

[1120] The server stores the generated business know-how in a database.

[1121] Output: New business know-how stored in the database

[1122] Step 5:

[1123] Preservation and dissemination of generated know-how

[1124] The server allows users to refer to new business know-how stored in the database.

[1125] Input: New business know-how stored in the database

[1126] Users can access the database through their terminals and view the generated business know-how.

[1127] Output: Business know-how that can be viewed by users

[1128] (Application example 3)

[1129] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1130] In conventional factory operations, the collection and analysis of work data was often done manually, making it difficult to carry out work efficiently or respond quickly when problems occurred. In addition, there was a lack of accumulation of work know-how and the creation of new know-how, and improvements in work efficiency were required.

[1131] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for shortening text conversation time using an AI summary function in an in-house communication tool, means for accumulating the content of the exchange as business know-how data, means for AI learning from the accumulated data, means for collecting work data within the factory in real time and analyzing the data with AI, means for learning response patterns when specific problems occur and proposing optimal response methods, means for learning communication patterns for efficient work progress and issuing appropriate instructions to workers, and means for generating new business know-how and improving work efficiency. This makes it possible to efficiently collect and analyze work data within the factory, quickly respond to problems when they occur, and accumulate and generate business know-how.

[1132] An "internal communication tool" is software that allows for efficient information sharing and communication within a company.

[1133] The "AI summary function" is a function that uses artificial intelligence to summarize long pieces of text into shorter sentences.

[1134] "Text conversation time-saving methods" are methods for streamlining text-based communication and saving time.

[1135] "Business know-how data" refers to the accumulated knowledge and experience necessary for carrying out business.

[1136] "Means for AI to learn from accumulated data" refers to a method by which artificial intelligence analyzes and learns from accumulated data.

[1137] "Factory work data" refers to data related to various types of work carried out within a factory.

[1138] "Real-time collection means" refers to a method for collecting data in real time.

[1139] "The means by which the AI ​​analyzes the data" refers to the method by which the artificial intelligence analyzes the collected data.

[1140] The "response pattern when a specific problem occurs" is a pattern of response methods to be taken when a specific problem occurs.

[1141] "Means for proposing the most appropriate response method" is a method for proposing the most appropriate response method when a problem occurs.

[1142] "Communication patterns for efficient business progress" are methods of communication for efficiently progressing business.

[1143] "Means for issuing appropriate instructions to workers" refers to a method for providing appropriate instructions to workers.

[1144] "Means for generating new business know-how" refers to a method for creating new business know-how.

[1145] "Means for improving work efficiency" are methods for increasing work efficiency.

[1146] The system for implementing this invention is configured as follows: First, the server provides a means for shortening text conversation time using an AI summarization function in an internal communication tool, allowing users to communicate more efficiently.

[1147] Next, the server has the means to store the content of these interactions as business know-how data, which will later become an important source of information for the AI ​​to learn from.

[1148] Furthermore, the server provides a means for AI to learn from the accumulated data, allowing the AI ​​to learn patterns for responding to specific problems when they arise and communication patterns for efficient business operations.

[1149] The server also includes a means for collecting data on factory operations in real time, allowing the server to instantly collect data on various operations within the factory and analyze the data using AI.

[1150] The server also includes a means for learning response patterns when specific problems occur and proposing optimal response methods. This means allows the server to propose a quick and appropriate response when a problem occurs.

[1151] The server also includes a means for learning communication patterns for efficient work progress and issuing appropriate instructions to workers. This means enables the server to provide efficient instructions to workers and ensure smooth work progress.

[1152] Finally, the server also includes a means for generating new business know-how and improving work efficiency. This means enables the server to generate new business know-how and improve work efficiency.

[1153] Specifically, the server processes and calculates data using software such as Python, Pandas, Scikit-learn, and Joblib. For example, if a specific machine in a factory breaks down, the AI ​​analyzes the failure data and suggests the optimal repair method based on past data. It can also learn patterns that allow workers to communicate efficiently and issue work instructions.

[1154] An example of a prompt sentence might be:

[1155] "Please suggest the best way to repair machine A when it breaks down in the factory. Based on past data, please tell me the most efficient repair procedure."

[1156] In this way, the server can efficiently collect and analyze work data within the factory, enabling quick responses when problems arise and the accumulation and generation of business know-how.

[1157] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1158] Step 1:

[1159] The server collects users' text conversations through internal communication tools. The input is the user's text conversation, and the output is a summarized text. Specifically, it uses an AI summary function to summarize long texts into shorter ones.

[1160] Step 2:

[1161] The server accumulates the summarized text as business know-how data. The input is the summarized text, and the output is the accumulated business know-how data. Specifically, the text is stored in a database.

[1162] Step 3:

[1163] The server uses AI to learn from the accumulated data. The input is the accumulated business know-how data, and the output is a trained model. Specifically, it analyzes the data and trains the model using Python and Scikit-learn.

[1164] Step 4:

[1165] The server collects work data from within the factory in real time. The input is data from various sensors within the factory, and the output is the collected work data. Specifically, data is collected using IoT devices and sent to the server.

[1166] Step 5:

[1167] The server analyzes the collected work data using AI. The input is the collected work data, and the output is the analysis results. Specifically, the data is preprocessed using Python and Pandas, and then analyzed using Scikit-learn.

[1168] Step 6:

[1169] The server learns response patterns when specific problems occur and proposes the optimal response method. The input is the analysis results, and the output is the optimal response method. Specifically, it extracts response patterns based on past data and generates proposals.

[1170] Step 7:

[1171] The server learns communication patterns for efficient work progress and issues appropriate instructions to workers. The input is the trained model and real-time data, and the output is work instructions. Specifically, the AI ​​generates optimal communication patterns and sends instructions to workers.

[1172] Step 8:

[1173] The server generates new business know-how and improves work efficiency. The input is a trained model and real-time data, and the output is new business know-how. Specifically, the AI ​​generates new know-how and stores it in a database.

[1174] In this way, the server can efficiently collect and analyze work data within the factory, enabling quick responses when problems arise and the accumulation and generation of business know-how.

[1175] Furthermore, 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.

[1176] "Example 1"

[1177] One embodiment of the present invention provides a system including an emotion engine in which an AI recognizes a user's emotions. In this system, when a user has a text conversation using an internal communication tool, the AI ​​summarizes the conversation content in real time. Furthermore, the emotion engine reads emotions from the user's text and adjusts the accuracy of the summary based on the emotions. For example, if the user expresses anger, the emotion engine feeds that information back to the AI, which then reflects that information in generating the summary. This results in a more appropriate summary based on the user's emotions.

[1178] "Example 2"

[1179] Another embodiment of the present invention provides a system in which an emotion engine adjusts the learning of business know-how data based on the user's emotions. In this system, conversations between users are saved as text data, and this data is accumulated as business know-how data. The emotion engine reads the user's emotions and adjusts the AI's learning based on those emotions. For example, if the user expresses joy, the emotion engine feeds that information back to the AI, and the AI ​​reflects that information in the learning of the business know-how data. This generates more appropriate business know-how that corresponds to the user's emotions.

[1180] "Example 3"

[1181] Furthermore, as a further embodiment of the present invention, a system is provided in which an emotion engine presents business know-how to a user that is generated based on the user's emotions. In this system, an AI analyzes accumulated data and extracts patterns of business know-how. The emotion engine reads the user's emotions and presents the user with business know-how that is generated based on those emotions. For example, if the user expresses anxiety, the emotion engine feeds that information back to the AI, and the AI ​​adjusts the presentation of business know-how to the user based on that information. This allows the system to present more appropriate business know-how that is in line with the user's emotions.

[1182] The processing flow of each embodiment will be described below.

[1183] "Example 1"

[1184] Step 1: Users engage in text conversations using internal communication tools.

[1185] Step 2: The AI ​​summarizes the conversation in real time.

[1186] Step 3: The emotion engine reads the emotion from the user's text.

[1187] Step 4: The emotion engine feeds the emotion information back to the AI.

[1188] Step 5: The AI ​​uses that information to adjust the accuracy of the summary.

[1189] "Example 2"

[1190] Step 1: The content of conversations between users is saved as text data, and that data is accumulated as business know-how data.

[1191] Step 2: The emotion engine reads the user's emotions.

[1192] Step 3: The emotion engine feeds the emotion information back to the AI.

[1193] Step 4: The AI ​​reflects this information and adjusts its learning of the business know-how data.

[1194] "Example 3"

[1195] Step 1: AI analyzes the accumulated data and extracts patterns of business know-how.

[1196] Step 2: The emotion engine reads the user's emotions.

[1197] Step 3: The emotion engine feeds the emotion information back to the AI.

[1198] Step 4: The AI ​​uses this information to adjust the presentation of business know-how to the user.

[1199] Example 1

[1200] 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."

[1201] In-house communication tools are required to efficiently summarize long text messages so that users can quickly obtain information. Another challenge is to improve the quality of communication by providing summaries that take the user's emotions into account. Furthermore, it is also important to accumulate the content of these exchanges as business know-how and use it to improve business operations.

[1202] 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.

[1203] In this invention, the server includes: means for shortening text conversation time using an AI summarization function in an internal communication tool; means for accumulating the content of the exchange as business know-how data; means for learning the accumulated data using AI; means for adjusting the accuracy of the summary using an emotion engine that recognizes the user's emotions; and means for displaying the summary results on the user's terminal. This allows users to save time reading long texts and obtain information efficiently. Furthermore, since appropriate summaries are provided based on the user's emotions, the quality of communication improves. Furthermore, the accumulated data can be used to improve business operations and generate new business know-how.

[1204] An "internal communication tool" is software or a platform that facilitates information sharing and communication within a company or organization.

[1205] "Artificial intelligence summary function" is a technology that analyzes long text data, extracts important information, and generates a short summary.

[1206] A "text conversation time shortener" is a method for quickly conveying information by summarizing long text messages sent by users.

[1207] "Business know-how data" refers to the accumulated data of knowledge and experience gained in the course of business operations.

[1208] "Means of learning accumulated data using artificial intelligence" refers to a method of analyzing accumulated business know-how data using artificial intelligence to learn patterns and trends.

[1209] An "emotion engine" is a technology for analyzing and identifying a user's emotions from text data.

[1210] "Means for adjusting the accuracy of the summary" refers to a method for appropriately adjusting the content and expression of the summary based on the emotional information obtained from the emotion engine.

[1211] "Means for displaying the summary results on the user's terminal" refers to a method for displaying the generated summary on the device used by the user (such as a personal computer or smartphone).

[1212] "Means for business improvement" refers to methods for improving business processes and methods based on accumulated data and the learning results of artificial intelligence.

[1213] "Means for generating new business know-how" refers to a method for creating new business knowledge and methods by utilizing the learning results of artificial intelligence.

