System

Abstract

To provide a system for enabling a person in charge of business to easily grasp a business flow and to advance effective business reform.SOLUTION: The system includes a means for a user to orally explain a business flow, a means for a terminal to collect the user's explanation as voice data, a means for a server to convert the voice data into text data by voice recognition AI, a means for the server to analyze the text data to generate an initial flowchart, a means for the terminal to display the initial flowchart, a means for the user to additionally explain a branch or a lacking part, a means for the terminal to collect the additional explanation as voice data and transmit the voice data to the server again, a means for the server to convert the additional voice data into text data to correct the flowchart, a means for the server to generate a problem and a solution based on past business reform project data, a means for the server to create a slide material based on the flowchart, the problem, and the solution, a means for the terminal to provide the slide material to a user, and a means for the terminal to provide the slide material to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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] As business processes and systems in local governments and private companies continue to age, paper-based processes and unnecessary stamping are causing significant declines in operational efficiency, particularly in local governments. Private companies are also increasingly using legacy systems, resulting in insufficient operational efficiency. Business Process Reform (BPR) is needed to resolve these issues. However, in many cases, it is unclear how to bring business process reform in-house, and people are unsure how to proceed. In these circumstances, a system is needed that allows business personnel to easily understand business processes and promote effective business reform. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides a method for efficiently and effectively visualizing business flows and automating the discovery of problems and the presentation of solutions using a system including: means for a user to orally explain a business flow; means for a terminal to collect the user's explanation as voice data; means for a server to convert the voice data into text data using voice recognition AI; means for the server to analyze the text data and generate an initial flow diagram; means for the terminal to display the initial flow diagram; means for the user to add explanations of branches and missing parts; means for the terminal to collect the additional explanation as voice data and send it again to the server; means for the server to convert the additional voice data into text data and modify the flow diagram; means for the server to generate issues and solutions based on data on past business reform projects; means for the server to create slide materials containing the generated flow diagrams, issues, and solutions; means for the server to generate videos based on the slide materials; and means for the terminal to provide the videos to the user.

[0006] "User" refers to the person in charge of operations who uses the system to explain and modify the business flow.

[0007] "Terminal" refers to a device that collects the user's voice and communicates with the server.

[0008] "Server" refers to a computer system that processes voice data, generates flow diagrams, and performs data analysis.

[0009] "Voice data" refers to sound data collected when a user verbally explains a business flow.

[0010] "Voice recognition AI" refers to artificial intelligence that analyzes voice data and converts it into text data.

[0011] "Text data" refers to text data generated from voice data by voice recognition AI.

[0012] An "initial flow diagram" refers to the first visualization of a business process generated based on text data.

[0013] A "branch" refers to a point in a business flow where options arise.

[0014] The "missing part" refers to the business process element that is missing from the initial flow diagram.

[0015] "Additional explanation" refers to an explanation that the user verbally provides to supplement the branches and missing parts of the initial flow diagram.

[0016] "Issues" refer to problems in the current business flow or areas that need improvement.

[0017] A "solution" refers to a specific means or method for solving a problem.

[0018] "Slide materials" refers to presentation materials that summarize business flow diagrams, issues, and solutions.

[0019] "Video" refers to media content that explains business reforms using visual and audio generated from slide presentations. [Brief explanation of the drawings]

[0020] [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. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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, a 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), and an APU (Accelerated Processing Unit).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. 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."

[0041] This invention relates to a system in which a user verbally explains a workflow, a voice recognition AI converts the explanation into text data, and then analyzes it to generate and modify a workflow diagram, presenting business issues and improvement measures. This system is composed of a user, a terminal, and a server.

[0042] Initial Setup

[0043] First, as an initial setup of the system, the user accesses a terminal (e.g., a PC or smartphone) and launches an interface to begin explaining the business flow. This assumes that the terminal has a microphone for voice input.

[0044] Workflow explanation and voice recognition

[0045] The user verbally explains the workflow into the device's microphone. For example, the user might say, "First, submit the application form at the reception desk, and then enter the data for confirmation." This voice data is collected by the device and sent to the server.

[0046] The server receives the voice data and converts it into text using speech recognition AI, for example, "First, submit your application form at the reception desk, then enter the data for confirmation."

[0047] Initial generation of flow diagram

[0048] The server generates an initial version of the workflow diagram based on the text data. For example, the server automatically generates a workflow diagram in the format of "Reception -> Application Submission -> Data Entry." This initial workflow diagram is sent from the server to the terminal, which displays it to the user.

[0049] Modifying the flow diagram

[0050] The user checks the initial flow diagram and adds or modifies it as necessary. For example, the user may add an explanation such as, "After entering the data, I will decide whether to approve or reject it once the confirmation process is complete." This explanation is also collected by the device's microphone and sent to the server.

[0051] The server converts the additional voice data into text and adds branches and missing parts to the original flow diagram. This completes the flow diagram, for example, "Data entry -> Confirmation work -> (Approval or rejection)." The corrected flow diagram is then sent back to the terminal from the server and displayed to the user.

[0052] Presenting the problem and solution

[0053] The server uses a generative AI model to generate issues and improvement measures based on data from past business reform projects. For example, the server generates an improvement suggestion such as "data entry can be automated," and the terminal displays this suggestion to the user.

[0054] Creating slide decks and videos

[0055] The server creates slide decks based on the generated workflow diagrams, problems, and solutions. These slide decks are created using Microsoft tools and sent to the terminal, which displays them to the user.

[0056] Finally, the server generates a video based on the slides. This video includes an explanation of the business flow, the challenges, and solutions. The generated video is sent to the terminal and provided to the user.

[0057] Specific examples

[0058] For example, if the user explains, "First, submit the application form at the reception desk, then enter the data for confirmation. After entering the data, once the confirmation process is complete, we will make a decision to approve or reject the application," the flow would be as follows:

[0059] 1. The user gives an explanation into the device's microphone.

[0060] 2. The device collects the voice data and sends it to the server.

[0061] 3. The server uses voice recognition AI to convert the voice data into text.

[0062] 4. The server generates the initial flow diagram "Reception -> Application submission -> Data entry" and the terminal displays it.

[0063] 5. The user provides additional explanation and adds a branch of "Data entry -> Confirmation -> (Approve or Reject)".

[0064] 6. The server modifies the flow diagram, and the terminal displays the modified flow diagram.

[0065] 7. The server generates problems and solutions based on past data, and the device displays them.

[0066] 8. The server creates the slides and the terminal displays them.

[0067] 9. Finally, the server generates the video and the device provides it to the user.

[0068] The above is a specific description of the embodiment for carrying out the present invention.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] The user speaks into the device's microphone to explain the work flow verbally. For example, they might explain, "First, submit the application form at the reception desk, and then enter the data for confirmation."

[0072] Step 2:

[0073] The terminal collects the user's explanation as voice data and transmits the voice data to the server.

[0074] Step 3:

[0075] The server receives the voice data, passes it to a voice recognition AI, and converts it into text data. For example, it converts it into text such as, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[0076] Step 4:

[0077] The server analyzes the text data and generates an initial version of the workflow diagram. For example, it generates an initial workflow diagram called "Reception -> Application Submission -> Data Entry."

[0078] Step 5:

[0079] The server sends the generated initial flow diagram to the terminal, which displays it to the user.

[0080] Step 6:

[0081] The user checks the initial flow diagram and adds explanations of branches and missing parts. For example, "After data entry, once the confirmation work is completed, a decision will be made on whether to approve or reject."

[0082] Step 7:

[0083] The terminal collects the user's additional explanation as voice data and transmits it again to the server.

[0084] Step 8:

[0085] The server passes the additional voice data to a voice recognition AI, converts it into text data, and adds branches or missing parts to the original flow diagram. For example, it generates a revised flow diagram such as "Data entry -> Confirmation work -> (Approval or rejection)."

[0086] Step 9:

[0087] The server sends the modified flow diagram to the terminal, which displays it to the user.

[0088] Step 10:

[0089] The server uses the generated AI model to generate issues and improvement measures based on data from past business reform projects. For example, it generates an improvement suggestion that "data entry can be automated."

[0090] Step 11:

[0091] The server sends the generated issues and solutions to the terminal, which then displays them to the user.

[0092] Step 12:

[0093] The server creates slide decks using Microsoft tools based on the generated business flow diagrams, issues, and solutions.

[0094] Step 13:

[0095] The server transmits the created slide material to the terminal, which then displays the slide material to the user.

[0096] Step 14:

[0097] The server generates a video based on the slides.

[0098] Step 15:

[0099] The server transmits the generated video to the terminal, which then provides the video to the user.

[0100] Example 1

[0101] Next, a description will be given of 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."

[0102] Conventional methods for creating business flowcharts require time and effort to collect and record business procedures, making it difficult to do so efficiently. Furthermore, when reflecting changes or improvements to procedures, it is often necessary to recreate them from scratch, which is also inefficient. Furthermore, there is also the problem that it is difficult to effectively utilize past data when identifying issues or proposing improvements.

[0103] 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.

[0104] In this invention, the server includes means for converting voice data into text data using acoustic analysis artificial intelligence, means for analyzing the text data to generate an initial procedure diagram, and means for creating an electronic document containing the generated procedure diagram, problems, and solutions. This makes it possible to efficiently generate a flowchart using only an oral explanation of the business procedure, and to quickly identify and propose problems and improvements.

[0105] "User" refers to a person who verbally explains business procedures.

[0106] "Terminal" refers to an electronic device for collecting voice data and displaying information to a user.

[0107] "Acoustic analysis artificial intelligence" refers to an intelligent system that uses technology to convert voice data into text data.

[0108] "Text data" refers to character information converted from audio data.

[0109] "Initial procedure diagram" refers to the first version of the business flow generated by analyzing text data.

[0110] A "procedure diagram" is a diagram that visually represents each step of a task.

[0111] "Branch" refers to an element in a procedure diagram that indicates multiple options or directions of progression.

[0112] "Missing parts" refer to elements or information that need to be added to the procedure diagram.

[0113] "Past work reform case data" refers to records and information relating to work reforms that have been implemented in the past.

[0114] "Issues" refer to problems in current business procedures that need improvement.

[0115] "Solution" refers to the improvement measures or methods proposed for a problem.

[0116] "Electronic document" refers to materials or reports created in digital format.

[0117] "Video" refers to materials in digital format that contain both audio and video.

[0118] This invention relates to a system in which a user verbally explains a business procedure, and an acoustic analysis AI converts the explanation into text data, which is then analyzed to generate and modify a business flow diagram, and presents business issues and improvement measures. This system is composed of a user, a terminal, and a server.

[0119] First, the user accesses a device such as a PC or smartphone and launches an interface to begin explaining the business flow. The device must have a microphone for voice input.

[0120] The user verbally explains the workflow into the device's microphone. For example, the user might say, "First, submit the application form at the reception desk, and then enter the data for confirmation." This voice data is collected by the device and sent to the server.

[0121] The server receives the voice data and converts it into text data using acoustic analysis artificial intelligence (e.g., a voice recognition algorithm), for example, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[0122] The server generates an initial version of the workflow diagram based on the text data. For example, the server automatically generates a workflow diagram in the format of "Reception -> Application Submission -> Data Entry." This initial workflow diagram is sent from the server to the terminal, which displays it to the user.

[0123] The user checks the initial flow diagram and adds or modifies it as necessary. For example, the user may add an explanation such as, "After entering the data, I will decide whether to approve or reject it once the confirmation process is complete." This explanation is also collected by the device's microphone and sent to the server.

[0124] The server converts the additional voice data into text and adds branches and missing parts to the original flow diagram. This completes the flow diagram, for example, "Data entry -> Confirmation work -> (Approval or rejection)." The corrected flow diagram is then sent back to the terminal from the server and displayed to the user.

[0125] The server uses a generative AI model (such as an advanced natural language processing model) to generate issues and improvement measures based on data from past business reform projects. For example, the server generates an improvement proposal such as "data entry can be automated," and the terminal displays this proposal to the user.

[0126] Finally, the server creates an electronic document based on the generated business flow diagram, problems, and solutions. This electronic document is created using a general presentation tool and sent to the terminal, where it is displayed to the user.

[0127] Finally, the server generates a video based on the electronic document. This video includes an explanation of the business flow, the challenges, and solutions. The generated video is sent to the terminal and provided to the user.

[0128] As a concrete example, the following prompt sentence is input to the generative AI model:

[0129] User workflow description:

[0130] "First, you submit an application form at the reception desk, and then the data is entered for verification. After the data is entered and the verification process is completed, a decision is made as to whether the application will be approved or rejected."

[0131] Based on this workflow, please create an initial workflow diagram, present the issues and solutions, and also create an electronic document and video.

[0132] In this manner, the present invention enables a user to quickly and efficiently generate a business flow chart, identify problems, and propose improvements simply by verbally explaining the business procedures.

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] Step 1:

[0135] The user launches the terminal interface.

[0136] Input: User initiated interface action.

[0137] How it works: The user launches an interface to begin explaining the business flow from an application or web browser on a device such as a PC or smartphone.

[0138] Output: The interface is displayed on the terminal.

[0139] Step 2:

[0140] The user verbally explains the business flow.

[0141] Input: User's voice.

[0142] Operation: The user verbally explains the workflow steps into the device's microphone. For example, "First, submit the application form at the reception desk, and then enter the data for confirmation."

[0143] Output: The device collects the audio data of the explanation.

[0144] Step 3:

[0145] The terminal transmits the voice data to the server.

[0146] Input: Audio data.

[0147] Operation: The device sends the collected voice data to the server. Before sending, the data is reformatted and transferred to the server via the network.

[0148] Output: The audio data arrives at the server.

[0149] Step 4:

[0150] The server converts the voice data into text data.

[0151] Input: Audio data.

[0152] How it works: The server uses acoustic analysis artificial intelligence (voice recognition AI) to convert the received voice data into text data. For example, it generates text data such as "First, submit the application form at the reception desk, then enter the data for confirmation."

[0153] Output: Text data.

[0154] Step 5:

[0155] The server analyzes the text data and generates an initial procedure diagram.

[0156] Input: Text data.

[0157] Operation: The server analyzes the text data and extracts each step of the process for each sentence. Based on the extracted steps, it generates an initial version of the workflow diagram. For example, it creates a flow diagram called "Reception -> Application Submission -> Data Entry."

[0158] Output: Initial procedure diagram.

[0159] Step 6:

[0160] The server sends the initial procedure diagram to the terminal, which displays it.

[0161] Input: Initial procedure diagram.

[0162] Operation: The server sends the generated initial procedure diagram to the terminal, which then displays the received procedure diagram to the user.

[0163] Output: User confirms initial procedure diagram.

[0164] Step 7:

[0165] The user provides additional explanations for the initial procedure diagram.

[0166] Input: Initial procedure diagram, additional user explanation voice.

[0167] Action: The user reviews the initial procedure diagram and provides additional information or corrections as needed. For example, they might explain, "After data entry, we will make a decision on whether to approve or reject the request once the review process is complete." The device collects this additional voice data.

[0168] Output: Collected audio data.

[0169] Step 8:

[0170] The terminal transmits the audio data of the additional explanation to the server.

[0171] Input: Additional audio data.

[0172] Operation: The device sends the collected additional voice data to the server. Before sending, the data is reformatted and transferred to the server via the network.

[0173] Output: Additional audio data arrives at the server.

[0174] Step 9:

[0175] The server converts the additional voice data into text data and corrects the procedure diagram.

[0176] Input: Additional audio data.

[0177] How it works: The server uses acoustic analysis AI to convert the additional voice data into text data. It then adds branches and missing parts to the existing flow diagram and modifies the procedure diagram. For example, it generates a final flow diagram that looks like "Data entry -> Confirmation work -> (Approval or rejection)."

[0178] Output: Revised procedure diagram.

[0179] Step 10:

[0180] The server transmits the correction procedure diagram to the terminal, which displays it.

[0181] Input: Correction procedure diagram.

[0182] Operation: The server sends the modified procedure diagram to the terminal, which displays the received procedure diagram to the user.

[0183] Output: The user checks the correction procedure diagram.

[0184] Step 11:

[0185] The server generates problems and solutions.

[0186] Input: Correction procedure diagram, past work reform case data.

[0187] How it works: The server uses the generative AI model to generate issues and solutions based on past work reform project data. For example, it generates improvement proposals such as "Data entry can be automated."

[0188] Output: Challenges and solutions.

[0189] Step 12:

[0190] The server sends the problem and solution to the terminal, which displays it.

[0191] Input: Challenges and solutions.

[0192] Operation: The server sends the generated problem and solution to the terminal, which displays it to the user.

[0193] Output: User sees the problem and solution.

[0194] Step 13:

[0195] The server creates the electronic document.

[0196] Input: Procedure diagram, problem, solution.

[0197] Operation: The server creates an electronic document based on the generated procedure diagram, problem, and solution. This electronic document is created using a common presentation tool.

[0198] Output: Electronic document.

[0199] Step 14:

[0200] The server transmits the electronic document to the terminal, which displays it.

[0201] Input: Electronic document.

[0202] Operation: The server sends the completed electronic document to the terminal, which displays it to the user.

[0203] Output: The user reviews the electronic document.

[0204] Step 15:

[0205] The server generates the video.

[0206] Input: Electronic document.

[0207] How it works: The server generates a video based on the electronic document, which includes an explanation of the business process, the problem, and the solution.

[0208] Output: Video.

[0209] Step 16:

[0210] The server sends the video to the terminal and provides it to the user.

[0211] Input: Video.

[0212] Operation: The server sends the generated video to the device, which then provides it to the user, who then watches the video.

[0213] Output: User watches a video.

[0214] (Application example 1)

[0215] Next, a description will be given of Application 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."

[0216] Managing workflows at logistics centers is complex, and presenting clear workflows and improvement measures is essential for on-site workers to work efficiently and accurately. However, existing systems do not automatically generate workflows using voice input or suggest improvements in real time, which places a heavy burden on workers and reduces work efficiency. Given this background, there is a need for a system that can quickly generate workflow diagrams using voice input and present improvement measures in real time.

[0217] 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.

[0218] In this invention, the server includes a means for a user to verbally explain a workflow, a means for a terminal to collect the user's explanation as voice data, a means for the server to convert the voice data into text data using voice recognition AI, a means for linking with a voice input function installed in a smart device, a means for displaying a workflow diagram on the smart device in real time, and a means for presenting improvement measures to a worker using the smart device. This allows a worker to simply explain a workflow through voice input, which is visualized in real time and immediately presented with improvement measures.

[0219] A "user" is a person who uses the system to explain and modify business processes.

[0220] A "terminal" is a device (such as a PC or smart device) that collects voice data, displays flow diagrams, and interfaces with the user.

[0221] A "server" is a computer system that performs a wide range of data processing, including converting and analyzing audio data, creating and modifying flow charts, presenting problems and solutions, and even creating slides and videos.

[0222] "Voice recognition AI" is an artificial intelligence technology that converts input voice data into text data.

[0223] "Text data" is character information obtained by converting voice data.

[0224] The "initial flow diagram" is the first version of the business flow generated by the server based on the voice description.

[0225] "Additional explanation" refers to the user verbally explaining further details or branches to the initial flow diagram.

[0226] "Past business process reform case data" refers to a data set of previously collected and analyzed business processes, and serves as reference material for generating issues and solutions.

[0227] "Issues" refer to problems in the current business flow or areas that need improvement.

[0228] "Solutions" refer to specific proposals and measures to resolve issues and improve business flow.

[0229] A "slide deck" is a presentation-style document that summarizes business flow diagrams, issues, solutions, etc.

[0230] "Video" refers to visual and audio content generated based on slide materials.

[0231] A "smart device" is a device (e.g., smart glasses, smartphone, etc.) that allows a user to verbally explain a business process and display a business process diagram and improvement measures on the screen in real time.

[0232] The "voice input function" is a function that allows a smart device to collect the user's voice and pass it on to the system.

[0233] "Real-time display" refers to the function of instantly processing user operations and explanations and displaying the results immediately.

[0234] A "worker" is a person who performs work at a logistics center.

[0235] This invention provides a system for streamlining workflow management in logistics centers. A user verbally explains the workflow, and a voice recognition AI analyzes the explanation, automatically generates and modifies a workflow diagram, and suggests issues and improvements.

[0236] First, the user puts on a smart device (e.g., smart glasses or a smartphone) and verbally explains the workflow. This explanation is collected as voice data through the smart device's microphone. The collected voice data is then sent directly to the server.

[0237] When the server receives the voice data, it converts it into text data using a speech recognition AI. This speech recognition AI can be, for example, the Google Cloud Speech-to-Text API. The converted text data is analyzed by a generative AI model for workflow analysis, and an initial workflow diagram is generated. An example of this generative AI model is the OpenAI API.

[0238] The generated initial flow diagram is sent from the server to the smart device and displayed to the user. The user checks the flow diagram and provides additional explanations by voice if necessary. The additional explanations are also collected through the smart device's microphone and sent to the server. The server converts the additional voice data into text data and corrects the flow diagram.

[0239] Furthermore, the server uses a generative AI model based on data from past business reform projects to propose issues and improvement measures. The proposed issues and improvement measures are displayed in real time on the smart device screen, allowing users to quickly implement countermeasures on-site.

[0240] Based on the generated business flow diagram and improvement measures, the server automatically creates slides. These slides are generated using, for example, the Python-pptx library. Finally, the server converts the slides into video format and generates a video using the MoviePy library. This video is then sent to the smart device and provided to the user.

[0241] As a concrete example, consider a situation where a user verbally explains, "First, we accept the cargo at the reception desk, then we sort it in the warehouse and prepare it for delivery." This system collects the voice data of the explanation and automatically generates a flow diagram such as "Reception -> Cargo Reception -> Sorting -> Delivery Preparation." The generative AI model then proposes "the issue of improving the efficiency of sorting is a problem, and an improvement plan to automate it."

[0242] An example of a prompt is:

[0243] Flowchart generation prompt:

[0244] "Translate the following workflow into a flow diagram: First, cargo is received at the reception desk, then it is sorted in the warehouse and prepared for delivery."

[0245] This system uses smart glasses or a smartphone to smoothly carry out the entire process from explaining the work flow to visualizing it and presenting improvement measures, significantly improving work efficiency at logistics centers.

[0246] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0247] Step 1:

[0248] The user verbally explains the workflow. The user verbally explains the workflow into the microphone on the smart device (smart glasses or smartphone). For example, the user might explain, "First, the cargo is received at the reception desk, then it is sorted in the warehouse and prepared for delivery."

[0249] Step 2:

[0250] The terminal collects the user's explanation as voice data. The terminal uses the smart device's microphone to collect the voice data in real time and transmits the voice data as is to the server. The output includes the collected voice data.

[0251] Step 3:

[0252] The server converts the voice data into text data using a voice recognition AI. The server then inputs the received voice data into a voice recognition AI such as Google Cloud Speech-to-Text API, and obtains text data as output, which is the voice converted into a string of characters. The converted text data then proceeds to the next analysis step.

[0253] Step 4:

[0254] The server analyzes the text data and generates an initial flow diagram. The server uses OpenAI's generative AI model to generate a flow diagram by inputting a prompt. Specifically, by inputting "Convert the following business flow into a flow diagram: text data," the server outputs an initial flow diagram such as "Reception -> Cargo Reception -> Sorting -> Delivery Preparation."

[0255] Step 5:

[0256] The terminal displays the initial flow diagram. The generated initial flow diagram is sent from the server to the smart device and displayed on the terminal display in real time, allowing the user to visually check the flow diagram.

[0257] Step 6:

[0258] The user provides additional explanations about branches and missing parts. While looking at the initial flow diagram, the user provides additional explanations (e.g., "After data entry, once confirmation work is completed, a decision will be made on whether to approve or reject the request.") by voice.

[0259] Step 7:

[0260] The terminal collects the additional explanation as voice data and transmits it again to the server. The microphone of the terminal collects the additional explanation and transmits it again to the server as voice data. The collected additional voice data is output.

[0261] Step 8:

[0262] The server converts the additional voice data into text data and modifies the flow diagram. The server again converts the additional voice data into text data using the Google Cloud Speech-to-Text API, and uses OpenAI's generative AI model to add branches and missing parts to the flow diagram and modify it.

[0263] Step 9:

[0264] The server generates issues and solutions based on data from past business reform projects. The server references past data sets and uses a generative AI model to automatically generate issues in business flows and their solutions.

[0265] Step 10:

[0266] The flow diagram, problems, and solutions generated by the server are compiled into slides. The server uses the python-pptx library to compile the flow diagram, problems, and solutions into slide-format materials.

[0267] Step 11:

[0268] The server generates a video based on the slides. The server uses the moviepy library to convert the slides into a video, creating a video that conveys the content visually and audibly.

[0269] Step 12:

[0270] The terminal provides the video to the user. The generated video is sent from the server to the smart device and provided in a format that the user can easily view.

[0271] 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.

[0272] This invention combines a system in which a user verbally explains a business process, a voice recognition AI converts the explanation into text data, analyzes it, generates and modifies a business process diagram, and presents business issues and improvement measures, with an emotion engine that recognizes the user's emotions. This system consists of a user, a terminal, a server, and an emotion engine.

[0273] Initial Setup

[0274] First, as an initial setup of the system, the user accesses a terminal (e.g., a PC or smartphone) and launches an interface to begin explaining the business flow. This assumes that the terminal has a microphone for voice input.

[0275] Workflow explanation and voice recognition

[0276] The user verbally explains the workflow into the device's microphone. For example, the user might say, "First, I submit the application form at the reception desk, and then I enter the data for confirmation." This voice data is collected by the device and sent to the server. At the same time, the emotion engine runs, analyzing the user's emotions in real time.

[0277] Collecting Emotional Data

[0278] When the device collects voice data, the emotion engine analyzes the user's emotional state and generates emotion data. For example, if the user is feeling stressed, the emotion data is collected as additional information.

[0279] Conversion to text data and initial generation of flow diagrams

[0280] The server receives the voice data and converts it into text using speech recognition AI. For example, it could be converted into text that says, "First, submit your application form at the reception desk, then enter the data for confirmation."

[0281] The server generates an initial version of the workflow diagram based on the text data. For example, it generates an initial workflow diagram called "Reception -> Application Submission -> Data Entry." This initial workflow diagram is sent from the server to the terminal, which displays it to the user.

[0282] Flowchart revision and emotional feedback

[0283] The user checks the initial flow diagram and adds or modifies it as necessary. For example, they might add, "After data entry, we will make a decision on whether to approve or reject the request once the review process is complete." This additional explanation is also collected by the device's microphone and sent to the server.

[0284] The server converts the additional voice data into text and adds branches and missing parts to the original flow diagram. This completes the flow diagram, for example, "Data Entry -> Confirmation -> (Approval or Rejection)." At the same time, it adjusts the revised flow diagram to avoid stress for the user, taking into account the emotional data generated by the emotion engine.