[1214] This invention is a system that combines an AI summarization function and an emotion recognition engine for an internal communication tool. When users have text conversations, the AI ​​summarizes the content in real time, and the emotion recognition engine recognizes the user's emotions and adjusts the accuracy of the summary.

[1215] Hardware and software used

[1216] Hardware: Server, user terminal (PC, smartphone)

[1217] Software: Internal communication tools (e.g., popular messaging platforms), artificial intelligence summarization engines (e.g., popular generative AI models), emotion recognition engines (e.g., popular emotion analysis tools)

[1218] Overview of program processing

[1219] 1. User initiates a text conversation:

[1220] A user types a text message using an internal communication tool and presses the send button.

[1221] 2. The server receives the text data:

[1222] The server receives the text message sent by the user and temporarily stores the data.

[1223] 3. The server sends the text data to the AI ​​summarization engine:

[1224] The server sends the received text data to the AI ​​summarization engine via an API.

[1225] 4. The server sends the text data to the emotion recognition engine:

[1226] The server also sends the same text data to an emotion recognition engine, also using an API.

[1227] 5. AI summarization engine summarizes text:

[1228] The AI ​​summarization engine analyzes the received text data and generates a summary, which is then temporarily saved.

[1229] 6. Emotion recognition engine analyzes emotions:

[1230] The emotion recognition engine analyzes the text data and identifies the user's emotions (e.g., anger, joy, sadness, etc.), and the analysis results are returned to the server.

[1231] 7. The server feeds back the emotion recognition results to the AI ​​summarization engine:

[1232] The server feeds back the emotion analysis results received from the emotion recognition engine to the AI ​​summarization engine, providing information for adjusting the accuracy of summarization.

[1233] 8. AI summarization engine adjusts the accuracy of summaries:

[1234] The AI ​​summarization engine adjusts the accuracy of summaries based on emotion recognition results. For example, if a user expresses anger, the summaries will reflect that information.

[1235] 9. The server sends the final summary to the user's device:

[1236] The server then sends the final adjusted summary to the user's device in real time.

[1237] 10. A summary is displayed on the user's terminal:

[1238] The final summary is displayed on the user's device, allowing the user to obtain information efficiently without having to spend time reading long texts.

[1239] Specific examples

[1240] Example user input: "I'm very frustrated with how slowly this project is progressing. Let's figure out how to move forward more efficiently."

[1241] AI Summarization Engine Output: "The project is lagging behind, so we need to find a more efficient way to do it."

[1242] Emotion recognition engine analysis result: Anger (high)

[1243] Final summary: "The project is progressing slowly and we urgently need to find a more efficient way to do it."

[1244] Prompt Sentence Examples

[1245] Prompt: "Design a system that summarizes text conversations in real time as users engage in them, and adjusts the accuracy of the summary based on the user's sentiment."

[1246] This system allows users to obtain information efficiently, saving them the time of reading long texts. It also provides appropriate summaries based on the user's emotions, improving the quality of communication. Furthermore, the accumulated data can be used to improve business operations and generate new business know-how.

[1247] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1248] Step 1:

[1249] A user initiates a text conversation.

[1250] A user types a text message using an internal communication tool and presses the send button.

[1251] Input: The text message entered by the user.

[1252] Output: A text message is sent to the server.

[1253] Step 2:

[1254] The server receives the text data.

[1255] The server receives the text message sent by the user and temporarily stores the data.

[1256] Input: The text message sent by the user.

[1257] Output: Text data is saved on the server.

[1258] Step 3:

[1259] The server sends the text data to the AI ​​summarization engine.

[1260] The server sends the received text data to the AI ​​summarization engine via an API.

[1261] Input: Text data stored on the server.

[1262] Output: The text data is sent to an AI summarization engine.

[1263] Step 4:

[1264] The server sends the text data to the emotion recognition engine.

[1265] The server also sends the same text data to an emotion recognition engine, also using an API.

[1266] Input: Text data stored on the server.

[1267] Output: The text data is sent to the emotion recognition engine.

[1268] Step 5:

[1269] An AI summarization engine summarizes the text.

[1270] The AI ​​summarization engine analyzes the received text data and generates a summary, which is then temporarily saved.

[1271] Input: Text data sent to the AI ​​summarization engine.

[1272] Output: Summarized text data.

[1273] Step 6:

[1274] The emotion recognition engine analyzes emotions.

[1275] The emotion recognition engine analyzes the text data and identifies the user's emotions (e.g., anger, joy, sadness, etc.), and the analysis results are returned to the server.

[1276] Input: Text data sent to the emotion recognition engine.

[1277] Output: Sentiment analysis results.

[1278] Step 7:

[1279] The server feeds back the emotion recognition results to the AI ​​summarization engine.

[1280] The server feeds back the emotion analysis results received from the emotion recognition engine to the AI ​​summarization engine, providing information for adjusting the accuracy of summarization.

[1281] Input: Sentiment analysis results.

[1282] Output: Sentiment analysis results are sent to an AI summarization engine.

[1283] Step 8:

[1284] The AI ​​summarization engine adjusts the accuracy of the summary.

[1285] The AI ​​summarization engine adjusts the accuracy of summaries based on emotion recognition results. For example, if a user expresses anger, the summaries will reflect that information.

[1286] Input: Sentiment analysis results.

[1287] Output: Adjusted summary text.

[1288] Step 9:

[1289] The server sends the final summary result to the user's terminal.

[1290] The server then sends the final adjusted summary to the user's device in real time.

[1291] Input: The adjusted summary text.

[1292] Output: The summary text is sent to the user's terminal.

[1293] Step 10:

[1294] A summary is displayed on the user's terminal.

[1295] The final summary is displayed on the user's device, allowing the user to obtain information efficiently without having to spend time reading long texts.

[1296] Input: Summary text.

[1297] Output: Summary text displayed on the user's terminal.

[1298] (Application example 1)

[1299] 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."

[1300] Conventional internal communication tools often involve long text exchanges, making it difficult for users to efficiently obtain information. Furthermore, summaries are often generated without taking the user's emotions into consideration, which can result in inappropriate summaries being provided. Furthermore, in physical stores, staff are required to communicate with customers quickly and accurately, but there has been a lack of technology to support this. To solve these issues, a system is needed that performs summaries and sentiment analysis in real time, providing appropriate summaries based on the user's emotions.

[1301] 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.

[1302] In this invention, the server includes: means for shortening text conversation time using an AI summarization function in an internal communication tool; means for accumulating the content of those exchanges as business know-how data; means for AI learning from the accumulated data; means for recognizing user emotions using an emotion engine and adjusting the accuracy of summaries based on those emotions; and means installed on a smart device for real-time summarization and emotion analysis. This allows users to save time reading long texts and obtain information efficiently. Furthermore, because appropriate summaries are provided based on the user's emotions, store staff can quickly grasp customer needs and emotions, enabling more appropriate customer service.

[1303] An "internal communication tool" is software that allows for efficient information sharing and communication within a company.

[1304] The "AI summary function" is a function that uses artificial intelligence to summarize long texts in a shorter form.

[1305] "Text conversation time reduction measures" are methods that allow users to reduce the time it takes to read long texts and obtain information efficiently.

[1306] "Business know-how data" refers to the accumulation of business-related knowledge and experience as data.

[1307] "Means of using AI to learn from accumulated data" refers to a method by which artificial intelligence learns from accumulated business know-how data.

[1308] An "emotion engine" is a system that reads emotions from a user's text and processes them based on those emotions.

[1309] "Means for recognizing user emotions" refers to a method for reading emotions from a user's text.

[1310] The "means for adjusting the accuracy of the summary" is a method for appropriately adjusting the content of the summary based on the recognized emotions.

[1311] A "smart device" is an electronic device that has Internet connectivity and can run a variety of applications.

[1312] "Means for real-time summarization and sentiment analysis" refers to a method for performing instant summarization and sentiment analysis as a user enters text.

[1313] The system for implementing this invention combines an AI summarization function, an emotion engine, and a smart device in an internal communication tool. Specifically, the server includes the following means:

[1314] First, the server uses the AI ​​summarization function of the internal communication tool to summarize the text entered by the user in real time. This summarization function is realized using OpenAI's API. When the user enters a long text, the server sends the text to OpenAI's API and receives the summarized text.

[1315] Next, the server uses an emotion engine to recognize emotions from the user's input text. The emotion engine is implemented using the emotion analysis model from the Transformers library. The server inputs the user's text into the emotion analysis model and obtains the emotion type and its score.

[1316] Furthermore, the server adjusts the accuracy of the summary based on the recognized emotion: for example, if the user expresses anger, the server will feed that information back into the summary generation process to generate a more appropriate summary.

[1317] A smart device (e.g., smart glasses) acts as an interface for executing these functions in real time. When a user inputs text through the smart device, the text is sent to the server, where it is summarized and sentiment analyzed, and the results are displayed on the smart device.

[1318] As a concrete example, consider the case where a customer says to a physical store, "This product was not what I expected. I would like to return it." In this case, the server performs the following process:

[1319] 1. The server receives the customer's text and generates a summary using OpenAI's API.

[1320] 2. The server uses an emotion engine to recognize the emotion of "anger" or "dissatisfaction" from the customer's text.

[1321] 3. The server adjusts the accuracy of the summary based on the recognized sentiment and generates a summary such as, "The customer is dissatisfied with the product and wishes to return it."

[1322] 4. This summary and the results of the sentiment analysis are displayed on the smart device, allowing staff to quickly understand the customer's needs and emotions.

[1323] An example of a prompt is as follows:

[1324] "Summarize the text below: This product was disappointing and I would like to return it."

[1325] In this way, users can obtain information efficiently without having to spend time reading long texts. In addition, by providing an appropriate summary based on the user's emotions, store staff can quickly understand the needs and emotions of customers and provide more appropriate customer service.

[1326] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1327] Step 1:

[1328] A user inputs text via a smart device.

[1329] Input: Text entered by the user (e.g., "This product was disappointing. I would like to return it.")

[1330] Output: The entered text is sent to the server.

[1331] Step 2:

[1332] The server sends the received text to OpenAI's API and generates a summary.

[1333] Input: Text entered by the user

[1334] Data processing: Send the text to OpenAI's API and create a prompt to generate a summary.

[1335] Output: Abridged text (e.g. "The customer is unhappy with the product and would like to return it.")

[1336] Step 3:

[1337] The server sends the summarized text to the emotion engine for sentiment analysis.

[1338] Input: Summarized text

[1339] Data Computing: Recognize emotions from text using the sentiment analysis model from the Transformers library.