[0285] Presenting the problem and solution

[0286] The server uses a generative AI model to generate issues and improvement measures based on data from past business reform projects. For example, the server generates an improvement suggestion such as "data entry can be automated," and the terminal displays this suggestion to the user.

[0287] Furthermore, based on the emotional data, we propose solutions that take into account the user's emotional state, for example, by proposing automation of processes that tend to cause stress to the user.

[0288] Creating slides and videos

[0289] The server creates slide decks based on the generated workflow diagrams, problems, and solutions. These slide decks are created using Microsoft tools and sent to the terminal, which displays them to the user.

[0290] Finally, the server generates a video based on the slides. This video includes an explanation of the business flow, the challenges, and solutions. The generated video is sent to the terminal and provided to the user.

[0291] Specific examples

[0292] For example, if the user explains, "First, submit the application form at the reception desk, then enter the data for confirmation. After entering the data, once the confirmation process is complete, we will make a decision to approve or reject the application," the flow would be as follows:

[0293] 1. The user gives an explanation into the device's microphone.

[0294] 2. The device collects the voice data and sends it to the server. At the same time, the emotion engine analyzes the user's emotions and recognizes that they are feeling stressed.

[0295] 3. The server uses voice recognition AI to convert the voice data into text.

[0296] 4. The server generates the initial flow diagram "Reception -> Application submission -> Data entry" and the terminal displays it.

[0297] 5. The user provides additional explanation and adds a branch of "Data entry -> Confirmation -> (Approve or Reject)".

[0298] 6. The server modifies the flow chart and suggests a less stressful work sequence based on the emotion data. The modified flow chart is then displayed on the device.

[0299] 7. The server generates problems and solutions based on past data, and the device displays them.

[0300] 8. The server creates the slides and the terminal displays them.

[0301] 9. Finally, the server generates the video and the device provides it to the user.

[0302] The above is a specific description of the embodiment of the present invention. By combining an emotion engine, it is possible to advance business reform while taking into consideration the emotional state of the user.

[0303] The processing flow will be explained below.

[0304] Step 1:

[0305] The user speaks into the device's microphone to explain the work flow verbally. For example, they might explain, "First, submit the application form at the reception desk, and then enter the data for confirmation."

[0306] Step 2:

[0307] The device collects the user's explanation as voice data and sends it to the server. At the same time, the emotion engine analyzes the user's emotions in real time and generates emotion data.

[0308] Step 3:

[0309] The server receives the voice data, passes it to a speech recognition AI, and converts it into text data. For example, it converts it into text such as, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[0310] Step 4:

[0311] The server analyzes the text data and generates an initial version of a workflow diagram. For example, it generates an initial workflow diagram called "Reception -> Application Submission -> Data Entry." It then sends this workflow diagram to the terminal, which displays it to the user.

[0312] Step 5:

[0313] The user checks the initial flow diagram and adds explanations of branches and missing parts as necessary. For example, they might add, "After data entry and confirmation, a decision will be made on whether to approve or reject the request." At the same time, the emotion engine continues to evaluate the user's emotions.

[0314] Step 6:

[0315] The terminal collects the user's additional explanation as voice data and transmits it again to the server.

[0316] Step 7:

[0317] The server passes the additional voice data to a voice recognition AI, converts it into text data, and adds branches or missing parts to the original flow diagram. For example, it generates a revised flow diagram such as "Data entry -> Confirmation work -> (Approval or rejection)."

[0318] Step 8:

[0319] The server sends the modified flow diagram to the terminal, which displays it to the user. At this time, the emotion engine provides an optimal flow diagram that is adjusted based on the emotional data analyzed to prevent the user from feeling stressed.

[0320] Step 9:

[0321] The server uses the generated AI model to generate issues and improvement measures based on data from past business reform projects. For example, the server may generate an improvement suggestion such as "data entry can be automated." Furthermore, it proposes solutions to issues that take into account the user's emotional state based on emotion data.

[0322] Step 10:

[0323] The server sends the generated issues and improvement measures to the device, which then displays them to the user. For example, the device may suggest, "By promoting automation of data entry, we can reduce stress."

[0324] Step 11:

[0325] The server uses Microsoft tools to create slides based on the generated workflow diagram, issues, and solutions, and then sends the slides to the terminal, which displays them to the user.

[0326] Step 12:

[0327] The server generates a video based on the slides. The generated video is sent to the terminal, which then provides it to the user. For example, a video containing an explanation of a business process, problems, and solutions is provided.

[0328] The above are the specific processing steps for implementing the invention in combination with the emotion engine. By utilizing emotion data, it is possible to advance business reform while taking into account the user's emotional state.

[0329] Example 2

[0330] Next, a description will be given of 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."

[0331] The main function of conventional workflow creation systems is to convert a user's verbal explanation into text data and generate a workflow diagram. However, if workflows or solutions to problems are proposed without taking the user's emotional state into consideration, the user may feel stressed or the workflow may not be applicable in the actual workplace. Furthermore, proposals for automating parts of a process that the user is unfamiliar with are insufficient, resulting in issues with the inability to achieve business process optimization. Against this background, the present invention aims to provide a system that proposes more flexible and considerate workflows and solutions to problems, taking into account the user's emotional data.

[0332] 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.

[0333] In this invention, the server includes: means for a user to verbally explain a business process; means for a terminal to collect the user's explanation as voice data; means for the server to convert the voice data into text data using a voice recognition AI; means for the server to analyze the text data and generate an initial flow diagram; means for the terminal to display the initial flow diagram; means for the user to add explanations regarding branches and missing parts; means for the terminal to collect the additional explanation as voice data and send it back to the server; means for the server to convert the additional voice data into text data and correct the flow diagram; means for the server to generate problems and solutions based on past business process improvement case data using a generative AI model; means for the server to create slides containing the generated flow diagram, problems, and solutions; means for the server to generate videos based on the slide documents; means for the terminal to provide the videos to the user; means for an emotion engine installed in the terminal to analyze and collect user emotion data simultaneously with the voice data; and means for the server to adjust the business process diagram and problem-solving solutions based on the emotion data. This enables the generation of business process diagrams and problem-solving solutions that take user emotion data into consideration.

[0334] "Business flow" refers to a series of work procedures and processes for progressing a business.

[0335] "Verbal explanation" refers to the act of a user explaining a business flow or task using voice.

[0336] "Terminal" refers to an electronic device (such as a PC, smartphone, or tablet) that allows users to input voice and display information.

[0337] "Voice data" refers to data that is a digital record of voice information input by a user through a terminal.

[0338] "Voice recognition AI" refers to artificial intelligence technology that analyzes voice data and converts it into text data.

[0339] "Text data" refers to character information converted by voice recognition.

[0340] An "initial flow diagram" refers to a diagram showing an initial version of a business flow process generated based on a user's description.

[0341] "Branch" refers to a point within a business flow where processes branch off into different steps or outcomes.

[0342] "Modification" refers to the act of adding new information or changes to an existing Workflow diagram.

[0343] A "generative AI model" refers to an artificial intelligence model that generates new problems and solutions based on past business data.

[0344] "Issues" refer to problems found within the business flow or points that require improvement.

[0345] "Solution" refers to a specific method or proposal for solving the problem that has been discovered.

[0346] "Slide materials" refers to materials used to visually organize and present information such as business flow diagrams, issues, and solutions.

[0347] "Video" refers to visual content that visually depicts the contents of slide materials, explanations of business processes, issues, and solutions.

[0348] "Emotion engine" refers to software or hardware for analyzing a user's emotional state and generating emotion data.

[0349] "Emotion data" refers to data that indicates the user's emotional state as analyzed by the emotion engine.

[0350] "Adjustment" refers to the act of improving workflow diagrams and solutions based on user emotional data.

[0351] This invention combines a system in which a user verbally explains a business process, a voice recognition AI converts the explanation into text data, and then analyzes it to generate and modify a business process diagram, presenting business issues and improvement measures, with an emotion engine that recognizes the user's emotions. This system consists of a user, a terminal, a server, and an emotion engine. The system configuration and operation are explained in detail below.

[0352] System configuration

[0353] The system uses the following hardware and software:

[0354] Device: An electronic device such as a PC, smartphone, or tablet that is equipped with a microphone for voice input and a display.

[0355] Server: A high-performance computer server that contains the software environment for running speech recognition AI and generative AI models.

[0356] Emotion engine: Software or hardware that analyzes emotional data from a user's voice in real time.

[0357] Workflow explanation and voice recognition

[0358] The user verbally explains the workflow using the device's microphone. For example, they might say, "First, submit the application form at the reception desk, and then enter the data for confirmation." The device collects this voice data and sends it to the server. At the same time, the device's built-in emotion engine analyzes the user's emotional state in real time, generating and collecting emotion data.

[0359] Conversion to text data and generation of flow diagrams

[0360] The server receives the voice data and converts it into text data using speech recognition AI. Based on the converted text data, the server generates an initial version of the business flow diagram. For example, a flow diagram of "Reception -> Application submission -> Data entry" is generated. This initial flow diagram is sent to the terminal and displayed to the user.

[0361] Flowchart revision and emotional feedback

[0362] The user checks the initial flow diagram and provides additional explanations or corrections. For example, they might explain, "After data entry, we will make a decision on whether to approve or reject the request once the review process is complete." This additional explanation is also collected by the device's microphone and resent to the server. The server converts the additional voice data into text data and reflects the corrections in the original flow diagram. At the same time, it suggests a work order that is less stressful based on emotional data.

[0363] Presenting the problem and solution

[0364] The server uses a generative AI model to extract issues and solutions from past business data. For example, it generates specific improvement measures, such as "data entry can be automated," and displays these to the user on the device. It also makes suggestions based on emotional data, such as automating parts that cause stress to the user.

[0365] Creating slides and videos

[0366] The server creates slides based on the generated workflow diagram, issues, and solutions. The slides are created using Microsoft software. The created slides are sent to the terminal and displayed to the user. Finally, the server generates a video based on the slides, which is also sent to the terminal and provided to the user.

[0367] Specific examples

[0368] For example, if the user explains, "First, submit the application form at the reception desk, then enter the data for confirmation. After the data is entered, once the confirmation process is complete, we will make a decision on whether to approve or reject the application," the following is an example of a prompt sentence:

[0369] User: "I'll first submit the application form at the reception desk, then I'll enter the data for verification."

[0370] User: "After entering the data, we will make a decision on whether to approve or reject it once the review process is complete."

[0371] In this way, by combining an emotion engine, the present invention can generate and improve workflows while taking into account the emotional state of the user.

[0372] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0373] Step 1: Initial Setup

[0374] To begin explaining a business flow, a user accesses a terminal (such as a PC or smartphone), confirms that the microphone for voice input is properly connected, and then launches the interface. The terminal displays the interface, and the user confirms that it is ready. This operation itself does not involve any specific input, and the output is the interface's startup status.

[0375] Step 2: Explanation of the business flow and voice recognition

[0376] The user verbally explains the workflow into the device's microphone. The input is the user's voice, and for example, an explanation such as "First, submit the application form at the reception desk, and then enter the data for confirmation" is collected as voice data. The device sends the voice data to the server. The device's emotion engine also analyzes the user's emotional state in real time and generates emotion data. The output is the voice data and emotion data sent to the server.

[0377] Step 3: Convert to text data

[0378] The server converts the received voice data into text data using voice recognition AI. The input is voice data, and voice recognition is performed as data processing, generating text data such as "First, submit the application form at the reception desk, then enter the data for confirmation." The output is the converted text data.

[0379] Step 4: Generate the initial flow diagram

[0380] The server analyzes the generated text data and generates an initial version of the workflow diagram. The input is text data, and the workflow is analyzed as data processing, generating a flow diagram of "Reception -> Application submission -> Data entry." The output is the initial flow diagram, which is sent to the terminal and displayed.

[0381] Step 5: Add explanations and modify the flow diagram

[0382] The user checks the initial flow diagram displayed on the terminal and provides additional explanations as necessary. The input is the user's additional voice explanation, for example, "After data entry, once confirmation work is completed, a decision will be made on whether to approve or reject." This voice data is also collected by the terminal and sent back to the server. The server converts the additional voice data into text data and reflects the corrections in the original flow diagram. The corrected flow diagram will be "Data entry -> Confirmation work -> (Approval or rejection)." The output is the corrected flow diagram.

[0383] Step 6: Emotional feedback and regulation

[0384] The server analyzes the emotion data generated by the emotion engine and adjusts the revised flow diagram so that the user feels less stressed. The input is the emotion data and the revised flow diagram, and emotion analysis is performed as data processing. For example, stress points are identified and adjustments are made based on that. The output is the adjusted flow diagram that takes the emotion data into account.

[0385] Step 7: Generate problems and solutions

[0386] The server uses a generative AI model to generate issues and solutions based on past business data. The input is the modified flow diagram and past business data, and data analysis generates specific solutions, such as "data entry can be automated." The output is the issue and solution, which is sent to the terminal and displayed to the user.

[0387] Step 8: Create your slide deck

[0388] The server creates slides based on the generated business flow diagram, problems, and solutions. The inputs are the flow diagram, problems, and solutions, and slides are created using Microsoft software. The output is the slides, which are sent to the terminal and displayed to the user.

[0389] Step 9: Create and deliver your video

[0390] The server generates a video based on the slides. The input is the slides, and the video is generated using video creation software. The output is the completed video, which is sent to the terminal and presented to the user.

[0391] (Application example 2)

[0392] Next, a description will be given of Application 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."

[0393] Conventional workflow diagram generation systems lack feedback that takes into account the user's emotional state, which can lead to stressful processes, especially in factory operations. This can lead to insufficient optimization of factory robot operations, resulting in reduced productivity and increased risk of errors. Furthermore, there is a lack of a way to effectively incorporate the workflow explained by on-site managers into the robots.

[0394] 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.

[0395] In this invention, the server includes a means for converting voice data into text data using a voice recognition AI, a means for an emotion engine to analyze the user's emotion data and reflect the result as feedback when generating and modifying a workflow diagram, and a means for a factory robot to perform work based on the generated workflow diagram. This allows a more optimized workflow diagram to be generated taking into account the user's emotional state, enabling the factory robot to perform work efficiently based on the workflow diagram.

[0396] "User" refers to a person who verbally explains the business flow.

[0397] "Terminal" refers to a device that collects user explanations as voice data and displays or transmits them.

[0398] "Audio data" refers to a conversion of a user's verbal description into digital data.

[0399] A "server" refers to a device that converts voice data into text data using voice recognition AI and performs processes such as analysis, generation, and transmission.

[0400] "Voice recognition AI" refers to artificial intelligence technology that converts voice data into text data.

[0401] "Text data" refers to text-format data converted by voice recognition AI.

[0402] "Initial flow diagram" refers to the initial version of the business flow generated by analyzing text data.

[0403] "Display" refers to the terminal visually presenting information such as a workflow diagram to the user.

[0404] "Additional explanation" refers to new verbal explanation given by the user to the flow diagram.

[0405] "Emotion engine" refers to an engine that analyzes the user's emotion data and reflects it as feedback in the generation and modification of business flow diagrams.

[0406] "Feedback" refers to the process of reflecting the analysis results of the emotion engine in the generation and modification of business flow diagrams.

[0407] A "factory robot" refers to a machine that actually carries out work based on the generated business flow diagram.

[0408] "Issues" refer to problems that need to be solved within the business flow.

[0409] "Solution" refers to a proposal or method for solving a problem.

[0410] "Slide deck" refers to a presentation-style deck that includes the generated flow diagram, problem, and solution.

[0411] "Video" refers to a dynamic file that provides visual information based on slide presentations.

[0412] The system for implementing this invention utilizes voice recognition AI and an emotion engine to efficiently convert the business flow explained orally by the user into text data, analyze it, and generate, modify, and display a business flow diagram, which factory robots use to carry out their work.

[0413] Hardware and software used

[0414] Hardware:

[0415] microphone

[0416] Factory robots

[0417] Device (e.g. PC, smartphone)

[0418] software:

[0419] Python

[0420] SpeechRecognition Library

[0421] EmotionRecognition Library

[0422] TextToFlowchart Library

[0423] ImprovementSuggestions Library

[0424] Processing flow

[0425] Step 1: A user verbally explains the workflow, and audio data is collected using a microphone. This audio data is sent to the server via the terminal.

[0426] Step 2: The server uses speech recognition AI to convert the voice data into text data, which is then analyzed to generate an initial flow diagram. This initial flow diagram is then sent to the device and displayed to the user.

[0427] Step 3: The user checks the initial flow diagram on the terminal and adds explanations for branches or missing parts as needed. This is also collected as voice data using a microphone and sent back to the server.

[0428] Step 4: The server converts the additional voice data into text data and modifies the original workflow diagram. Furthermore, the emotion engine analyzes the user's emotional state and reflects emotional data such as stress as feedback in modifying the workflow diagram.

[0429] Step 5: Based on the revised workflow diagram, the server generates issues and solutions using data from past business reform projects. The generated workflow diagram, issues, and solutions are created as slides and sent to the terminal.

[0430] Step 6: The server generates a video based on the slides, and the device provides the video to the user. Finally, the factory robot performs the work based on the generated workflow diagram.

[0431] Specific examples

[0432] For example, a factory manager might explain his work as follows:

[0433] "We first receive the raw materials, then we inspect them for quality. If there are no problems, we start assembling them into parts."

[0434] Prompt Sentence Examples

[0435] Explain verbally the workflow of your factory, for example, "We first receive the raw materials, then inspect them for quality. If there are no problems, we start assembling them into parts."

[0436] This system takes into account the user's emotional state to generate more optimized workflow diagrams, enabling factory robots to carry out their work efficiently based on these diagrams.

[0437] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0438] Step 1:

[0439] The user verbally explains the workflow. The microphone is used to collect voice data and send it to the terminal. The user's voice is taken as input and digital voice data is generated as output.

[0440] Step 2:

[0441] The terminal sends the collected voice data to the server. The input is the voice data, and the output is the voice data transferred to the server.

[0442] Step 3:

[0443] The server uses voice recognition AI to convert the voice data into text data. The input is the voice data, and the output is the corresponding text data. The text data represents an outline of the business flow.

[0444] Step 4:

[0445] The server analyzes the text data and generates an initial flow diagram. The input is text data and the output is the initial flow diagram. Natural Language Processing technology is used for the analysis.

[0446] Step 5:

[0447] The server sends the generated initial flow diagram to the terminal. The input is the initial flow diagram, and the output is the flow diagram transferred to the terminal.

[0448] Step 6:

[0449] The terminal displays the initial flow diagram to the user, with the input being the initial flow diagram and the output being the visual representation that the user can see.

[0450] Step 7:

[0451] The user adds explanations to the flow diagram for branches and missing parts. The explanations are collected as voice data using a microphone and sent to the terminal. The input is the voice of the explanations, and the output is digital voice data.

[0452] Step 8:

[0453] The terminal sends additional audio data to the server. The input is the audio data, and the output is the audio data transferred to the server.

[0454] Step 9:

[0455] The server converts the additional voice data into text data and modifies the original flow diagram, with the additional voice data as input and the modified text data and flow diagram as output.

[0456] Step 10:

[0457] The emotion engine analyzes the user's voice data and generates emotion data. The input is voice data and the output is emotion data. The revised flow diagram is optimized based on this emotion data.

[0458] Step 11:

[0459] The server generates issues and solutions based on the optimized flow diagram and using data from past business reform projects. The input is the optimized flow diagram, and the output is the issues and solutions.

[0460] Step 12:

[0461] The flow diagram, problem, and solution generated by the server are created as slides. The input is the optimized flow diagram and solution, and the output is the slides.

[0462] Step 13:

[0463] The server generates a video based on the slides. The input is the slides, and the output is a video file.

[0464] Step 14:

[0465] The device provides the generated video to the user. The input is a video file, and the output is a visual representation of the video.

[0466] Step 15:

[0467] Factory robots carry out tasks based on the generated workflow diagram. The input is the optimized workflow diagram, and the output is the business process to be executed.

[0468] 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.

[0469] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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.

[0470] 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.

[0471] [Second embodiment]

[0472] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0473] 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.

[0474] 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).

[0475] 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.

[0476] 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.

[0477] 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).

[0478] 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.

[0479] 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.

[0480] 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.

[0481] 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.

[0482] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0483] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0484] This invention relates to a system in which a user verbally explains a workflow, a voice recognition AI converts the explanation into text data, and then analyzes it to generate and modify a workflow diagram, presenting business issues and improvement measures. This system is composed of a user, a terminal, and a server.

[0485] Initial Setup

[0486] First, as an initial setup of the system, the user accesses a terminal (e.g., a PC or smartphone) and launches an interface to begin explaining the business flow. This assumes that the terminal has a microphone for voice input.

[0487] Workflow explanation and voice recognition

[0488] The user verbally explains the workflow into the device's microphone. For example, the user might say, "First, submit the application form at the reception desk, and then enter the data for confirmation." This voice data is collected by the device and sent to the server.

[0489] The server receives the voice data and converts it into text using speech recognition AI, for example, "First, submit your application form at the reception desk, then enter the data for confirmation."

[0490] Initial generation of flow diagram

[0491] The server generates an initial version of the workflow diagram based on the text data. For example, the server automatically generates a workflow diagram in the format of "Reception -> Application Submission -> Data Entry." This initial workflow diagram is sent from the server to the terminal, which displays it to the user.

[0492] Modifying the flow diagram

[0493] The user checks the initial flow diagram and adds or modifies it as necessary. For example, the user may add an explanation such as, "After entering the data, I will decide whether to approve or reject it once the confirmation process is complete." This explanation is also collected by the device's microphone and sent to the server.

[0494] The server converts the additional voice data into text and adds branches and missing parts to the original flow diagram. This completes the flow diagram, for example, "Data entry -> Confirmation work -> (Approval or rejection)." The corrected flow diagram is then sent back to the terminal from the server and displayed to the user.

[0495] Presenting the problem and solution

[0496] The server uses a generative AI model to generate issues and improvement measures based on data from past business reform projects. For example, the server generates an improvement suggestion such as "data entry can be automated," and the terminal displays this suggestion to the user.

[0497] Creating slide decks and videos

[0498] The server creates slide decks based on the generated workflow diagrams, problems, and solutions. These slide decks are created using Microsoft tools and sent to the terminal, which displays them to the user.

[0499] Finally, the server generates a video based on the slides. This video includes an explanation of the business flow, the challenges, and solutions. The generated video is sent to the terminal and provided to the user.

[0500] Specific examples

[0501] For example, if the user explains, "First, submit the application form at the reception desk, then enter the data for confirmation. After entering the data, once the confirmation process is complete, we will make a decision to approve or reject the application," the flow would be as follows:

[0502] 1. The user gives an explanation into the device's microphone.

[0503] 2. The device collects the voice data and sends it to the server.

[0504] 3. The server uses voice recognition AI to convert the voice data into text.

[0505] 4. The server generates the initial flow diagram "Reception -> Application submission -> Data entry" and the terminal displays it.

[0506] 5. The user provides additional explanation and adds a branch of "Data entry -> Confirmation -> (Approve or Reject)".

[0507] 6. The server modifies the flow diagram, and the terminal displays the modified flow diagram.

[0508] 7. The server generates problems and solutions based on past data, and the device displays them.

[0509] 8. The server creates the slides and the terminal displays them.

[0510] 9. Finally, the server generates the video and the device provides it to the user.

[0511] The above is a specific description of the embodiment for carrying out the present invention.

[0512] The processing flow will be explained below.

[0513] Step 1:

[0514] The user speaks into the device's microphone to explain the work flow verbally. For example, they might explain, "First, submit the application form at the reception desk, and then enter the data for confirmation."

[0515] Step 2:

[0516] The terminal collects the user's explanation as voice data and transmits the voice data to the server.

[0517] Step 3:

[0518] The server receives the voice data, passes it to a speech recognition AI, and converts it into text data. For example, it converts it into text such as, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[0519] Step 4:

[0520] The server analyzes the text data and generates an initial version of the workflow diagram. For example, it generates an initial workflow diagram called "Reception -> Application Submission -> Data Entry."

[0521] Step 5:

[0522] The server sends the generated initial flow diagram to the terminal, which displays it to the user.

[0523] Step 6:

[0524] The user checks the initial flow diagram and adds explanations of branches and missing parts. For example, "After data entry, once the confirmation work is completed, a decision will be made on whether to approve or reject."

[0525] Step 7:

[0526] The terminal collects the user's additional explanation as voice data and transmits it again to the server.

[0527] Step 8:

[0528] The server passes the additional voice data to a voice recognition AI, converts it into text data, and adds branches or missing parts to the original flow diagram. For example, it generates a revised flow diagram such as "Data entry -> Confirmation work -> (Approval or rejection)."

[0529] Step 9:

[0530] The server sends the modified flow diagram to the terminal, which displays it to the user.

[0531] Step 10:

[0532] The server uses the generated AI model to generate issues and improvement measures based on data from past business reform projects. For example, it generates an improvement suggestion that "data entry can be automated."

[0533] Step 11:

[0534] The server sends the generated issues and solutions to the terminal, which then displays them to the user.

[0535] Step 12:

[0536] The server creates slide decks using Microsoft tools based on the generated business flow diagrams, issues, and solutions.

[0537] Step 13:

[0538] The server transmits the created slide material to the terminal, which then displays the slide material to the user.

[0539] Step 14:

[0540] The server generates a video based on the slides.

[0541] Step 15:

[0542] The server transmits the generated video to the terminal, which then provides the video to the user.

[0543] Example 1

[0544] Next, a description will be given of 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."

[0545] Conventional methods for creating business flowcharts require time and effort to collect and record business procedures, making it difficult to do so efficiently. Furthermore, when reflecting changes or improvements to procedures, it is often necessary to recreate them from scratch, which is also inefficient. Furthermore, there is also the problem that it is difficult to effectively utilize past data when identifying issues or proposing improvements.

[0546] 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.

[0547] In this invention, the server includes means for converting voice data into text data using acoustic analysis artificial intelligence, means for analyzing the text data to generate an initial procedure diagram, and means for creating an electronic document containing the generated procedure diagram, problems, and solutions. This makes it possible to efficiently generate a flowchart using only an oral explanation of the business procedure, and to quickly identify and propose problems and improvements.

[0548] "User" refers to a person who verbally explains business procedures.

[0549] "Terminal" refers to an electronic device for collecting voice data and displaying information to a user.

[0550] "Acoustic analysis artificial intelligence" refers to an intelligent system that uses technology to convert voice data into text data.

[0551] "Text data" refers to character information converted from audio data.

[0552] "Initial procedure diagram" refers to the first version of the business flow generated by analyzing text data.

[0553] A "procedure diagram" is a diagram that visually represents each step of a task.

[0554] "Branch" refers to an element in a procedure diagram that indicates multiple options or directions of progression.