[1340] Output: Emotion type and its score (e.g., "Anger" or "Frustrated", score: 0.85)

[1341] Step 4:

[1342] The server adjusts the accuracy of the summary based on the recognized emotions.

[1343] Input: Sentiment type and its score, summarized text

[1344] Data processing: The content of the summary is adjusted appropriately taking into account the type and score of the emotion.

[1345] Output: Tailored summary text (e.g. "The customer is unhappy with the product and would like to return it.")

[1346] Step 5:

[1347] The server sends the adjusted summary text and the results of sentiment analysis to the smart device.

[1348] Input: Adjusted summary text, sentiment analysis results

[1349] Output: Summary text and sentiment analysis results displayed on smart devices

[1350] Step 6:

[1351] Users can view the summary text and sentiment analysis results via their smart devices.

[1352] Input: Summary text displayed on a smart device and sentiment analysis results

[1353] Output: The information is provided so that users can quickly grasp it and take appropriate action.

[1354] The above processing steps allow users to obtain information efficiently, saving them the time of reading long text. In addition, by providing an appropriate summary based on the user's emotions, staff in brick-and-mortar stores can quickly grasp the needs and emotions of customers and provide more appropriate customer service.

[1355] Example 2

[1356] Next, a description will be given of 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."

[1357] Conventional internal communication tools have made it difficult to efficiently manage conversation content and accumulate it as business know-how. Furthermore, they were unable to generate business know-how that took user emotions into account, limiting the efficiency and improvement of business processes. Furthermore, simply saving conversation content as text data makes it difficult to generate appropriate business know-how that reflects emotional nuances.

[1358] 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.

[1359] In this invention, the server includes means for shortening text conversation time using an AI summarization function in an internal communication tool, means for accumulating the content of the exchange as business know-how data, means for learning the accumulated data using AI, means for converting the content of the user's conversation from voice to text data in real time, means for saving the converted text data in a database, means for sending the saved text data to an emotion analysis engine and analyzing the user's emotions, and means for adjusting the learning data of the generation AI model based on the analyzed emotion information. This makes it possible to generate more appropriate business know-how according to the user's emotions, thereby realizing efficiency and improvement of business operations.

[1360] "Internal communication tools" are software and platforms that facilitate information sharing and communication within a company or organization.

[1361] "Artificial intelligence summary function" is a technology that shortens long pieces of text or conversation content and extracts only the important information.

[1362] "Business know-how data" refers to the accumulated knowledge and experience necessary for carrying out business.

[1363] The "means for converting voice to text data" is a technology that uses voice recognition technology to convert voice information into text information.

[1364] "Means of storing data in a database" refers to the technology used to store data in a database system so that it can be efficiently managed and searched.

[1365] An "emotion analysis engine" is a technology that analyzes user emotions from text data and outputs those emotions as numerical values ​​or categories.

[1366] A "generative AI model" is an artificial intelligence model that generates new information and knowledge based on given data.

[1367] "Means for adjusting learning data" refers to a technology that optimizes the data that the generative AI model learns based on analyzed emotional information.

[1368] This invention is a system that shortens the time spent on text conversations by using an AI summary function in an internal communication tool, accumulates the content of those exchanges as business know-how data, and then uses AI to learn from the accumulated data. Specific embodiments of this system are described below.

[1369] Hardware and software used

[1370] Hardware: Servers, devices (PCs, smartphones, etc.)

[1371] Software: database management systems (e.g., MySQL), sentiment analysis engines (e.g., IBM Watson), generative AI models (e.g., GPT-4), and voice recognition software (e.g., Google Speech-to-Text)

[1372] Specific operation of the system

[1373] 1. Collecting conversation content

[1374] Users use terminals to have conversations.

[1375] The device uses voice recognition software to convert the conversation from voice to text data in real time. For example, if User A says, "The project is progressing smoothly," the device converts this voice into text data: "The project is progressing smoothly."

[1376] The terminal transmits the converted text data to the server.

[1377] 2. Data storage

[1378] The server receives the text data sent from the terminal.

[1379] The server stores the received text data in a database management system. For example, the text data "The project is progressing smoothly" is stored in the database.

[1380] 3. Emotion analysis

[1381] The server sends the stored text data to a sentiment analysis engine.

[1382] A sentiment analysis engine reads user emotions from text data. For example, it analyzes positive emotions from the text "The project is progressing smoothly."

[1383] The emotion analysis engine returns the analysis result to the server. For example, the analysis result "positive emotion" is returned to the server.

[1384] 4. Adjusting AI learning

[1385] The server adjusts the learning data for the generative AI model based on the analysis results received from the emotion analysis engine.

[1386] The server preferentially feeds back text data containing positive emotions to the generative AI model. For example, text data containing positive emotions such as "The project is progressing smoothly" is fed back to the generative AI model.

[1387] The generative AI model learns from the business know-how data based on the feedback information, thereby generating more appropriate business know-how in response to the user's emotions.

[1388] Specific examples

[1389] Collection and storage of conversations

[1390] User A and User B are having a conversation about the progress of a project.

[1391] The device converts the conversation "The project is progressing smoothly" into text data and sends it to the server.

[1392] The server stores this text data in a database.

[1393] Sentiment analysis and AI learning adjustments

[1394] The sentiment analysis engine detects positive sentiment from the text "Everything is going well."

[1395] The server feeds this positive emotional information back into the generative AI model.

[1396] Based on this information, the generative AI model prioritizes learning business know-how data that contains positive emotions.

[1397] Prompt Sentence Examples

[1398] "Please explain in detail the processing steps of a system that stores conversations between users as text data and adjusts learning from that data using a sentiment analysis engine."

[1399] "If the user expresses happiness, please explain, with specific examples, how to feed that information back to the AI ​​and reflect it in the learning of business know-how data."

[1400] This system generates more appropriate business know-how based on the user's emotions, leading to improved and more efficient business operations.

[1401] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1402] Step 1:

[1403] Collection of conversation content

[1404] Users use terminals to have conversations.

[1405] The device uses voice recognition software to convert conversations from voice to text data in real time.

[1406] Input: User's voice data

[1407] Data processing: Speech recognition software converts the voice data into text data.

[1408] Output: Text data

[1409] Specific operation: For example, when user A says, "The project is progressing smoothly," the device converts this speech into text data, "The project is progressing smoothly."

[1410] Step 2:

[1411] Data transmission and storage

[1412] The terminal transmits the converted text data to the server.

[1413] The server receives the text data sent from the terminal.

[1414] The server stores the received text data in a database management system.

[1415] Input: Text data

[1416] Data processing: Save the text data in a database.

[1417] Output: Text data stored in a database

[1418] Specific operation: For example, text data such as "The project is progressing smoothly" is stored in the database.

[1419] Step 3:

[1420] Emotion analysis

[1421] The server sends the stored text data to a sentiment analysis engine.

[1422] The sentiment analysis engine reads user emotions from text data.

[1423] The sentiment analysis engine returns the analysis results to the server.

[1424] Input: Text data stored in a database

[1425] Data processing: The sentiment analysis engine analyzes the text data and generates sentiment information.

[1426] Output: Emotional information

[1427] Specific operation: For example, positive emotions are analyzed from the text "The project is progressing smoothly," and the analysis result "positive emotions" is returned to the server.

[1428] Step 4:

[1429] AI learning adjustments

[1430] The server adjusts the learning data for the generative AI model based on the analysis results received from the emotion analysis engine.

[1431] The server prioritizes text data containing positive emotions and feeds it back to the generative AI model.

[1432] The generative AI model learns business know-how data based on the feedback information.

[1433] Input: Emotional information and text data

[1434] Data processing: Adjusting the learning data of the generative AI model based on emotional information.

[1435] Output: Refine training data

[1436] Specific operation: For example, text data containing positive emotions such as "The project is progressing smoothly" is fed back to the generative AI model, and the generative AI model uses this information to learn business know-how data.

[1437] In this way, more appropriate business know-how is generated in accordance with the user's feelings, and business efficiency and improvement can be realized.

[1438] (Application example 2)

[1439] 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."

[1440] Conventional internal communication tools can accumulate conversation content as business know-how data, but they do not take user emotions into account when learning data or recommend content based on emotions, which means that they do not sufficiently improve business efficiency or user satisfaction.

[1441] 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.

[1442] In this invention, the server includes means for shortening text conversation time using an AI summarization function in an internal communication tool, means for accumulating the content of the exchange as business know-how data, means for learning the accumulated data using an AI, means for adjusting the learning of the business know-how data using an emotion engine that analyzes user emotions, and means for recommending optimal content based on the user emotions. This makes it possible to learn data taking user emotions into consideration and recommend content based on emotions.

[1443] "Internal communication tools" are software and platforms that enable efficient information sharing and communication within a company or organization.

[1444] The "AI summary function" is a function that uses artificial intelligence to summarize long texts in a short form.

[1445] "Means to shorten text conversation time" refers to methods that efficiently summarize conversation content and allow users to obtain the necessary information in a short amount of time.

[1446] "Business know-how data" refers to the accumulation of business-related knowledge and experience as data.

[1447] "Storage means" refers to the method by which data is stored and made available for later reference.

[1448] "Means of learning with AI" refers to a method of using artificial intelligence to analyze accumulated data and learn new knowledge and patterns.

[1449] An "emotion engine" is software that analyzes the user's emotions and adjusts the system's behavior based on the results.

[1450] The "means for adjusting the learning of business know-how data" is a method for optimizing the data learning process based on the user's emotions using an emotion engine.

[1451] "Content recommendation methods" are methods that suggest optimal content based on a user's emotions and past behavior.

[1452] The following system configuration will be described as an embodiment of the present invention.

[1453] Server provides a means to shorten text conversation times by using an AI summary function in internal communication tools. This means that it uses artificial intelligence (AI) to summarize long texts entered by users, allowing them to obtain the necessary information in a short amount of time. Specifically, it uses natural language processing (NLP) technology to analyze the text and extract important parts.

[1454] Next, the server provides a means to store the content of these exchanges as business know-how data. This means saves the content of conversations between users as text data and stores it in a database. This makes it possible to refer to past conversations, contributing to improved business efficiency.

[1455] Furthermore, the server provides a means for AI-based learning of the accumulated data. This means analyzing the accumulated business know-how data using artificial intelligence and learning new knowledge and patterns. This allows the quality of business know-how to be improved.

[1456] The server also provides a means for adjusting the learning of business know-how data using an emotion engine that analyzes user emotions. This means analyzes user emotions and optimizes the data learning process based on the results. Specifically, the emotion engine reads the user's emotions and adjusts the AI ​​learning based on those emotions.

[1457] Furthermore, the server provides a means for recommending optimal content based on the user's emotions. This means proposes optimal content based on the user's emotions and past behavior. Specifically, the emotion engine analyzes the user's emotions and recommends content based on the results.