[0555] "Missing parts" refer to elements or information that need to be added to the procedure diagram.

[0556] "Past work reform case data" refers to records and information relating to work reforms that have been implemented in the past.

[0557] "Issues" refer to problems in current business procedures that need improvement.

[0558] "Solution" refers to the improvement measures or methods proposed for a problem.

[0559] "Electronic document" refers to materials or reports created in digital format.

[0560] "Video" refers to materials in digital format that contain both audio and video.

[0561] This invention relates to a system in which a user verbally explains a business procedure, and an acoustic analysis AI converts the explanation into text data, which is then analyzed to generate and modify a business flow diagram, and presents business issues and improvement measures. This system is composed of a user, a terminal, and a server.

[0562] First, the user accesses a device such as a PC or smartphone and launches an interface to begin explaining the business flow. The device must have a microphone for voice input.

[0563] The user verbally explains the workflow into the device's microphone. For example, the user might say, "First, submit the application form at the reception desk, and then enter the data for confirmation." This voice data is collected by the device and sent to the server.

[0564] The server receives the voice data and converts it into text data using acoustic analysis artificial intelligence (e.g., a voice recognition algorithm), for example, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[0565] The server generates an initial version of the workflow diagram based on the text data. For example, the server automatically generates a workflow diagram in the format of "Reception -> Application Submission -> Data Entry." This initial workflow diagram is sent from the server to the terminal, which then displays it to the user.

[0566] The user checks the initial flow diagram and adds or modifies it as necessary. For example, the user may add an explanation such as, "After entering the data, I will decide whether to approve or reject it once the confirmation process is complete." This explanation is also collected by the device's microphone and sent to the server.

[0567] The server converts the additional voice data into text and adds branches and missing parts to the original flow diagram. This completes the flow diagram, for example, "Data entry -> Confirmation work -> (Approval or rejection)." The corrected flow diagram is then sent back to the terminal from the server and displayed to the user.

[0568] The server uses a generative AI model (such as an advanced natural language processing model) to generate issues and improvement measures based on data from past business reform projects. For example, the server generates an improvement proposal such as "data entry can be automated," and the terminal displays this proposal to the user.

[0569] Finally, the server creates an electronic document based on the generated business flow diagram, problems, and solutions. This electronic document is created using a general presentation tool and sent to the terminal, where it is displayed to the user.

[0570] Finally, the server generates a video based on the electronic document. This video includes an explanation of the business flow, the challenges, and solutions. The generated video is sent to the terminal and provided to the user.

[0571] As a concrete example, the following prompt sentence is input to the generative AI model:

[0572] User workflow description:

[0573] "First, you submit an application form at the reception desk, and then the data is entered for verification. After the data is entered and the verification process is completed, a decision is made as to whether the application will be approved or rejected."

[0574] Based on this workflow, please create an initial workflow diagram, present the issues and solutions, and also create an electronic document and video.

[0575] In this manner, the present invention enables a user to quickly and efficiently generate a business flow chart, identify problems, and propose improvements simply by verbally explaining the business procedures.

[0576] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0577] Step 1:

[0578] The user launches the terminal interface.

[0579] Input: User initiated interface action.

[0580] How it works: The user launches an interface to begin explaining the business flow from an application or web browser on a device such as a PC or smartphone.

[0581] Output: The interface is displayed on the terminal.

[0582] Step 2:

[0583] The user verbally explains the business flow.

[0584] Input: User's voice.

[0585] Operation: The user verbally explains the workflow steps into the device's microphone. For example, "First, submit the application form at the reception desk, and then enter the data for confirmation."

[0586] Output: The device collects the audio data of the explanation.

[0587] Step 3:

[0588] The terminal transmits the voice data to the server.

[0589] Input: Audio data.

[0590] Operation: The device sends the collected voice data to the server. Before sending, the data is reformatted and transferred to the server via the network.

[0591] Output: The audio data arrives at the server.

[0592] Step 4:

[0593] The server converts the voice data into text data.

[0594] Input: Audio data.

[0595] How it works: The server uses acoustic analysis artificial intelligence (voice recognition AI) to convert the received voice data into text data. For example, it generates text data such as "First, submit the application form at the reception desk, then enter the data for confirmation."

[0596] Output: Text data.

[0597] Step 5:

[0598] The server analyzes the text data and generates an initial procedure diagram.

[0599] Input: Text data.

[0600] Operation: The server analyzes the text data and extracts each step of the process for each sentence. Based on the extracted steps, it generates an initial version of the workflow diagram. For example, it creates a flow diagram called "Reception -> Application Submission -> Data Entry."

[0601] Output: Initial procedure diagram.

[0602] Step 6:

[0603] The server sends the initial procedure diagram to the terminal, which displays it.

[0604] Input: Initial procedure diagram.

[0605] Operation: The server sends the generated initial procedure diagram to the terminal, which then displays the received procedure diagram to the user.

[0606] Output: User confirms initial procedure diagram.

[0607] Step 7:

[0608] The user provides additional explanations for the initial procedure diagram.

[0609] Input: Initial procedure diagram, additional user explanation voice.

[0610] Action: The user reviews the initial procedure diagram and provides additional information or corrections as needed. For example, they might explain, "After data entry, we will make a decision on whether to approve or reject the request once the review process is complete." The device collects this additional voice data.

[0611] Output: Collected audio data.

[0612] Step 8:

[0613] The terminal transmits the audio data of the additional explanation to the server.

[0614] Input: Additional audio data.

[0615] Operation: The device sends the collected additional voice data to the server. Before sending, the data is reformatted and transferred to the server via the network.

[0616] Output: Additional audio data arrives at the server.

[0617] Step 9:

[0618] The server converts the additional voice data into text data and corrects the procedure diagram.

[0619] Input: Additional audio data.

[0620] How it works: The server uses acoustic analysis AI to convert the additional voice data into text data. It then adds branches and missing parts to the existing flow diagram and modifies the procedure diagram. For example, it generates a final flow diagram that looks like "Data entry -> Confirmation work -> (Approval or rejection)."

[0621] Output: Revised procedure diagram.

[0622] Step 10:

[0623] The server transmits the correction procedure diagram to the terminal, which displays it.

[0624] Input: Correction procedure diagram.

[0625] Operation: The server sends the modified procedure diagram to the terminal, which displays the received procedure diagram to the user.

[0626] Output: The user checks the correction procedure diagram.

[0627] Step 11:

[0628] The server generates problems and solutions.

[0629] Input: Correction procedure diagram, past work reform case data.

[0630] How it works: The server uses the generative AI model to generate issues and solutions based on past work reform project data. For example, it generates improvement proposals such as "Data entry can be automated."

[0631] Output: Challenges and solutions.

[0632] Step 12:

[0633] The server sends the problem and solution to the terminal, which displays it.

[0634] Input: Challenges and solutions.

[0635] Operation: The server sends the generated problem and solution to the terminal, which displays it to the user.

[0636] Output: User sees the problem and solution.

[0637] Step 13:

[0638] The server creates the electronic document.

[0639] Input: Procedure diagram, problem, solution.

[0640] Operation: The server creates an electronic document based on the generated procedure diagram, problem, and solution. This electronic document is created using a common presentation tool.

[0641] Output: Electronic document.

[0642] Step 14:

[0643] The server transmits the electronic document to the terminal, which displays it.

[0644] Input: Electronic document.

[0645] Operation: The server sends the completed electronic document to the terminal, which displays it to the user.

[0646] Output: The user reviews the electronic document.

[0647] Step 15:

[0648] The server generates the video.

[0649] Input: Electronic document.

[0650] How it works: The server generates a video based on the electronic document, which includes an explanation of the business process, the problem, and the solution.

[0651] Output: Video.

[0652] Step 16:

[0653] The server sends the video to the terminal and provides it to the user.

[0654] Input: Video.

[0655] Operation: The server sends the generated video to the device, which then provides it to the user, who then watches the video.

[0656] Output: User watches a video.

[0657] (Application example 1)

[0658] Next, a description will be given of Application 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."

[0659] Managing workflows at logistics centers is complex, and presenting clear workflows and improvement measures is essential for on-site workers to work efficiently and accurately. However, existing systems do not automatically generate workflows using voice input or provide real-time improvement suggestions, which places a heavy burden on workers and reduces work efficiency. Given this background, there is a need for a system that can quickly generate workflow diagrams using voice input and present improvement measures in real time.

[0660] 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.

[0661] In this invention, the server includes a means for a user to verbally explain a workflow, a means for a terminal to collect the user's explanation as voice data, a means for the server to convert the voice data into text data using voice recognition AI, a means for linking with a voice input function installed in a smart device, a means for displaying a workflow diagram on the smart device in real time, and a means for presenting improvement measures to a worker using the smart device. This allows a worker to simply explain a workflow through voice input, which is visualized in real time and immediately presented with improvement measures.

[0662] A "user" is a person who uses the system to explain and modify business processes.

[0663] A "terminal" is a device (such as a PC or smart device) that collects voice data, displays flow diagrams, and interfaces with the user.

[0664] A "server" is a computer system that performs a wide range of data processing, including converting and analyzing audio data, creating and modifying flow charts, presenting problems and solutions, and even creating slides and videos.

[0665] "Voice recognition AI" is an artificial intelligence technology that converts input voice data into text data.

[0666] "Text data" is character information obtained by converting voice data.

[0667] The "initial flow diagram" is the first version of the business flow generated by the server based on the voice description.

[0668] "Additional explanation" refers to the user verbally explaining further details or branches to the initial flow diagram.

[0669] "Past business process reform case data" refers to a data set of previously collected and analyzed business processes, and serves as reference material for generating issues and solutions.

[0670] "Issues" refer to problems in the current business flow or areas that need improvement.

[0671] "Solutions" refer to specific proposals and measures to resolve issues and improve business flow.

[0672] A "slide deck" is a presentation-style document that summarizes business flow diagrams, issues, solutions, etc.

[0673] "Video" refers to visual and audio content generated based on slide materials.

[0674] A "smart device" is a device (e.g., smart glasses, smartphone, etc.) that allows a user to verbally explain a business process and display a business process diagram and improvement measures on the screen in real time.

[0675] The "voice input function" is a function that allows a smart device to collect the user's voice and pass it on to the system.

[0676] "Real-time display" refers to the function of instantly processing user operations and explanations and displaying the results immediately.

[0677] A "worker" is a person who performs work at a logistics center.

[0678] This invention provides a system for streamlining workflow management in logistics centers. A user verbally explains the workflow, and a voice recognition AI analyzes the explanation, automatically generates and modifies a workflow diagram, and suggests issues and improvements.

[0679] First, the user puts on a smart device (e.g., smart glasses or a smartphone) and verbally explains the workflow. This explanation is collected as voice data through the smart device's microphone. The collected voice data is then sent directly to the server.

[0680] When the server receives the voice data, it converts it into text data using a speech recognition AI. This speech recognition AI can be, for example, the Google Cloud Speech-to-Text API. The converted text data is analyzed by a generative AI model for workflow analysis, and an initial workflow diagram is generated. An example of this generative AI model is the OpenAI API.

[0681] The generated initial flow diagram is sent from the server to the smart device and displayed to the user. The user checks the flow diagram and provides additional explanations by voice if necessary. The additional explanations are also collected through the smart device's microphone and sent to the server. The server converts the additional voice data into text data and corrects the flow diagram.

[0682] Furthermore, the server uses a generative AI model based on data from past business reform projects to propose issues and improvement measures. The proposed issues and improvement measures are displayed in real time on the smart device screen, allowing users to quickly implement countermeasures on-site.

[0683] Based on the generated business flow diagram and improvement measures, the server automatically creates slides. These slides are generated using, for example, the Python-pptx library. Finally, the server converts the slides into video format and generates a video using the MoviePy library. This video is then sent to the smart device and provided to the user.

[0684] As a concrete example, consider a situation where a user verbally explains, "First, we accept the cargo at the reception desk, then we sort it in the warehouse and prepare it for delivery." This system collects the voice data of the explanation and automatically generates a flow diagram such as "Reception -> Cargo Reception -> Sorting -> Delivery Preparation." The generative AI model then proposes "the issue of improving the efficiency of sorting is a problem, and an improvement plan to automate it."

[0685] An example of a prompt is:

[0686] Flowchart generation prompt:

[0687] "Translate the following workflow into a flow diagram: First, cargo is received at the reception desk, then it is sorted in the warehouse and prepared for delivery."

[0688] This system uses smart glasses or a smartphone to smoothly carry out the entire process from explaining the work flow to visualizing it and presenting improvement measures, significantly improving work efficiency at logistics centers.

[0689] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0690] Step 1:

[0691] The user verbally explains the workflow. The user verbally explains the workflow into the microphone on the smart device (smart glasses or smartphone). For example, the user might explain, "First, the cargo is received at the reception desk, then it is sorted in the warehouse and prepared for delivery."

[0692] Step 2:

[0693] The terminal collects the user's explanation as voice data. The terminal uses the smart device's microphone to collect the voice data in real time and transmits the voice data as is to the server. The output includes the collected voice data.

[0694] Step 3:

[0695] The server converts the voice data into text data using a voice recognition AI. The server then inputs the received voice data into a voice recognition AI such as Google Cloud Speech-to-Text API, and obtains text data as output, which is the voice converted into a string of characters. The converted text data then proceeds to the next analysis step.

[0696] Step 4:

[0697] The server analyzes the text data and generates an initial flow diagram. The server uses OpenAI's generative AI model to generate a flow diagram by inputting a prompt. Specifically, by inputting "Convert the following business flow into a flow diagram: text data," the server outputs an initial flow diagram such as "Reception -> Cargo Reception -> Sorting -> Delivery Preparation."

[0698] Step 5:

[0699] The terminal displays the initial flow diagram. The generated initial flow diagram is sent from the server to the smart device and displayed on the terminal display in real time, allowing the user to visually check the flow diagram.

[0700] Step 6:

[0701] The user provides additional explanations about branches and missing parts. While looking at the initial flow diagram, the user provides additional explanations (e.g., "After data entry, once confirmation work is completed, a decision will be made on whether to approve or reject the request.") by voice.

[0702] Step 7:

[0703] The terminal collects the additional explanation as voice data and transmits it again to the server. The microphone of the terminal collects the additional explanation and transmits it again to the server as voice data. The collected additional voice data is output.

[0704] Step 8:

[0705] The server converts the additional voice data into text data and modifies the flow diagram. The server again converts the additional voice data into text data using the Google Cloud Speech-to-Text API, and uses OpenAI's generative AI model to add and modify branches and missing parts of the flow diagram.

[0706] Step 9:

[0707] The server generates issues and solutions based on data from past business reform projects. The server references past data sets and uses a generative AI model to automatically generate issues in business flows and their solutions.

[0708] Step 10:

[0709] The server creates slides based on the generated flow diagrams, problems, and solutions. The server uses the python-pptx library to compile the flow diagrams, problems, and solutions into slide-format materials.

[0710] Step 11:

[0711] The server generates a video based on the slides. The server uses the moviepy library to convert the slides into a video, creating a video that conveys the content visually and audibly.

[0712] Step 12:

[0713] The terminal provides the video to the user. The generated video is sent from the server to the smart device and provided in a format that the user can easily view.

[0714] 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.

[0715] This invention combines a system in which a user verbally explains a business process, a voice recognition AI converts the explanation into text data, analyzes it, generates and modifies a business process diagram, and presents business issues and improvement measures, with an emotion engine that recognizes the user's emotions. This system consists of a user, a terminal, a server, and an emotion engine.

[0716] Initial Setup

[0717] First, as an initial setup of the system, the user accesses a terminal (e.g., a PC or smartphone) and launches an interface to begin explaining the business flow. This assumes that the terminal has a microphone for voice input.

[0718] Workflow explanation and voice recognition

[0719] The user verbally explains the workflow into the device's microphone. For example, the user might say, "First, I submit the application form at the reception desk, and then I enter the data for confirmation." This voice data is collected by the device and sent to the server. At the same time, the emotion engine runs, analyzing the user's emotions in real time.

[0720] Collecting Emotional Data

[0721] When the device collects voice data, the emotion engine analyzes the user's emotional state and generates emotion data. For example, if the user is feeling stressed, the emotion data is collected as additional information.

[0722] Conversion to text data and initial generation of flow diagrams

[0723] The server receives the voice data and converts it into text using speech recognition AI. For example, it could be converted into text that says, "First, submit your application form at the reception desk, then enter the data for confirmation."

[0724] The server generates an initial version of the workflow diagram based on the text data. For example, it generates an initial workflow diagram called "Reception -> Application Submission -> Data Entry." This initial workflow diagram is sent from the server to the terminal, which displays it to the user.

[0725] Flowchart revision and emotional feedback

[0726] The user checks the initial flow diagram and adds or modifies it as necessary. For example, they might add, "After data entry, we will make a decision on whether to approve or reject the request once the review process is complete." This additional explanation is also collected by the device's microphone and sent to the server.

[0727] The server converts the additional voice data into text and adds branches and missing parts to the original flow diagram. This completes the flow diagram, for example, "Data Entry -> Confirmation -> (Approval or Rejection)." At the same time, it adjusts the revised flow diagram to avoid stress for the user, taking into account the emotional data generated by the emotion engine.

[0728] Presenting the problem and solution

[0729] The server uses a generative AI model to generate issues and improvement measures based on data from past business reform projects. For example, the server generates an improvement suggestion such as "data entry can be automated," and the terminal displays this suggestion to the user.

[0730] Furthermore, based on the emotional data, we propose solutions that take into account the user's emotional state, for example, by proposing automation of processes that tend to cause stress to the user.

[0731] Creating slide decks and videos

[0732] The server creates slide decks based on the generated workflow diagrams, problems, and solutions. These slide decks are created using Microsoft tools and sent to the terminal, which displays them to the user.

[0733] Finally, the server generates a video based on the slides. This video includes an explanation of the business flow, the challenges, and solutions. The generated video is sent to the terminal and provided to the user.

[0734] Specific examples

[0735] For example, if the user explains, "First, submit the application form at the reception desk, then enter the data for confirmation. After entering the data, once the confirmation process is complete, we will make a decision to approve or reject the application," the flow would be as follows:

[0736] 1. The user gives an explanation into the device's microphone.

[0737] 2. The device collects the voice data and sends it to the server. At the same time, the emotion engine analyzes the user's emotions and recognizes that they are feeling stressed.

[0738] 3. The server uses voice recognition AI to convert the voice data into text.

[0739] 4. The server generates the initial flow diagram "Reception -> Application submission -> Data entry" and the terminal displays it.

[0740] 5. The user provides additional explanation and adds a branch of "Data entry -> Confirmation -> (Approve or Reject)".

[0741] 6. The server modifies the flow chart and suggests a less stressful work sequence based on the emotion data. The modified flow chart is then displayed on the device.

[0742] 7. The server generates problems and solutions based on past data, and the device displays them.

[0743] 8. The server creates the slides and the terminal displays them.

[0744] 9. Finally, the server generates the video and the device provides it to the user.

[0745] The above is a specific description of the embodiment of the present invention. By combining an emotion engine, it is possible to advance business reform while taking into consideration the emotional state of the user.

[0746] The processing flow will be explained below.

[0747] Step 1:

[0748] The user speaks into the device's microphone to explain the work flow verbally. For example, they might explain, "First, submit the application form at the reception desk, and then enter the data for confirmation."

[0749] Step 2:

[0750] The device collects the user's explanation as voice data and sends it to the server. At the same time, the emotion engine analyzes the user's emotions in real time and generates emotion data.

[0751] Step 3:

[0752] The server receives the voice data, passes it to a voice recognition AI, and converts it into text data. For example, it converts it into text such as, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[0753] Step 4:

[0754] The server analyzes the text data and generates an initial version of a workflow diagram. For example, it generates an initial workflow diagram called "Reception -> Application Submission -> Data Entry." It then sends this workflow diagram to the terminal, which displays it to the user.

[0755] Step 5:

[0756] The user checks the initial flow diagram and adds explanations of branches and missing parts as necessary. For example, they might add, "After data entry and confirmation, a decision will be made on whether to approve or reject the request." At the same time, the emotion engine continues to evaluate the user's emotions.

[0757] Step 6:

[0758] The terminal collects the user's additional explanation as voice data and transmits it again to the server.

[0759] Step 7:

[0760] The server passes the additional voice data to a voice recognition AI, converts it into text data, and adds branches or missing parts to the original flow diagram. For example, it generates a revised flow diagram such as "Data entry -> Confirmation work -> (Approval or rejection)."

[0761] Step 8:

[0762] The server sends the modified flow diagram to the terminal, which displays it to the user. At this time, the emotion engine provides an optimal flow diagram that is adjusted based on the emotional data analyzed to prevent the user from feeling stressed.

[0763] Step 9:

[0764] The server uses the generated AI model to generate issues and improvement measures based on data from past business reform projects. For example, the server may generate an improvement suggestion such as "data entry can be automated." Furthermore, it proposes solutions to issues that take into account the user's emotional state based on emotional data.

[0765] Step 10:

[0766] The server sends the generated issues and improvement measures to the device, which then displays them to the user. For example, the device may suggest, "By promoting automation of data entry, we can reduce stress."

[0767] Step 11:

[0768] The server uses Microsoft tools to create slides based on the generated workflow diagram, issues, and solutions, and then sends the slides to the terminal, which displays them to the user.

[0769] Step 12:

[0770] The server generates a video based on the slides. The generated video is sent to the terminal, which then provides it to the user. For example, a video containing an explanation of a business process, problems, and solutions is provided.

[0771] The above are the specific processing steps for implementing the invention in combination with the emotion engine. By utilizing emotion data, it is possible to advance business reform while taking into account the user's emotional state.

[0772] Example 2

[0773] Next, a description will be given of 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."

[0774] The main function of conventional workflow creation systems is to convert a user's verbal explanation into text data and generate a workflow diagram. However, if workflows or solutions to problems are proposed without taking the user's emotional state into consideration, the user may feel stressed or the workflow may not be applicable in the actual workplace. Furthermore, proposals for automating parts of a process that the user is unfamiliar with are insufficient, resulting in issues with the inability to achieve business process optimization. Against this background, the present invention aims to provide a system that proposes more flexible and considerate workflows and solutions to problems, taking into account the user's emotional data.

[0775] 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.

[0776] In this invention, the server includes: means for a user to verbally explain a business process; means for a terminal to collect the user's explanation as voice data; means for the server to convert the voice data into text data using a voice recognition AI; means for the server to analyze the text data and generate an initial flow diagram; means for the terminal to display the initial flow diagram; means for the user to add explanations regarding branches and missing parts; means for the terminal to collect the additional explanation as voice data and send it back to the server; means for the server to convert the additional voice data into text data and correct the flow diagram; means for the server to generate problems and solutions based on past business process improvement case data using a generative AI model; means for the server to create slides containing the generated flow diagram, problems, and solutions; means for the server to generate videos based on the slide documents; means for the terminal to provide the videos to the user; means for an emotion engine installed in the terminal to analyze and collect user emotion data simultaneously with the voice data; and means for the server to adjust the business process diagram and problem-solving solutions based on the emotion data. This enables the generation of business process diagrams and problem-solving solutions that take user emotion data into consideration.

[0777] "Business flow" refers to a series of work procedures and processes for progressing a business.

[0778] "Verbal explanation" refers to the act of a user explaining a business flow or task using voice.

[0779] "Terminal" refers to an electronic device (such as a PC, smartphone, or tablet) that allows users to input voice and display information.

[0780] "Voice data" refers to data that is a digital record of voice information input by a user through a terminal.

[0781] "Voice recognition AI" refers to artificial intelligence technology that analyzes voice data and converts it into text data.

[0782] "Text data" refers to character information converted by voice recognition.

[0783] An "initial flow diagram" refers to a diagram showing an initial version of a business flow process generated based on a user's description.

[0784] "Branch" refers to a point within a business flow where processes branch off into different steps or outcomes.

[0785] "Modification" refers to the act of adding new information or changes to an existing Workflow diagram.

[0786] A "generative AI model" refers to an artificial intelligence model that generates new problems and solutions based on past business data.

[0787] "Issues" refer to problems found within the business flow or points that require improvement.

[0788] "Solution" refers to a specific method or proposal for solving the problem that has been discovered.

[0789] "Slide materials" refers to materials used to visually organize and present information such as business flow diagrams, issues, and solutions.

[0790] "Video" refers to visual content that visually depicts the contents of slide materials, explanations of business processes, issues, and solutions.

[0791] "Emotion engine" refers to software or hardware for analyzing a user's emotional state and generating emotion data.

[0792] "Emotion data" refers to data that indicates the user's emotional state as analyzed by the emotion engine.

[0793] "Adjustment" refers to the act of improving workflow diagrams and solutions based on user emotional data.

[0794] This invention combines a system in which a user verbally explains a business process, a voice recognition AI converts the explanation into text data, and then analyzes it to generate and modify a business process diagram, presenting business issues and improvement measures, with an emotion engine that recognizes the user's emotions. This system consists of a user, a terminal, a server, and an emotion engine. The system configuration and operation are explained in detail below.

[0795] System configuration

[0796] The system uses the following hardware and software:

[0797] Device: An electronic device such as a PC, smartphone, or tablet that is equipped with a microphone for voice input and a display.

[0798] Server: A high-performance computer server that contains the software environment for running speech recognition AI and generative AI models.

[0799] Emotion engine: Software or hardware that analyzes emotional data from a user's voice in real time.

[0800] Workflow explanation and voice recognition

[0801] The user verbally explains the workflow using the device's microphone. For example, they might say, "First, submit the application form at the reception desk, and then enter the data for confirmation." The device collects this voice data and sends it to the server. At the same time, the device's built-in emotion engine analyzes the user's emotional state in real time, generating and collecting emotion data.

[0802] Conversion to text data and generation of flow diagrams

[0803] The server receives the voice data and converts it into text data using speech recognition AI. Based on the converted text data, the server generates an initial version of the business flow diagram. For example, a flow diagram of "Reception -> Application submission -> Data entry" is generated. This initial flow diagram is sent to the terminal and displayed to the user.

[0804] Flowchart revision and emotional feedback

[0805] The user checks the initial flow diagram and provides additional explanations or corrections. For example, they might explain, "After data entry, we will make a decision on whether to approve or reject the request once the review process is complete." This additional explanation is also collected by the device's microphone and resent to the server. The server converts the additional voice data into text data and reflects the corrections in the original flow diagram. At the same time, it suggests a work order that is less stressful based on emotional data.

[0806] Presenting the problem and solution

[0807] The server uses a generative AI model to extract issues and solutions from past business data. For example, it generates specific improvement measures, such as "data entry can be automated," and displays these to the user on the device. It also makes suggestions based on emotional data, such as automating parts that cause stress to the user.