[1458] The hardware used includes servers, databases, and user devices (smartphones, PCs, etc.). The software used includes natural language processing (NLP) libraries, sentiment analysis engines, database management systems (DBMS), etc. Specific software examples include TextBlob (NLP library) and SQLite (DBMS).

[1459] For example, if a user says, "I had so much fun today!", a past conversation such as "This movie was great" will be recommended based on that emotion. An example of this prompt is as follows:

[1460] User ID: user123

[1461] Conversation: Today was so much fun!

[1462] In this way, it becomes possible to learn data that takes user emotions into account and recommend content based on those emotions.

[1463] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1464] Step 1:

[1465] A user has a conversation using an internal communication tool. The text data entered by the user is sent from the terminal to the server. The input is the content of the user's conversation, and the output is the text data sent to the server.

[1466] Step 2:

[1467] The server analyzes the received text data using an AI summarization function. Specifically, it uses a natural language processing (NLP) library to analyze the text and extract important parts. The input is the text data of the user's conversation, and the output is the summarized text data.

[1468] Step 3:

[1469] The server stores the summarized text data in a database as business know-how data. Specifically, the data is saved using a database management system (DBMS) such as SQLite. The input is the summarized text data, and the output is the business know-how data saved in the database.

[1470] Step 4:

[1471] The server uses AI to learn from the accumulated business know-how data. Specifically, it analyzes the data using machine learning algorithms and learns new knowledge and patterns. The input is the business know-how data stored in the database, and the output is the learning results.

[1472] Step 5:

[1473] The server uses an emotion engine to analyze the user's emotions. Specifically, it uses an emotion analysis library such as TextBlob to analyze the user's emotions. The input is the text data of the user's conversation, and the output is the analyzed emotion data.

[1474] Step 6:

[1475] The server uses an emotion engine to adjust the learning of business know-how data. Specifically, it optimizes the AI ​​learning process based on the user's emotions. The input is the analyzed emotion data and business know-how data, and the output is the adjusted learning process.

[1476] Step 7:

[1477] The server recommends optimal content based on the user's emotions. Specifically, it selects optimal content from past conversations based on emotional data analyzed by the emotion engine. The input is the analyzed emotional data and past conversations, and the output is recommended content.

[1478] Step 8:

[1479] The server sends the recommended content to the user terminal, and the user can receive and view the recommended content on the terminal. The input is the recommended content, and the output is the content displayed on the user terminal.

[1480] Example 3

[1481] Next, a description will be given of Example 3 of Form Example 3. 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."

[1482] With conventional internal communication tools, conversations tended to take a long time via text, which often hindered efficient work progress. Furthermore, there was a lack of effective ways to utilize accumulated business data, and work know-how was not shared or improved sufficiently. Furthermore, it was difficult to provide appropriate business know-how that reflected the user's feelings, which meant that users' anxiety and stress could not be alleviated.

[1483] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes means for shortening the time of text conversations using an AI summarization function in an internal communication tool, means for accumulating the content of the exchanges as business know-how data, means for learning the accumulated data using AI, means for analyzing user emotions, means for generating business know-how based on the user emotions, and means for presenting the generated business know-how to the user. This enables efficient communication and effective sharing of business know-how, and further enables the provision of appropriate business know-how according to the user's emotions.

[1484] "Internal communication tools" are software and platforms that enable efficient information sharing and communication within a company or organization.

[1485] "Artificial intelligence" is the technology that enables computer systems to mimic human intelligence and perform functions such as learning, reasoning, recognition, and decision-making.

[1486] The "summary function" is a function that shortens the content of long text or conversations and extracts and presents only the important information.

[1487] "Business know-how data" refers to the accumulation of knowledge and experience related to business progress and problem solving.

[1488] "Accumulated data" refers to records of past business operations and communications stored in a database or similar.

[1489] The "means of learning" is the process by which artificial intelligence analyzes accumulated data, extracts patterns and knowledge, and learns.

[1490] "Means for analyzing emotions" refers to technology that reads emotions from a user's text or voice and identifies those emotions.

[1491] "Means for generating business know-how" refers to the process of creating new business know-how based on data learned by artificial intelligence and user emotions.

[1492] The "means for presenting business know-how" is a method for providing the generated business know-how to the user visually or audibly.

[1493] MODE FOR CARRYING OUT THE INVENTION

[1494] This invention is a system that shortens text conversation time using an AI summarization function in an internal communication tool, accumulates the content of the exchange as business know-how data, and further uses AI to learn from the accumulated data.In addition, it includes functions to analyze user emotions, generate business know-how based on those emotions, and present the generated business know-how to the user.

[1495] Hardware and software used

[1496] The server stores business data using a database (e.g., MySQL or PostgreSQL) and analyzes the data using an artificial intelligence model (e.g., TensorFlow or PyTorch). For sentiment analysis, an emotion engine (e.g., IBM Watson or Microsoft Azure's sentiment analysis API) is used. The terminal is a device (e.g., a PC or smartphone) that provides a user interface and receives user input.

[1497] Program processing

[1498] The server periodically collects business data from the database and inputs it into the AI ​​model for analysis. Specifically, the server executes the SQL query "SELECT FROM project_logs WHERE date >= CURDATE()" to collect data for the current day. The collected data is input into the AI ​​model, which extracts patterns of business know-how. For example, the AI ​​model learns "how to respond when a project is delayed" and saves the pattern.

[1499] The device uses an emotion engine to analyze the user's emotions in real time. When a user types "I'm anxious about moving forward with a new project" into the device, the device sends the text to the emotion engine and obtains emotion data. The emotion engine analyzes the emotion "anxiety" and returns the result to the device.

[1500] The server feeds the user's emotional data obtained from the emotion engine back to the AI. The AI ​​generates business know-how based on the user's emotions. Specifically, if the user is feeling anxious, the AI ​​extracts business know-how from past data that will give the user a sense of security.

[1501] The device presents the generated business know-how to the user. For example, the device screen might display a message such as, "If you are worried about the progress of a project, take the following steps: 1. Communicate regularly with your team members. 2. Use tools to visualize progress. 3. Take immediate action if a problem occurs."

[1502] Examples of specific examples and prompts

[1503] As a concrete example, consider a case where a user is feeling anxious about progressing with a new project. The emotion engine detects the user's anxiety and feeds that information back to the AI. The AI ​​then uses past data to extract successful project progression methods in similar situations and presents specific steps and communication methods to the user.

[1504] Example prompt sentence:

[1505] "I'm nervous about starting a new project. Can you tell me how to proceed based on past success stories?"

[1506] In this way, the server, the terminal, and the user work together to provide business know-how based on emotions. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1507] Step 1: Data collection

[1508] The server collects business data from the database. Specifically, the server executes the SQL query "SELECT FROM project_logs WHERE date >= CURDATE()" to retrieve the data for the current day. This data includes the progress of the project, how to respond when problems occur, communication logs, etc. The input is the query result from the database, and the output is the collected business data.

[1509] Step 2: Data analysis

[1510] The server inputs the collected business data into an artificial intelligence model and performs data analysis. Specifically, the server uses TensorFlow and PyTorch to extract patterns of business know-how. For example, the AI ​​model learns "how to respond when a project is delayed" and saves it as a pattern. The input is the collected business data, and the output is the extracted business know-how pattern.

[1511] Step 3: Sentiment Analysis

[1512] The device uses an emotion engine to analyze the user's emotions in real time. When the user types "I'm anxious about moving forward with a new project" into the device, the device sends the text to the emotion engine and obtains emotion data. The emotion engine analyzes the emotion "anxiety" and returns the result to the device. The input is the user's text input, and the output is the analyzed emotion data.

[1513] Step 4: Generate business know-how

[1514] The server feeds the user's emotional data obtained from the emotion engine back to the AI. The AI ​​generates business know-how based on the user's emotions. Specifically, if the user feels anxious, the AI ​​extracts business know-how from past data that will give the user a sense of security. The input is emotional data and past business know-how data, and the output is the generated business know-how.

[1515] Step 5: Presentation of business know-how

[1516] The terminal presents the generated business know-how to the user. Specifically, the terminal screen displays the following message: "If you are worried about the progress of a project, take the following steps: 1. Communicate regularly with your team members. 2. Use tools to visualize progress. 3. Take immediate action if a problem occurs." The input is the generated business know-how, and the output is what is presented to the user.

[1517] In this way, the server, terminal, and user work together to provide emotion-based business know-how.

[1518] (Application example 3)

[1519] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1520] Conventional work support systems present work know-how without considering the emotions of workers, which means they are unable to reduce worker stress and anxiety. Furthermore, data analysis to generate efficient work know-how is insufficient, limiting the effectiveness of work improvement. This can lead to a decline in worker productivity and work efficiency.

[1521] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1522] In this invention, the server includes means for shortening text conversation time using an AI summarization function in an internal communication tool, means for accumulating the content of the exchange as business know-how data, means for learning the accumulated data using AI, means for reading the user's emotions using an emotion recognition engine, and means for presenting business know-how generated based on the user's emotions. This allows for the provision of appropriate business know-how in accordance with the emotions of workers, enabling efficient business improvement while reducing stress and anxiety.

[1523] "Internal communication tools" are software and platforms that facilitate information sharing and communication within a company.

[1524] The "AI summary function" is a function that uses artificial intelligence to summarize long pieces of text into shorter sentences.

[1525] "Text conversation time-saving methods" are methods and techniques for streamlining and saving time in text-based communication.

[1526] "Business know-how data" refers to the accumulation of knowledge and experience related to business progress and problem solving.

[1527] "Means of learning from accumulated data using AI" refers to a method of analyzing accumulated data using artificial intelligence to extract patterns and knowledge.

[1528] An "emotion recognition engine" is technology or software that can read emotions from a user's facial expressions, tone of voice, etc.

[1529] The "means for presenting business know-how generated based on the user's emotions" refers to a method or technology for providing optimal business know-how according to the user's emotional state.

[1530] As an embodiment of the present invention, an emotion-responsive business support system is constructed. A specific embodiment of the system is shown below.

[1531] System Configuration

[1532] The system consists of the following main components:

[1533] 1. Internal communication tools: Software that facilitates information sharing and communication within a company.

[1534] 2. AI summarization: An artificial intelligence function that summarizes long texts in a concise manner.

[1535] 3. Business know-how database: A database that accumulates knowledge and experience related to business progress and problem solving.

[1536] 4. Emotion recognition engine: Technology that reads emotions from the user's facial expressions, tone of voice, etc.

[1537] 5. Business know-how presentation engine: An engine that provides optimal business know-how according to the user's emotional state.

[1538] Program processing explanation

[1539] Hardware used

[1540] Factory robots: Physical robots used to perform tasks.