[0808] Creating slide decks and videos

[0809] The server creates slides based on the generated workflow diagram, issues, and solutions. The slides are created using Microsoft software. The created slides are sent to the terminal and displayed to the user. Finally, the server generates a video based on the slides, which is also sent to the terminal and provided to the user.

[0810] Specific examples

[0811] For example, if the user explains, "First, submit the application form at the reception desk, then enter the data for confirmation. After the data is entered, once the confirmation process is complete, we will make a decision on whether to approve or reject the application," the following is an example of a prompt sentence:

[0812] User: "I first submit the application form at the reception desk, then I enter the data for verification."

[0813] User: "After entering the data, we will make a decision on whether to approve or reject it once the review process is complete."

[0814] In this way, by combining an emotion engine, the present invention can generate and improve a workflow while taking into account the emotional state of the user.

[0815] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0816] Step 1: Initial Setup

[0817] To begin explaining a business flow, a user accesses a terminal (such as a PC or smartphone), confirms that the microphone for voice input is properly connected, and then launches the interface. The terminal displays the interface, and the user confirms that it is ready. This operation itself does not involve any specific input, and the output is the interface's startup status.

[0818] Step 2: Explanation of the business flow and voice recognition

[0819] The user verbally explains the workflow into the device's microphone. The input is the user's voice, and for example, an explanation such as "First, submit the application form at the reception desk, and then enter the data for confirmation" is collected as voice data. The device sends the voice data to the server. The device's emotion engine also analyzes the user's emotional state in real time and generates emotion data. The output is the voice data and emotion data sent to the server.

[0820] Step 3: Convert to text data

[0821] The server converts the received voice data into text data using voice recognition AI. The input is voice data, and voice recognition is performed as data processing, generating text data such as "First, submit the application form at the reception desk, then enter the data for confirmation." The output is the converted text data.

[0822] Step 4: Generate the initial flow diagram

[0823] The server analyzes the generated text data and generates an initial version of the workflow diagram. The input is text data, and the workflow is analyzed as data processing, generating a flow diagram of "Reception -> Application submission -> Data entry." The output is the initial flow diagram, which is sent to the terminal and displayed.

[0824] Step 5: Add explanations and modify the flow diagram

[0825] The user checks the initial flow diagram displayed on the terminal and provides additional explanations as necessary. The input is the user's additional voice explanation, for example, "After data entry, once confirmation work is completed, a decision will be made on whether to approve or reject." This voice data is also collected by the terminal and sent back to the server. The server converts the additional voice data into text data and reflects the corrections in the original flow diagram. The corrected flow diagram will be "Data entry -> Confirmation work -> (Approval or rejection)." The output is the corrected flow diagram.

[0826] Step 6: Emotional feedback and regulation

[0827] The server analyzes the emotion data generated by the emotion engine and adjusts the revised flow diagram so that the user feels less stressed. The input is the emotion data and the revised flow diagram, and emotion analysis is performed as data processing. For example, stress points are identified and adjustments are made based on that. The output is the adjusted flow diagram that takes the emotion data into account.

[0828] Step 7: Generate problems and solutions

[0829] The server uses a generative AI model to generate issues and solutions based on past business data. The input is the modified flow diagram and past business data, and data analysis generates specific solutions, such as "data entry can be automated." The output is the issue and solution, which is sent to the terminal and displayed to the user.

[0830] Step 8: Create your slide deck

[0831] The server creates slides based on the generated business flow diagram, issues, and solutions. The inputs are the flow diagram, issues, and solutions, and slides are created using Microsoft software. The output is the slides, which are sent to the terminal and displayed to the user.

[0832] Step 9: Create and deliver your video

[0833] The server generates a video based on the slides. The input is the slides, and the video is generated using video creation software. The output is the completed video, which is sent to the terminal and presented to the user.

[0834] (Application example 2)

[0835] Next, a description will be given of Application 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."

[0836] Conventional workflow diagram generation systems lack feedback that takes into account the user's emotional state, which can lead to stressful processes, especially in factory operations. This can lead to insufficient optimization of factory robot operations, resulting in reduced productivity and increased risk of errors. Furthermore, there is a lack of a way to effectively incorporate the workflow explained by on-site managers into the robots.

[0837] 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.

[0838] In this invention, the server includes a means for converting voice data into text data using a voice recognition AI, a means for an emotion engine to analyze the user's emotion data and reflect the result as feedback when generating and modifying a workflow diagram, and a means for a factory robot to perform work based on the generated workflow diagram. This allows a more optimized workflow diagram to be generated taking into account the user's emotional state, enabling the factory robot to perform work efficiently based on the workflow diagram.

[0839] "User" refers to a person who verbally explains the business flow.

[0840] "Terminal" refers to a device that collects user explanations as voice data and displays or transmits them.

[0841] "Audio data" refers to a conversion of a user's verbal description into digital data.

[0842] A "server" refers to a device that converts voice data into text data using voice recognition AI and performs processes such as analysis, generation, and transmission.

[0843] "Voice recognition AI" refers to artificial intelligence technology that converts voice data into text data.

[0844] "Text data" refers to text-format data converted by voice recognition AI.

[0845] "Initial flow diagram" refers to the initial version of the business flow generated by analyzing text data.

[0846] "Display" refers to the terminal visually presenting information such as a workflow diagram to the user.

[0847] "Additional explanation" refers to new verbal explanation given by the user to the flow diagram.

[0848] "Emotion engine" refers to an engine that analyzes the user's emotion data and reflects it as feedback in the generation and modification of business flow diagrams.

[0849] "Feedback" refers to the process of reflecting the analysis results of the emotion engine in the generation and modification of business flow diagrams.

[0850] A "factory robot" refers to a machine that actually carries out work based on the generated business flow diagram.

[0851] "Issues" refer to problems that need to be solved within the business flow.

[0852] "Solution" refers to a proposal or method for solving a problem.

[0853] "Slide deck" refers to a presentation-style deck that includes the generated flow diagram, problem, and solution.

[0854] "Video" refers to a dynamic file that provides visual information based on slide presentations.

[0855] The system for implementing this invention utilizes voice recognition AI and an emotion engine to efficiently convert the business flow explained orally by the user into text data, analyze it, and generate, modify, and display a business flow diagram, which factory robots use to carry out their work.

[0856] Hardware and software used

[0857] Hardware:

[0858] microphone

[0859] Factory robots

[0860] Device (e.g. PC, smartphone)

[0861] software:

[0862] Python

[0863] SpeechRecognition Library

[0864] EmotionRecognition Library

[0865] TextToFlowchart Library

[0866] ImprovementSuggestions Library

[0867] Processing flow

[0868] Step 1: A user verbally explains the workflow, and audio data is collected using a microphone. This audio data is sent to the server via the terminal.

[0869] Step 2: The server uses speech recognition AI to convert the voice data into text data, which is then analyzed to generate an initial flow diagram. This initial flow diagram is then sent to the device and displayed to the user.

[0870] Step 3: The user checks the initial flow diagram on the terminal and adds explanations for branches or missing parts as needed. This is also collected as voice data using a microphone and sent back to the server.

[0871] Step 4: The server converts the additional voice data into text data and modifies the original workflow diagram. Furthermore, the emotion engine analyzes the user's emotional state and reflects emotional data such as stress as feedback in modifying the workflow diagram.

[0872] Step 5: Based on the revised workflow diagram, the server generates issues and solutions using data from past business reform projects. The generated workflow diagram, issues, and solutions are created as slides and sent to the terminal.

[0873] Step 6: The server generates a video based on the slides, and the device provides the video to the user. Finally, the factory robot performs the work based on the generated workflow diagram.

[0874] Specific examples

[0875] For example, a factory manager might explain his work as follows:

[0876] "We first receive the raw materials, then we inspect them for quality. If there are no problems, we start assembling them into parts."

[0877] Prompt Sentence Examples

[0878] Explain verbally the workflow of your factory, for example, "We first receive the raw materials, then inspect them for quality. If there are no problems, we start assembling them into parts."

[0879] This system takes into account the user's emotional state to generate more optimized workflow diagrams, enabling factory robots to carry out their work efficiently based on these diagrams.

[0880] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0881] Step 1:

[0882] The user verbally explains the workflow. The microphone is used to collect voice data and send it to the terminal. The user's voice is taken as input and digital voice data is generated as output.

[0883] Step 2:

[0884] The terminal sends the collected voice data to the server. The input is the voice data, and the output is the voice data transferred to the server.

[0885] Step 3:

[0886] The server uses voice recognition AI to convert the voice data into text data. The input is the voice data, and the output is the corresponding text data. The text data represents an outline of the business flow.

[0887] Step 4:

[0888] The server analyzes the text data and generates an initial flow diagram. The input is text data and the output is the initial flow diagram. Natural Language Processing technology is used for the analysis.

[0889] Step 5:

[0890] The server sends the generated initial flow diagram to the terminal. The input is the initial flow diagram, and the output is the flow diagram transferred to the terminal.

[0891] Step 6:

[0892] The terminal displays the initial flow diagram to the user, with the input being the initial flow diagram and the output being the visual representation that the user can see.

[0893] Step 7:

[0894] The user adds explanations to the flow diagram for branches and missing parts. The explanations are collected as voice data using a microphone and sent to the terminal. The input is the voice of the explanations, and the output is digital voice data.

[0895] Step 8:

[0896] The terminal sends additional audio data to the server. The input is the audio data, and the output is the audio data transferred to the server.

[0897] Step 9:

[0898] The server converts the additional voice data into text data and modifies the original flow diagram, with the additional voice data as input and the modified text data and flow diagram as output.

[0899] Step 10:

[0900] The emotion engine analyzes the user's voice data and generates emotion data. The input is voice data and the output is emotion data. The revised flow diagram is optimized based on this emotion data.

[0901] Step 11:

[0902] The server generates issues and solutions based on the optimized flow diagram and using data from past business reform projects. The input is the optimized flow diagram, and the output is the issues and solutions.

[0903] Step 12:

[0904] The flow diagram, problem, and solution generated by the server are created as slides. The input is the optimized flow diagram and solution, and the output is the slides.

[0905] Step 13:

[0906] The server generates a video based on the slides. The input is the slides, and the output is a video file.

[0907] Step 14:

[0908] The device provides the generated video to the user. The input is a video file, and the output is a visual representation of the video.

[0909] Step 15:

[0910] Factory robots carry out tasks based on the generated workflow diagram. The input is the optimized workflow diagram, and the output is the business process to be executed.

[0911] 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.

[0912] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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.

[0913] 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.

[0914] [Third embodiment]

[0915] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0916] 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.

[0917] 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).

[0918] 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.

[0919] 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.

[0920] 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).

[0921] 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.

[0922] 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.

[0923] 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.

[0924] 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.

[0925] 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.

[0926] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0927] This invention relates to a system in which a user verbally explains a workflow, a voice recognition AI converts the explanation into text data, and then analyzes it to generate and modify a workflow diagram, presenting business issues and improvement measures. This system is composed of a user, a terminal, and a server.

[0928] Initial Setup

[0929] First, as an initial setup of the system, the user accesses a terminal (e.g., a PC or smartphone) and launches an interface to begin explaining the business flow. This assumes that the terminal has a microphone for voice input.

[0930] Workflow explanation and voice recognition

[0931] The user verbally explains the workflow into the device's microphone. For example, the user might say, "First, submit the application form at the reception desk, and then enter the data for confirmation." This voice data is collected by the device and sent to the server.

[0932] The server receives the voice data and converts it into text using speech recognition AI, for example, "First, submit your application form at the reception desk, then enter the data for confirmation."

[0933] Initial generation of flow diagram

[0934] The server generates an initial version of the workflow diagram based on the text data. For example, the server automatically generates a workflow diagram in the format of "Reception -> Application Submission -> Data Entry." This initial workflow diagram is sent from the server to the terminal, which then displays it to the user.

[0935] Modifying the flow diagram

[0936] The user checks the initial flow diagram and adds or modifies it as necessary. For example, the user may add an explanation such as, "After entering the data, I will decide whether to approve or reject it once the confirmation process is complete." This explanation is also collected by the device's microphone and sent to the server.

[0937] The server converts the additional voice data into text and adds branches and missing parts to the original flow diagram. This completes the flow diagram, for example, "Data entry -> Confirmation work -> (Approval or rejection)." The corrected flow diagram is then sent back to the terminal from the server and displayed to the user.

[0938] Presenting the problem and solution

[0939] The server uses a generative AI model to generate issues and improvement measures based on data from past business reform projects. For example, the server generates an improvement suggestion such as "data entry can be automated," and the terminal displays this suggestion to the user.

[0940] Creating slide decks and videos

[0941] The server creates slide decks based on the generated workflow diagrams, problems, and solutions. These slide decks are created using Microsoft tools and sent to the terminal, which displays them to the user.

[0942] Finally, the server generates a video based on the slides. This video includes an explanation of the business flow, the challenges, and solutions. The generated video is sent to the terminal and provided to the user.

[0943] Specific examples

[0944] For example, if the user explains, "First, submit the application form at the reception desk, then enter the data for confirmation. After entering the data, once the confirmation process is complete, we will make a decision to approve or reject the application," the flow would be as follows:

[0945] 1. The user gives an explanation into the device's microphone.

[0946] 2. The device collects the voice data and sends it to the server.

[0947] 3. The server uses voice recognition AI to convert the voice data into text.

[0948] 4. The server generates the initial flow diagram "Reception -> Application submission -> Data entry" and the terminal displays it.

[0949] 5. The user provides additional explanation and adds a branch of "Data entry -> Confirmation -> (Approve or Reject)".