[1541] Emotion-aware camera: A camera that captures the user's facial expressions and voice in real time.

[1542] Software used

[1543] Python: A programming language used to implement the program.

[1544] scikit-learn: A library used for data analysis (KMeans clustering).

[1545] EmotionRecognizer library: A library used for emotion recognition.

[1546] AIKnowledgeBase Library: A library used to manage business know-how.

[1547] Data processing and calculation

[1548] 1. Data accumulation: Text data collected through internal communication tools is accumulated in a business know-how database.

[1549] 2. Data analysis: Analyze the accumulated data using scikit-learn's KMeans clustering to extract efficient work patterns.

[1550] 3. Emotion Recognition: Using the EmotionRecognizer library, we analyze the data obtained from the emotion recognition camera and recognize the user's emotions in real time.

[1551] 4. Presentation of business know-how: Based on the recognized emotions, appropriate business know-how is retrieved from the AIKnowledgeBase and presented to the user.

[1552] Specific examples

[1553] For example, if a worker in a factory feels anxious, the emotion recognition camera will recognize that emotion. The emotion recognition engine will then feed that information back to the AI, which will then suggest a relaxing work method from the AI ​​Knowledge Base. This will reduce worker stress and enable more efficient work.

[1554] Prompt Sentence Examples

[1555] Design a system where an emotion-recognition camera reads the emotions of workers in real time, and AI suggests optimal work know-how based on those emotions. For example, if a worker is feeling anxious, it suggests a relaxing work method, and if a worker is feeling stressed, it suggests an efficient procedure.

[1556] The above is an embodiment of the present invention.

[1557] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1558] Step 1:

[1559] The server receives text data collected through internal communication tools and stores it in a business know-how database. The input is text data, and the output is the accumulated business know-how data. Specifically, the server analyzes the text data, extracts important information, and stores it in the database.

[1560] Step 2:

[1561] The server analyzes the accumulated data using scikit-learn's KMeans clustering to extract efficient work patterns. The input is the accumulated business know-how data, and the output is the extracted work patterns. Specifically, the server inputs the data into the clustering algorithm and calculates the center point of each cluster.

[1562] Step 3:

[1563] The emotion recognition camera captures the user's facial expressions and voice in real time and analyzes the data using the EmotionRecognizer library. The input is the user's facial and voice data, and the output is the recognized emotion. Specifically, the camera captures the user's face and voice and sends the data to the emotion recognition engine.

[1564] Step 4:

[1565] The server retrieves appropriate business know-how from the AIKnowledgeBase based on the recognized emotions and presents it to the user. The input is the recognized emotions and extracted work patterns, and the output is the business know-how presented to the user. Specifically, the server searches for the most appropriate business know-how based on the emotion data and displays it to the user.

[1566] Step 5:

[1567] The user performs a task based on the presented business know-how and sends the results as feedback to the server. The input is the user's work result, and the output is feedback data. In concrete terms, the user completes the task and inputs the result to the system.

[1568] Step 6:

[1569] The server stores the feedback data from the user in the business know-how database again and uses it for the next data analysis. The input is the feedback data and the output is the updated business know-how data. Specifically, the server saves the feedback data in the database and prepares it for the next analysis.

[1570] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1571] 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 performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1572] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1573] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1574] [Third embodiment]

[1575] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1576] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1577] 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1578] 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.

[1579] 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 audio in accordance with instructions from the processor 46.

[1580] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1581] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1582] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1583] 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.

[1584] 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.

[1585] In the headset type terminal 314, a 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.

[1586] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1587] "Example 1"

[1588] As one embodiment of the present invention, an AI summarization function is incorporated into an internal communication tool. Specifically, when users are engaged in text conversations, the AI ​​summarizes the content in real time and displays it to the user. This allows users to save time reading long texts and obtain information efficiently.

[1589] "Example 2"

[1590] Furthermore, the content of conversations between users is stored as business know-how data. Specifically, the content of conversations is saved as text data and stored in a database. This makes it possible to refer to the content of past conversations, contributing to improved business efficiency.

[1591] "Example 3"

[1592] Furthermore, the accumulated data is learned by AI. Specifically, the AI ​​analyzes the accumulated data and extracts patterns of business know-how. For example, it learns response patterns when specific problems arise, and communication patterns for efficient business progress. This allows the AI ​​to generate new business know-how that can be used to improve business operations.

[1593] The processing flow of each embodiment will be described below.

[1594] "Example 1"

[1595] Step 1: A user opens an internal communication tool and starts a text conversation.

[1596] Step 2: The AI ​​summarizes the conversation in real time and displays it to the user. Specifically, the AI ​​analyzes the text data, extracts key information, and generates a summary.

[1597] Step 3: The user reviews the summary generated by the AI ​​and efficiently obtains the necessary information.

[1598] "Example 2"

[1599] Step 1: The conversation between users is saved as text data.

[1600] Step 2: The saved text data is stored in a database.

[1601] Step 3: The user can refer to the database for past conversations as needed.

[1602] "Example 3"

[1603] Step 1: The AI ​​analyzes the accumulated data. Specifically, the AI ​​analyzes the text data in the database and extracts patterns of business know-how.

[1604] Step 2: Generate new business know-how based on the patterns extracted by AI.

[1605] Step 3: The generated business know-how is used to improve business operations. For example, by referencing response patterns when a specific problem occurs, the company can quickly respond if a similar problem occurs.

[1606] Example 1

[1607] 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 headset type terminal 314 will be referred to as a "terminal."

[1608] Conventional internal communication tools have the problem that it takes time to read long text messages, making it difficult to share information efficiently. There was also a need for a system that could accumulate the content of exchanges as business know-how and further utilize that data to improve business operations and generate new know-how.

[1609] 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.

[1610] In this invention, the server includes: means for transmitting text entered by a user from a terminal to the server; means for the server to analyze the received text using a natural language processing library; means for the server to send a prompt sentence to a generative AI model based on the analysis results; means for the generative AI model to generate a summary; means for the server to send the generated summary to the terminal; means for the terminal to display the summary to the user; means for accumulating the content of the exchange as business know-how data; and means for AI to learn from the accumulated data. This allows users to efficiently obtain information without having to read long texts. Furthermore, the accumulated data can be used to improve business operations and generate new business know-how.

[1611] An "internal communication tool" is software that allows for efficient information sharing and communication within a company or organization.

[1612] The "AI summary function" is a function that uses artificial intelligence to summarize long texts in a shorter form.

[1613] The "means for shortening text conversation time" is a means for summarizing long texts entered by a user, allowing the user to grasp the content in a short time.

[1614] The "means for transmitting text entered by a user from a terminal to a server" refers to a means for transmitting text data entered by a user into a terminal to a server via a network.

[1615] The "means for analyzing text received by the server using a natural language processing library" refers to a means for analyzing text data received by the server using a software library for natural language processing.

[1616] "Means for the server to send a prompt sentence to the generative AI model based on the analysis results" refers to means for the server to send a prompt sentence to the generative AI model to request a summary based on the text data analyzed.

[1617] The "means by which the generative AI model generates a summary" is the means by which the generative AI model generates a summary of the text based on the prompt sentence.

[1618] "Means for the server to send the generated summary to the terminal" refers to means for the server to send the summary received from the generative AI model to the user's terminal.

[1619] The "means for the terminal to display the summary to the user" refers to the means for the user's terminal to display the received summary on the screen.

[1620] "Business know-how data" refers to the accumulation of business-related knowledge and experience as data.

[1621] "Means of learning accumulated data using AI" refers to means of having artificial intelligence learn accumulated business know-how data.

[1622] "Means for business improvement" refers to the analysis of accumulated data to improve business efficiency and quality.

[1623] "Means for generating new business know-how" refers to means for creating new business knowledge and methods based on the learning results of AI.

[1624] This invention is a system that incorporates an AI summarization function into an internal communication tool. When users have a text conversation, the AI ​​summarizes the content in real time and displays it to the user, saving them the time of reading long texts and allowing them to obtain information efficiently.

[1625] Hardware and software used

[1626] Hardware:

[1627] server

[1628] Devices (PCs, smartphones, tablets, etc.)

[1629] software:

[1630] Natural language processing libraries (e.g. spaCy)

[1631] Generative AI models (e.g., GPT-4)

[1632] Internal communication tools

[1633] Data processing and calculation

[1634] The user enters text

[1635] A user types text into a chat window in an internal communication tool, for example, "I'd like to discuss the agenda for our next meeting."

[1636] The device sends the text to the server

[1637] The terminal sends the text entered by the user to the server. At this time, the text data is sent as an HTTP request.

[1638] The server receives and parses the text

[1639] The server receives the text sent from the device. The received text is analyzed using a natural language processing library (e.g., spaCy). As a result of the analysis, the context of the text and important keywords are extracted.

[1640] The server sends a prompt to the generative AI model

[1641] The server generates a prompt to send to a generative AI model (e.g., GPT-4) based on the analysis results. For example, it generates a prompt such as, "Please summarize the following text: I would like to discuss the agenda for the next meeting."

[1642] A generative AI model generates a summary

[1643] The generative AI model receives the prompt sent from the server and generates a summary, for example, "I would like to discuss the meeting agenda."

[1644] The server receives the summary and sends it to the device.

[1645] The server receives the summary returned by the generative AI model, which is then sent back to the device as an HTTP response.

[1646] The terminal displays the summary to the user

[1647] The terminal displays the summary received from the server in the user's chat window, thereby saving the user the trouble of reading long texts and enabling them to obtain information efficiently.

[1648] Examples of specific examples and prompts

[1649] For example, if a user types "I'd like to discuss the agenda for our next meeting," the following happens:

[1650] 1. The user enters the text "I'd like to discuss the agenda for our next meeting."

[1651] 2. The device sends this text to the server.

[1652] 3. The server receives the text and uses spaCy to extract keywords such as "meeting," "agenda," and "discussion."

[1653] 4. The server generates a prompt sentence: "Please summarize the following text: I would like to discuss the agenda for the next meeting" and sends it to the generative AI model.

[1654] 5. The generative AI model generates a summary such as "I would like to discuss the meeting agenda."

[1655] 6. The server receives this summary and sends it to the terminal.

[1656] 7. The device displays the summary in the user's chat window.

[1657] In this way, users can obtain information efficiently without having to read long texts. Furthermore, the content of the interactions is accumulated as business know-how data, which can be used to improve business operations and generate new business know-how through AI learning.

[1658] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1659] Step 1:

[1660] The user enters text.

[1661] A user inputs text into a chat window of an internal communication tool. For example, the user inputs "I would like to discuss the agenda for the next meeting." The input text becomes the input data for the next processing step.

[1662] Step 2:

[1663] The device sends the text to the server.

[1664] The terminal sends the text entered by the user to the server as an HTTP request. The input data is the text entered by the user, and the output data is the text data sent to the server.

[1665] Step 3:

[1666] The server receives and parses the text.

[1667] The server receives the text sent from the device. The received text is analyzed using a natural language processing library (e.g., spaCy). As a result of the analysis, the context of the text and important keywords are extracted. The input data is the received text, and the output data is the analysis result.

[1668] Step 4:

[1669] The server sends a prompt to the generative AI model.

[1670] The server generates a prompt sentence to be sent to the generative AI model based on the analysis results. For example, it generates a prompt sentence such as "Please summarize the following text: I would like to discuss the agenda for the next meeting." The generated prompt sentence becomes the input data for the next processing step.

[1671] Step 5:

[1672] A generative AI model generates the summary.

[1673] The generative AI model receives a prompt sent from the server and generates a summary, for example, "I would like to discuss the meeting agenda." The input data is the prompt, and the output data is the generated summary.

[1674] Step 6:

[1675] The server receives the summary and sends it to the terminal.

[1676] The server receives the summary returned from the generative AI model. The received summary is then sent to the terminal as an HTTP response. The input data is the generated summary, and the output data is the summary sent to the terminal.

[1677] Step 7:

[1678] The terminal displays the summary to the user.

[1679] The terminal displays the summary received from the server in the user's chat window, which allows the user to obtain information efficiently without having to read long text. The input data is the summary received from the server, and the output data is the summary displayed to the user.

[1680] (Application example 1)

[1681] 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."

[1682] Conventional internal communication tools often involve long text exchanges, making it difficult for users to efficiently obtain information. Furthermore, in the operation management of autonomous vehicles, there was a lack of a way to efficiently grasp conversations and instructions during operation. This resulted in issues such as operational managers and passengers being unable to quickly obtain important information, resulting in reduced operational efficiency.

[1683] 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.

[1684] In this invention, the server includes: a means for shortening text conversation time using an AI summarization function in an internal communication tool; a means for accumulating the content of the exchange as business know-how data; a means for learning the accumulated data using AI; and, in an autonomous vehicle operation management system, a means for converting conversation into text using speech recognition; a means for summarizing the text using a generative AI model; and a means for converting the summarized text into speech and playing it back. This allows users to save time reading long texts and obtain information efficiently. It also improves the efficiency of communication within autonomous vehicles, enabling smoother operation management.

[1685] An "internal communication tool" is software that allows for efficient information sharing and communication within a company.

[1686] The "AI summary function" is a function that uses artificial intelligence to summarize long texts in a shorter form.

[1687] "Text conversation time-saving methods" are methods that users use to streamline and save time in text-based communication.

[1688] "Business know-how data" refers to the accumulation of business-related knowledge and experience as data.

[1689] "Storage means" refers to the method by which data is stored and made available for later use.

[1690] "Means of learning with AI" refers to a method of using artificial intelligence to analyze accumulated data and learn patterns and knowledge.

[1691] An "autonomous vehicle" is a vehicle that operates autonomously using artificial intelligence and sensor technology.

[1692] A "traffic management system" is a system for monitoring and controlling vehicle operations.

[1693] "Speech recognition" is a technology that converts speech into text.

[1694] A "generative AI model" is an artificial intelligence model trained to perform tasks such as text generation and summarization.

[1695] A "summarization tool" is a method for summarizing a long text in a short form.

[1696] "Means of converting to audio and playing" refers to a method of converting text to audio and playing it through a speaker or the like.

[1697] An embodiment of this invention will be described. First, a system is constructed that shortens text conversation time using an AI summarization function in an internal communication tool. In this system, when users have a text conversation, the AI ​​summarizes the content in real time and displays it to the user. This allows users to save time reading long texts and obtain information efficiently.

[1698] Next, the system includes a means for accumulating the content of interactions as business know-how data. The accumulated data is then learned by AI and used to improve business operations and generate new business know-how.

[1699] Furthermore, this invention has application in a fleet management system for autonomous vehicles, where the fleet management system converts conversations taking place in the vehicle into text using speech recognition, then uses a generative AI model to summarize the text, which is then converted into audio and played back to the driver or passengers.

[1700] Specifically, the server performs the following processes: First, it uses speech recognition technology to convert the conversation in the vehicle into text. For example, the speech recognition software used for this purpose is Google's speech recognition API. Next, it uses a generative AI model (e.g., OpenAI's GPT-3) to summarize the converted text. For this summarization process, it uses the prompt "Please summarize the following text:" Finally, it uses the gTTS (Google Text-to-Speech) library to convert the summarized text into speech and play it back.

[1701] As a concrete example, if a dispatcher in an autonomous vehicle asks, "Where is the next stop?", speech recognition technology converts the question into text, and a generative AI model summarizes it as, "Confirm next stop." The summarized text is then converted into speech and played back to the driver or passengers.

[1702] An example of a prompt is as follows:

[1703] "Summarize the following text: Where is the next stop?"

[1704] In this way, users can obtain information efficiently without having to read long texts, and communication within autonomous vehicles will be made more efficient, enabling smoother operation management.

[1705] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1706] Step 1:

[1707] The server uses voice recognition technology to convert conversations taking place inside the vehicle into text. Specifically, the voice data acquired from the microphone as voice input is sent to Google's voice recognition API, which then outputs it as text data. This process converts the voice data into text data.

[1708] Step 2:

[1709] The server uses a generative AI model to summarize the converted text. Specifically, it sends the text data obtained in step 1 as input to OpenAI's GPT-3 model along with the prompt "Please summarize the following text:" and obtains the summarized text as output. This process results in a short summary of the long text.

[1710] Step 3:

[1711] The server converts the summarized text into audio and plays it back. Specifically, it uses the summarized text obtained in step 2 as input and generates an audio file using the gTTS (Google Text-to-Speech) library, and plays the audio file through a speaker. This process provides the summarized information to the user as audio.

[1712] Step 4:

[1713] The user listens to the audio and obtains the necessary information. Specifically, the operation manager and passengers listen to the audio coming from the speaker and decide on the next course of action. This process allows the user to obtain information efficiently and take appropriate action.

[1714] Example 2

[1715] Next, a description will be given of 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."

[1716] With conventional internal communication tools, it was difficult to efficiently accumulate conversations between users and utilize them as business know-how. Furthermore, the process of converting voice data into text data and saving it in a database was often done manually, preventing business efficiency. Furthermore, there was a lack of a way to effectively learn from the accumulated data and generate new business know-how.

[1717] 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.

[1718] In this invention, the server includes means for capturing conversations between users as voice data, means for converting the captured voice data into text data, and means for storing the converted text data in a database, thereby enabling the conversations between users to be efficiently accumulated and utilized as business know-how.

[1719] "User" refers to an individual or group that uses the system to engage in conversation.

[1720] "Voice data" refers to data that is recorded in digital format using a voice input device such as a microphone to record the contents of a user's conversation.

[1721] "Capture" refers to the process of acquiring and recording audio data in real time.

[1722] "Text data" refers to data obtained by converting voice data into character information.

[1723] "Conversion" refers to the process of turning audio data into text data.

[1724] A "database" refers to a system for systematically storing and managing text data.

[1725] "Business know-how data" refers to knowledge and information about business obtained from the content of conversations between users.

[1726] A "generative AI model" refers to an artificial intelligence model that learns from accumulated data and generates new knowledge and information.

[1727] "Learning" refers to the process by which a generative AI model analyzes accumulated data and extracts patterns and knowledge.

[1728] "Business improvement" refers to the process of using accumulated data and the learning results of generative AI models to improve business efficiency and quality.

[1729] "New business know-how" refers to new knowledge and information obtained from the learning results of the generative AI model.

[1730] The present invention is a system for efficiently storing conversational content between users and utilizing it as business know-how. A specific embodiment of this system will be described below.

[1731] First, the user starts a business conversation. When the user starts the conversation, the device captures the voice data through the microphone. The device has voice capture software (e.g., Audacity) installed. The captured voice data is sent to the server in real time using the HTTP protocol.

[1732] The server converts the received voice data into text data using the Google Cloud Speech-to-Text API. The converted text data is used as business know-how data. The server then saves the converted text data in a MySQL database. When saving, the date and time of the conversation and participant information are also recorded.

[1733] Users can search and refer to past conversations through a dedicated interface, for example, by accessing the database using a web browser. This allows users to easily refer to past conversations, contributing to improved work efficiency.

[1734] For example, suppose user A and user B start talking about the progress of a project. When user A says, "Let's schedule the next meeting for next Tuesday," the device captures this voice data and sends it to the server. The server converts the voice data into text using the Google Cloud Speech-to-Text API, generating the text data, "Let's schedule the next meeting for next Tuesday." This text data is then stored in a MySQL database.

[1735] Examples of prompts to be input to a generative AI model include:

[1736] "User A and User B were talking about the progress of a project. User A said, 'Let's set up the next meeting for next Tuesday.' How can I save this conversation as text data and store it in a database?"

[1737] This system allows users to easily refer to past conversations, contributing to improved work efficiency. Additionally, by using a generative AI model to learn from the accumulated data, it becomes possible to generate new business know-how.

[1738] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1739] Step 1:

[1740] A user initiates a conversation.

[1741] Input: User's voice

[1742] Output: Audio data

[1743] What happens: User A and User B start talking about the progress of a project. User A says, "Let's schedule the next meeting for next Tuesday."

[1744] Step 2:

[1745] The device captures the audio data.

[1746] Input: User's voice

[1747] Output: Digital audio data

[1748] Specific operation: The device captures user A's speech as audio data through the microphone. Audio capture software (e.g., Audacity) records the audio data in real time.

[1749] Step 3:

[1750] The terminal transmits the voice data to the server.

[1751] Input: Digital audio data

[1752] Output: Audio data sent to the server

[1753] How it works: The device sends the recorded audio data to the server using the HTTP protocol, using the Python requests library.

[1754] Step 4:

[1755] The server converts the voice data into text data.

[1756] Input: Audio data sent to the server

[1757] Output: Text data

[1758] What happens next: The server calls the Google Cloud Speech-to-Text API to convert the voice data into text, which then becomes "Let's schedule our next meeting for next Tuesday."

[1759] Step 5:

[1760] The server stores the text data in a database.

[1761] Input: Text data

[1762] Output: Text data stored in a database

[1763] How it works: The server saves the converted text data in a MySQL database, along with the date and time of the conversation and participant information.

[1764] Step 6:

[1765] Users can view past conversations.

[1766] Input: Text data stored in a database

[1767] Output: Text data as search results

[1768] Specific operation: Users open a web browser and access the database through a dedicated interface. User A can easily search and refer to past conversations such as "Let's schedule the next meeting for next Tuesday."

[1769] (Application example 2)

[1770] 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."

[1771] In logistics centers, inefficient communication between staff can lead to delays and mistakes. Furthermore, because past conversations cannot be referenced, the same questions and confirmations are often repeated, resulting in a decline in work efficiency. To solve these issues, a system that can efficiently store and reference the conversations between staff is needed.

[1772] 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.

[1773] In this invention, the server includes means for shortening text conversation time using an AI summarization function in an internal communication tool, means for accumulating the content of the exchange as business know-how data, means for learning the accumulated data using AI, means for saving the content of the conversation as text data using voice recognition technology, means for storing the saved text data in a cloud database, and means for making the saved text data accessible. This improves the efficiency of communication between staff at the logistics center and makes it easy to refer to the content of past conversations.

[1774] "Internal communication tools" are software and platforms that enable efficient information sharing and communication within a company.

[1775] The "AI summary function" is a function that uses artificial intelligence to summarize long texts and conversations in a concise manner.

[1776] "Methods for shortening text conversation time" refers to a method for reducing the time required for text exchange by summarizing the content of the conversation.

[1777] "Business know-how data" refers to the accumulated data of knowledge and experience gained in the course of carrying out business.

[1778] "Means of using AI to learn from accumulated data" refers to a method of having artificial intelligence learn from accumulated business know-how data.

[1779] "Speech recognition technology" is a technology that converts voice into text data.

[1780] "Means for saving as text data" refers to a method for saving text data obtained using speech recognition technology.

[1781] A "cloud database" is a database that is accessible via the Internet.

[1782] "Means for making stored text data accessible" refers to a method for making stored text data easily searchable and accessible later.

[1783] The system for carrying out the present invention is designed to improve the efficiency of communication between staff members at a logistics center. A specific embodiment of this system is described below.

[1784] Hardware and software used

[1785] Hardware: Smartphone, microphone

[1786] Software: Python, SpeechRecognition library, SQLite database, cloud storage service

[1787] System configuration

[1788] 1. Speech recognition technology: An application installed on a smartphone collects staff's speech in real time through a microphone and converts it into text data using the SpeechRecognition library.

[1789] 2. Data storage: The converted text data is temporarily stored on the smartphone, and then stored in a cloud database using a cloud storage service.

[1790] 3. Database Management: The accumulated text data is managed using an SQLite database, which stores the conversation timestamp, user name, and conversation content.

[1791] 4. Data Reference: The accumulated text data is designed to be easily searchable and accessible later. Staff can search for past conversations via their smartphones and use them in their work.

[1792] Processing flow

[1793] 1. Speech Recognition: The employee launches the smartphone application and starts a conversation. The microphone collects the voice and the SpeechRecognition library converts the voice into text.

[1794] 2. Data storage: The converted text data is temporarily stored on the smartphone along with a timestamp and the user name, and then transferred to a cloud database via a cloud storage service.

[1795] 3. Data reference: Staff can use a smartphone application to search and reference past conversations from a database on the cloud.

[1796] Specific examples

[1797] For example, if a staff member at a logistics center asks, "Where is the next delivery destination?", the conversation is saved as text data. Later, when another staff member asks the same question, they can refer to the past conversation and get a quick answer.

[1798] Prompt Sentence Examples

[1799] If you ask the question "Where is the next delivery destination?" the prompt text will be as follows:

[1800] User: Where is my next delivery?

[1801] System: Your conversation has been saved.

[1802] In this way, the operational efficiency of the logistics center can be improved.

[1803] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1804] Step 1:

[1805] The user launches the application on their smartphone and starts a conversation.

[1806] Input: User's voice

[1807] Output: Audio data collected by microphone

[1808] Specific operation: The user launches an application on their smartphone and the microphone collects audio.

[1809] Step 2:

[1810] The terminal uses voice recognition technology to convert the collected voice data into text data.

[1811] Input: Audio data

[1812] Output: Text data

[1813] Specific operation: The device uses the SpeechRecognition library to convert the voice data into text data.

[1814] Step 3:

[1815] The terminal temporarily stores the converted text data.

[1816] Input: Text data

[1817] Output: Temporarily saved text data

[1818] What it does: The device temporarily stores the text data on your smartphone along with a timestamp and your username.

[1819] Step 4:

[1820] The device transfers the temporarily stored text data to a database on the cloud.

[1821] Input: Temporarily saved text data

[1822] Output: Text data stored in a cloud database

[1823] Specific operation: The device uses a cloud storage service to transfer text data to a database on the cloud.

[1824] Step 5:

[1825] The server manages the text data stored in a database on the cloud.

[1826] Input: Text data stored in a cloud database

[1827] Output: Managed text data

[1828] Specific operation: The server uses an SQLite database to manage the accumulated text data.

[1829] Step 6:

[1830] Users use a smartphone application to search and view past conversations from a database on the cloud.

[1831] Input: search query

[1832] Output: Text data as search results

[1833] How it works: A user uses a smartphone application to send a search query to a database in the cloud, and the server returns the relevant text data.

[1834] Example 3

[1835] Next, a third embodiment of the third embodiment 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."

[1836] Conventional internal communication tools tend to require long text conversations, which often hinders efficient work progress. Furthermore, there was a lack of effective ways to utilize accumulated business data, preventing the sharing of business know-how and business improvements. Furthermore, there was no effective method for generating new business know-how based on accumulated data. To solve these issues, a system was needed that could efficiently process and analyze data and effectively generate and share business know-how.

[1837] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1838] In this invention, the server includes means for a user to input business data and send it to the server, means for the server to save the received data in a database, means for the server to retrieve data from the database and preprocess it using a data analysis tool, means for the server to input the preprocessed data into a generative AI model and extract patterns of business know-how, means for the server to generate new business know-how based on the patterns extracted and save it in the database, and means for a user to refer to the generated business know-how through a terminal. This enables efficient data processing and analysis, and enables the effective generation and sharing of business know-how.

[1839] An "internal communication tool" is software that facilitates information sharing and communication within a company.

[1840] "Artificial intelligence" refers to computer systems that mimic human intelligence and can learn and reason.

[1841] The "summarization function" is a function that summarizes long texts in a short form, extracting important information and expressing it concisely.

[1842] "Business know-how data" refers to the accumulated knowledge and experience necessary for carrying out business.

[1843] A "database" is a system for efficiently storing, managing, and searching large amounts of data.

[1844] A "data analysis tool" is software used to analyze data and extract meaningful information.

[1845] A "generative AI model" is an artificial intelligence model that generates new information and patterns based on input data.

[1846] "Pattern extraction" is the process of finding common characteristics and patterns in data.

[1847] "Business know-how" refers to the knowledge and skills required to carry out business efficiently.

[1848] A "terminal" is a device such as a computer or smartphone that is operated by a user.

[1849] MODE FOR CARRYING OUT THE INVENTION

[1850] This invention is a system that shortens text conversation time using an AI summarization function in an internal communication tool, accumulates the content of that exchange as business know-how data, and further uses AI to learn from the accumulated data. This system includes: a means for a user to input business data and send it to a server; a means for the server to store the received data in a database; a means for the server to retrieve data from the database and preprocess it using a data analysis tool; a means for the server to input the preprocessed data into a generative AI model and extract patterns of business know-how; a means for the server to generate new business know-how based on the patterns extracted and store it in a database; and a means for a user to refer to the generated business know-how via a terminal.

[1851] Hardware and software used

[1852] Hardware: Servers, terminals

[1853] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), data analysis tools (e.g., Python's pandas library)

[1854] Explanation of program processing

[1855] 1. Data entry and storage

[1856] The user inputs business data from the terminal, such as details of complaint handling and records of work progress.

[1857] The terminal transmits the input data to the server.

[1858] The server stores the received data in a database, typically using a database management system such as MySQL.

[1859] 2. Data Preprocessing

[1860] The server periodically retrieves the accumulated data from the database.

[1861] The server preprocesses the acquired data using a data analysis tool (e.g., Python's pandas library), specifically cleaning the data (filling in missing values ​​and removing outliers) and standardizing the format.

[1862] 3. Data analysis using AI models

[1863] The server inputs the preprocessed data into a generative AI model (e.g., GPT-4).

[1864] The generative AI model analyzes data and extracts patterns of business know-how, such as patterns for responding to specific problems and communication patterns for efficient business progress.

[1865] 4. Generation of business know-how

[1866] The server generates new business know-how based on the patterns extracted by the generative AI model. For example, it generates specific procedures such as "When a complaint occurs, first apologize to the customer, then check the details of the problem."

[1867] The server stores the generated business know-how in a database.

[1868] 5. Preservation and provision of generated know-how

[1869] The server allows users to refer to new business know-how stored in the database.

[1870] Users can access the database through their terminals and view the generated business know-how.

[1871] Specific examples

[1872] For example, a user inputs "procedures for handling complaints" from a terminal. The terminal sends this data to a server, which stores it in a database. The server periodically retrieves this data and cleans it using the pandas library. The server then inputs the preprocessed data into GPT-4, and the generative AI model extracts patterns for handling complaints. For example, a pattern may be found that "when a complaint occurs, first apologize to the customer, then confirm the details of the problem." Based on this pattern, the server generates a new procedure for handling complaints and stores it in a database. The user can view this new procedure through their terminal and use it in their actual work.

[1873] Prompt Sentence Examples

[1874] An example of a prompt sentence to input to the generative AI model is as follows:

[1875] "Generate effective complaint handling procedures based on past complaint handling data."

[1876] By inputting this prompt sentence into the generative AI model, the model analyzes past data and generates a new procedure for handling complaints. The flow of the identification process in Example 3 will be described with reference to FIG. 15.

[1877] Step 1:

[1878] Data entry and accumulation

[1879] The user inputs business data from the terminal, such as details of complaint handling and records of work progress.

[1880] Input: Business data (e.g., complaint handling details)

[1881] The terminal transmits the input data to the server.

[1882] The server stores the received data in a database, typically using a database management system such as MySQL.

[1883] Output: Business data stored in a database

[1884] Step 2:

[1885] Data Preprocessing

[1886] The server periodically retrieves the accumulated data from the database.

[1887] Input: Business data stored in a database

[1888] The server preprocesses the acquired data using a data analysis tool (e.g., Python's pandas library), specifically cleaning the data (filling in missing values ​​and removing outliers) and standardizing the format.

[1889] Output: Preprocessed data

[1890] Step 3:

[1891] Data analysis using AI models

[1892] The server inputs the preprocessed data into a generative AI model (e.g., GPT-4).

[1893] Input: Preprocessed data

[1894] The generative AI model analyzes data and extracts patterns of business know-how, such as patterns for responding to specific problems and communication patterns for efficient business progress.

[1895] Output: Extracted business know-how patterns

[1896] Step 4:

[1897] Generation of business know-how

[1898] The server generates new business know-how based on the patterns extracted by the generative AI model. For example, it generates specific procedures such as "When a complaint occurs, first apologize to the customer, then check the details of the problem."

[1899] Input: Extracted business know-how patterns

[1900] The server stores the generated business know-how in a database.

[1901] Output: New business know-how stored in the database

[1902] Step 5:

[1903] Preservation and dissemination of generated know-how

[1904] The server allows users to refer to new business know-how stored in the database.

[1905] Input: New business know-how stored in the database

[1906] Users can access the database through their terminals and view the generated business know-how.

[1907] Output: Business know-how that can be viewed by users

[1908] (Application example 3)

[1909] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1910] In conventional factory operations, the collection and analysis of work data was often done manually, making it difficult to carry out work efficiently or respond quickly when problems occurred. In addition, there was a lack of accumulation of work know-how and the creation of new know-how, and improvements in work efficiency were required.

[1911] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for shortening text conversation time using an AI summary function in an in-house communication tool, means for accumulating the content of the exchange as business know-how data, means for AI learning from the accumulated data, means for collecting work data within the factory in real time and analyzing the data with AI, means for learning response patterns when specific problems occur and proposing optimal response methods, means for learning communication patterns for efficient work progress and issuing appropriate instructions to workers, and means for generating new business know-how and improving work efficiency. This makes it possible to efficiently collect and analyze work data within the factory, quickly respond to problems when they occur, and accumulate and generate business know-how.

[1912] An "internal communication tool" is software that allows for efficient information sharing and communication within a company.

[1913] The "AI summary function" is a function that uses artificial intelligence to summarize long pieces of text into shorter sentences.

[1914] "Text conversation time-saving methods" are methods for streamlining text-based communication and saving time.

[1915] "Business know-how data" refers to the accumulated knowledge and experience necessary for carrying out business.

[1916] "Means for AI to learn from accumulated data" refers to a method by which artificial intelligence analyzes and learns from accumulated data.

[1917] "Factory work data" refers to data related to various types of work carried out within a factory.

[1918] "Real-time collection means" refers to a method for collecting data in real time.

[1919] "The means by which the AI ​​analyzes the data" refers to the method by which the artificial intelligence analyzes the collected data.

[1920] The "response pattern when a specific problem occurs" is a pattern of response methods to be taken when a specific problem occurs.

[1921] "Means for proposing the most appropriate response method" is a method for proposing the most appropriate response method when a problem occurs.

[1922] "Communication patterns for efficient business progress" are methods of communication for efficiently progressing business.

[1923] "Means for issuing appropriate instructions to workers" refers to a method for providing appropriate instructions to workers.

[1924] "Means for generating new business know-how" refers to a method for creating new business know-how.

[1925] "Means for improving work efficiency" are methods for increasing work efficiency.

[1926] The system for implementing this invention is configured as follows: First, the server provides a means for shortening text conversation time using an AI summarization function in an internal communication tool, allowing users to communicate more efficiently.

[1927] Next, the server has the means to store the content of these interactions as business know-how data, which will later become an important source of information for the AI ​​to learn from.

[1928] Furthermore, the server provides a means for AI to learn from the accumulated data, allowing the AI ​​to learn patterns for responding to specific problems when they arise and communication patterns for efficient business operations.

[1929] The server also includes a means for collecting data on factory operations in real time, allowing the server to instantly collect data on various operations within the factory and analyze the data using AI.

[1930] The server also includes a means for learning response patterns when specific problems occur and proposing optimal response methods. This means allows the server to propose a quick and appropriate response when a problem occurs.

[1931] The server also includes a means for learning communication patterns for efficient work progress and issuing appropriate instructions to workers. This means enables the server to provide efficient instructions to workers and ensure smooth work progress.

[1932] Finally, the server also includes a means for generating new business know-how and improving work efficiency. This means enables the server to generate new business know-how and improve work efficiency.

[1933] Specifically, the server processes and calculates data using software such as Python, Pandas, Scikit-learn, and Joblib. For example, if a specific machine in a factory breaks down, the AI ​​analyzes the failure data and suggests the optimal repair method based on past data. It can also learn patterns that allow workers to communicate efficiently and issue work instructions.

[1934] An example of a prompt sentence might be:

[1935] "Please suggest the best way to repair machine A when it breaks down in the factory. Based on past data, please tell me the most efficient repair procedure."

[1936] In this way, the server can efficiently collect and analyze work data within the factory, enabling quick responses when problems arise and the accumulation and generation of business know-how.

[1937] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1938] Step 1:

[1939] The server collects users' text conversations through internal communication tools. The input is the user's text conversation, and the output is a summarized text. Specifically, it uses an AI summary function to summarize long texts into shorter ones.

[1940] Step 2:

[1941] The server accumulates the summarized text as business know-how data. The input is the summarized text, and the output is the accumulated business know-how data. Specifically, the text is stored in a database.

[1942] Step 3:

[1943] The server uses AI to learn from the accumulated data. The input is the accumulated business know-how data, and the output is a trained model. Specifically, it analyzes the data and trains the model using Python and Scikit-learn.

[1944] Step 4:

[1945] The server collects work data from within the factory in real time. The input is data from various sensors within the factory, and the output is the collected work data. Specifically, data is collected using IoT devices and sent to the server.

[1946] Step 5:

[1947] The server analyzes the collected work data using AI. The input is the collected work data, and the output is the analysis results. Specifically, the data is preprocessed using Python and Pandas, and then analyzed using Scikit-learn.

[1948] Step 6:

[1949] The server learns response patterns when specific problems occur and proposes the optimal response method. The input is the analysis results, and the output is the optimal response method. Specifically, it extracts response patterns based on past data and generates proposals.

[1950] Step 7:

[1951] The server learns communication patterns for efficient work progress and issues appropriate instructions to workers. The input is the trained model and real-time data, and the output is work instructions. Specifically, the AI ​​generates optimal communication patterns and sends instructions to workers.

[1952] Step 8:

[1953] The server generates new business know-how and improves work efficiency. The input is a trained model and real-time data, and the output is new business know-how. Specifically, the AI ​​generates new know-how and stores it in a database.

[1954] In this way, the server can efficiently collect and analyze work data within the factory, enabling quick responses when problems arise and the accumulation and generation of business know-how.

[1955] Furthermore, 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.

[1956] "Example 1"

[1957] One embodiment of the present invention provides a system including an emotion engine in which an AI recognizes a user's emotions. In this system, when a user has a text conversation using an internal communication tool, the AI ​​summarizes the conversation content in real time. Furthermore, the emotion engine reads emotions from the user's text and adjusts the accuracy of the summary based on the emotions. For example, if the user expresses anger, the emotion engine feeds that information back to the AI, which then reflects that information in generating the summary. This results in a more appropriate summary based on the user's emotions.

[1958] "Example 2"

[1959] Another embodiment of the present invention provides a system in which an emotion engine adjusts the learning of business know-how data based on the user's emotions. In this system, conversations between users are saved as text data, and this data is accumulated as business know-how data. The emotion engine reads the user's emotions and adjusts the AI's learning based on those emotions. For example, if the user expresses joy, the emotion engine feeds that information back to the AI, and the AI ​​reflects that information in the learning of the business know-how data. This generates more appropriate business know-how that corresponds to the user's emotions.

[1960] "Example 3"

[1961] Furthermore, as a further embodiment of the present invention, a system is provided in which an emotion engine presents business know-how to a user that is generated based on the user's emotions. In this system, an AI analyzes accumulated data and extracts patterns of business know-how. The emotion engine reads the user's emotions and presents the user with business know-how that is generated based on those emotions. For example, if the user expresses anxiety, the emotion engine feeds that information back to the AI, and the AI ​​adjusts the presentation of business know-how to the user based on that information. This allows the system to present more appropriate business know-how that is in line with the user's emotions.

[1962] The processing flow of each embodiment will be described below.

[1963] "Example 1"

[1964] Step 1: Users engage in text conversations using internal communication tools.

[1965] Step 2: The AI ​​summarizes the conversation in real time.

[1966] Step 3: The emotion engine reads the emotion from the user's text.

[1967] Step 4: The emotion engine feeds the emotion information back to the AI.

[1968] Step 5: The AI ​​uses that information to adjust the accuracy of the summary.

[1969] "Example 2"

[1970] Step 1: The contents of conversations between users are saved as text data, and that data is used for business purposes.

[1971] It is accumulated as know-how data.

[1972] Step 2: The emotion engine reads the user's emotions.

[1973] Step 3: The emotion engine feeds the emotion information back to the AI.

[1974] Step 4: The AI ​​reflects this information and adjusts its learning of the business know-how data.

[1975] "Example 3"

[1976] Step 1: AI analyzes the accumulated data and extracts patterns of business know-how.

[1977] Step 2: The emotion engine reads the user's emotions.

[1978] Step 3: The emotion engine feeds the emotion information back to the AI.

[1979] Step 4: The AI ​​uses this information to adjust the presentation of business know-how to the user.

[1980] Example 1

[1981] 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 headset type terminal 314 will be referred to as a "terminal."

[1982] In-house communication tools are required to efficiently summarize long text messages so that users can quickly obtain information. Another challenge is to improve the quality of communication by providing summaries that take the user's emotions into account. Furthermore, it is also important to accumulate the content of these exchanges as business know-how and use it to improve business operations.

[1983] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodim...

Claims

1. A means of shortening text conversation time using an AI summary function in an internal communication tool; and A means to accumulate the contents of internal communications as business know-how data, A means for learning the accumulated data using AI; A means for storing the data received by the server in a database; means for retrieving said data from said database and pre-processing said data using a data analysis tool; A means for inputting the preprocessed data into a generative AI model to extract patterns of the business know-how; A means for generating new business know-how based on the extracted patterns and storing the generated know-how in the database; A means for allowing a user to refer to the generated business know-how through a terminal; A system including:

2. A means of shortening text conversation time using an AI summary function in an internal communication tool; and A means to accumulate the contents of internal communications as business know-how data, A means for learning the accumulated data using AI; A means for collecting work data in a factory in real time and analyzing the work data by an AI; A means for learning response patterns when a specific problem occurs in the factory and proposing an optimal response method; A means for learning a communication pattern for efficient business progress and issuing instructions to workers in the factory; A system including: a means for generating new work know-how for the worker.

3. A means of shortening text conversation time using an AI summary function in an internal communication tool; and A means to accumulate the contents of internal communications as business know-how data, A means for learning the accumulated data using AI; A means of analyzing user sentiment; A means for generating business know-how based on the user's emotions; and a means for presenting the generated business know-how to a user.

Images