[0950] 6. The server modifies the flow diagram, and the terminal displays the modified flow diagram.

[0951] 7. The server generates problems and solutions based on past data, and the device displays them.

[0952] 8. The server creates the slides and the terminal displays them.

[0953] 9. Finally, the server generates the video and the device provides it to the user.

[0954] The above is a specific description of the embodiment for carrying out the present invention.

[0955] The processing flow will be explained below.

[0956] Step 1:

[0957] The user speaks into the device's microphone to explain the work flow verbally. For example, they might explain, "First, submit the application form at the reception desk, and then enter the data for confirmation."

[0958] Step 2:

[0959] The terminal collects the user's explanation as voice data and transmits the voice data to the server.

[0960] Step 3:

[0961] The server receives the voice data, passes it to a speech recognition AI, and converts it into text data. For example, it converts it into text such as, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[0962] Step 4:

[0963] The server analyzes the text data and generates an initial version of the workflow diagram. For example, it generates an initial workflow diagram called "Reception -> Application Submission -> Data Entry."

[0964] Step 5:

[0965] The server sends the generated initial flow diagram to the terminal, which displays it to the user.

[0966] Step 6:

[0967] The user checks the initial flow diagram and adds explanations of branches and missing parts. For example, "After data entry, once the confirmation work is completed, a decision will be made on whether to approve or reject."

[0968] Step 7:

[0969] The terminal collects the user's additional explanation as voice data and transmits it again to the server.

[0970] Step 8:

[0971] The server passes the additional voice data to a voice recognition AI, converts it into text data, and adds branches or missing parts to the original flow diagram. For example, it generates a revised flow diagram such as "Data entry -> Confirmation work -> (Approval or rejection)."

[0972] Step 9:

[0973] The server sends the modified flow diagram to the terminal, which displays it to the user.

[0974] Step 10:

[0975] The server uses the generated AI model to generate issues and improvement measures based on data from past business reform projects. For example, it generates an improvement suggestion that "data entry can be automated."

[0976] Step 11:

[0977] The server sends the generated issues and solutions to the terminal, which then displays them to the user.

[0978] Step 12:

[0979] The server creates slide decks using Microsoft tools based on the generated business flow diagrams, issues, and solutions.

[0980] Step 13:

[0981] The server transmits the created slide material to the terminal, which then displays the slide material to the user.

[0982] Step 14:

[0983] The server generates a video based on the slides.

[0984] Step 15:

[0985] The server transmits the generated video to the terminal, which then provides the video to the user.

[0986] Example 1

[0987] Next, a description will be given of 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."

[0988] Conventional methods for creating business flowcharts require time and effort to collect and record business procedures, making it difficult to do so efficiently. Furthermore, when reflecting changes or improvements to procedures, it is often necessary to recreate them from scratch, which is also inefficient. Furthermore, there is also the problem that it is difficult to effectively utilize past data when identifying issues or proposing improvements.

[0989] 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.

[0990] In this invention, the server includes means for converting voice data into text data using acoustic analysis artificial intelligence, means for analyzing the text data to generate an initial procedure diagram, and means for creating an electronic document containing the generated procedure diagram, problems, and solutions. This makes it possible to efficiently generate a flowchart using only an oral explanation of the business procedure, and to quickly identify and propose problems and improvements.

[0991] "User" refers to a person who verbally explains business procedures.

[0992] "Terminal" refers to an electronic device for collecting voice data and displaying information to a user.

[0993] "Acoustic analysis artificial intelligence" refers to an intelligent system that uses technology to convert voice data into text data.

[0994] "Text data" refers to character information converted from audio data.

[0995] "Initial procedure diagram" refers to the first version of the business flow generated by analyzing text data.

[0996] A "procedure diagram" is a diagram that visually represents each step of a task.

[0997] "Branch" refers to an element in a procedure diagram that indicates multiple options or directions of progression.

[0998] "Missing parts" refer to elements or information that need to be added to the procedure diagram.

[0999] "Past work reform case data" refers to records and information relating to work reforms that have been implemented in the past.

[1000] "Issues" refer to problems in current business procedures that need improvement.

[1001] "Solution" refers to the improvement measures or methods proposed for a problem.

[1002] "Electronic document" refers to materials or reports created in digital format.

[1003] "Video" refers to materials in digital format that contain both audio and video.

[1004] This invention relates to a system in which a user verbally explains a business procedure, and an acoustic analysis AI converts the explanation into text data, which is then analyzed to generate and modify a business flow diagram, and presents business issues and improvement measures. This system is composed of a user, a terminal, and a server.

[1005] First, the user accesses a device such as a PC or smartphone and launches an interface to begin explaining the business flow. The device must have a microphone for voice input.

[1006] The user verbally explains the workflow into the device's microphone. For example, the user might say, "First, submit the application form at the reception desk, and then enter the data for confirmation." This voice data is collected by the device and sent to the server.

[1007] The server receives the voice data and converts it into text data using acoustic analysis artificial intelligence (e.g., a voice recognition algorithm), for example, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[1008] The server generates an initial version of the workflow diagram based on the text data. For example, the server automatically generates a workflow diagram in the format of "Reception -> Application Submission -> Data Entry." This initial workflow diagram is sent from the server to the terminal, which then displays it to the user.

[1009] The user checks the initial flow diagram and adds or modifies it as necessary. For example, the user may add an explanation such as, "After entering the data, I will decide whether to approve or reject it once the confirmation process is complete." This explanation is also collected by the device's microphone and sent to the server.

[1010] The server converts the additional voice data into text and adds branches and missing parts to the original flow diagram. This completes the flow diagram, for example, "Data entry -> Confirmation work -> (Approval or rejection)." The corrected flow diagram is then sent back to the terminal from the server and displayed to the user.

[1011] The server uses a generative AI model (such as an advanced natural language processing model) to generate issues and improvement measures based on data from past business reform projects. For example, the server generates an improvement proposal such as "data entry can be automated," and the terminal displays this proposal to the user.

[1012] Finally, the server creates an electronic document based on the generated business flow diagram, problems, and solutions. This electronic document is created using a general presentation tool and sent to the terminal, where it is displayed to the user.

[1013] Finally, the server generates a video based on the electronic document. This video contains an explanation of the business flow, the challenges, and solutions. The generated video is sent to the terminal and provided to the user.

[1014] As a concrete example, the following prompt sentence is input to the generative AI model:

[1015] User workflow description:

[1016] "First, you submit an application form at the reception desk, and then the data is entered for verification. After the data is entered and the verification process is completed, a decision is made as to whether the application will be approved or rejected."

[1017] Based on this workflow, please create an initial workflow diagram, present the issues and solutions, and also create an electronic document and video.

[1018] In this manner, the present invention enables a user to quickly and efficiently generate a business flowchart, identify problems, and propose improvements simply by verbally explaining the business procedures.

[1019] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1020] Step 1:

[1021] The user launches the terminal interface.

[1022] Input: User initiated interface action.

[1023] How it works: The user launches an interface to begin explaining the business flow from an application or web browser on a device such as a PC or smartphone.

[1024] Output: The interface is displayed on the terminal.

[1025] Step 2:

[1026] The user verbally explains the business flow.

[1027] Input: User's voice.

[1028] Operation: The user verbally explains the workflow steps into the device's microphone. For example, "First, submit the application form at the reception desk, and then enter the data for confirmation."

[1029] Output: The device collects the audio data of the explanation.

[1030] Step 3:

[1031] The terminal transmits the voice data to the server.

[1032] Input: Audio data.

[1033] Operation: The device sends the collected voice data to the server. Before sending, the data is reformatted and transferred to the server via the network.

[1034] Output: The audio data arrives at the server.

[1035] Step 4:

[1036] The server converts the voice data into text data.

[1037] Input: Audio data.

[1038] How it works: The server uses acoustic analysis artificial intelligence (voice recognition AI) to convert the received voice data into text data. For example, it generates text data such as "First, submit the application form at the reception desk, then enter the data for confirmation."

[1039] Output: Text data.

[1040] Step 5:

[1041] The server analyzes the text data and generates an initial procedure diagram.

[1042] Input: Text data.

[1043] Operation: The server analyzes the text data and extracts each step of the process for each sentence. Based on the extracted steps, it generates an initial version of the workflow diagram. For example, it creates a flow diagram called "Reception -> Application Submission -> Data Entry."

[1044] Output: Initial procedure diagram.

[1045] Step 6:

[1046] The server sends the initial procedure diagram to the terminal, which displays it.

[1047] Input: Initial procedure diagram.

[1048] Operation: The server sends the generated initial procedure diagram to the terminal, which then displays the received procedure diagram to the user.

[1049] Output: User confirms initial procedure diagram.

[1050] Step 7:

[1051] The user provides additional explanations for the initial procedure diagram.

[1052] Input: Initial procedure diagram, additional user explanation voice.

[1053] Action: The user reviews the initial procedure diagram and provides additional information or corrections as needed. For example, they might explain, "After data entry, we will make a decision on whether to approve or reject the request once the review process is complete." The device collects this additional voice data.

[1054] Output: Collected audio data.

[1055] Step 8:

[1056] The terminal transmits the audio data of the additional explanation to the server.

[1057] Input: Additional audio data.

[1058] Operation: The device sends the collected additional voice data to the server. Before sending, the data is reformatted and transferred to the server via the network.

[1059] Output: Additional audio data arrives at the server.

[1060] Step 9:

[1061] The server converts the additional voice data into text data and corrects the procedure diagram.

[1062] Input: Additional audio data.

[1063] How it works: The server uses acoustic analysis AI to convert the additional voice data into text data. It then adds branches and missing parts to the existing flow diagram and modifies the procedure diagram. For example, it generates a final flow diagram that looks like "Data entry -> Confirmation work -> (Approval or rejection)."

[1064] Output: Revised procedure diagram.

[1065] Step 10:

[1066] The server transmits the correction procedure diagram to the terminal, which displays it.

[1067] Input: Correction procedure diagram.

[1068] Operation: The server sends the modified procedure diagram to the terminal, which displays the received procedure diagram to the user.

[1069] Output: The user checks the correction procedure diagram.

[1070] Step 11:

[1071] The server generates problems and solutions.

[1072] Input: Correction procedure diagram, past work reform case data.

[1073] How it works: The server uses a generative AI model to generate issues and solutions based on past work reform project data. For example, it generates improvement proposals such as "data entry can be automated."

[1074] Output: Challenges and solutions.

[1075] Step 12:

[1076] The server sends the problem and solution to the terminal, which displays it.

[1077] Input: Challenges and solutions.

[1078] Operation: The server sends the generated problem and solution to the terminal, which displays it to the user.

[1079] Output: User sees the problem and solution.

[1080] Step 13:

[1081] The server creates the electronic document.

[1082] Input: Procedure diagram, problem, solution.

[1083] Operation: The server creates an electronic document based on the generated procedure diagram, problem, and solution. This electronic document is created using a common presentation tool.

[1084] Output: Electronic document.

[1085] Step 14:

[1086] The server transmits the electronic document to the terminal, which displays it.

[1087] Input: Electronic document.

[1088] Operation: The server sends the completed electronic document to the terminal, which displays it to the user.

[1089] Output: The user reviews the electronic document.

[1090] Step 15:

[1091] The server generates the video.

[1092] Input: Electronic document.

[1093] How it works: The server generates a video based on the electronic document, which includes an explanation of the business process, the problem, and the solution.

[1094] Output: Video.

[1095] Step 16:

[1096] The server sends the video to the terminal and provides it to the user.

[1097] Input: Video.

[1098] Operation: The server sends the generated video to the device, which then provides it to the user, who then watches the video.

[1099] Output: User watches a video.

[1100] (Application example 1)

[1101] Next, a description will be given of Application 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."

[1102] Managing workflows at logistics centers is complex, and presenting clear workflows and improvement measures is essential for on-site workers to work efficiently and accurately. However, existing systems do not automatically generate workflows using voice input or provide real-time improvement suggestions, which places a heavy burden on workers and reduces work efficiency. Given this background, there is a need for a system that can quickly generate workflow diagrams using voice input and present improvement measures in real time.

[1103] 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.

[1104] In this invention, the server includes a means for a user to verbally explain a workflow, a means for a terminal to collect the user's explanation as voice data, a means for the server to convert the voice data into text data using voice recognition AI, a means for linking with a voice input function installed in a smart device, a means for displaying a workflow diagram on the smart device in real time, and a means for presenting improvement measures to a worker using the smart device. This enables a worker to simply explain a workflow through voice input, which is visualized in real time and immediately presented with improvement measures.

[1105] A "user" is a person who uses the system to explain and modify business processes.

[1106] A "terminal" is a device (such as a PC or smart device) that collects voice data, displays flow diagrams, and interfaces with the user.

[1107] A "server" is a computer system that performs a wide range of data processing, including converting and analyzing audio data, creating and modifying flow charts, presenting problems and solutions, and even creating slides and videos.

[1108] "Voice recognition AI" is an artificial intelligence technology that converts input voice data into text data.

[1109] "Text data" is character information obtained by converting voice data.

[1110] The "initial flow diagram" is the first version of the business flow generated by the server based on the voice description.

[1111] "Additional explanation" refers to the user verbally explaining further details or branches to the initial flow diagram.

[1112] "Past business process reform case data" refers to a data set of previously collected and analyzed business processes, and serves as reference material for generating issues and solutions.

[1113] "Issues" refer to problems in the current business flow or areas that need improvement.

[1114] "Solutions" refer to specific proposals and measures to resolve issues and improve business flow.

[1115] A "slide deck" is a presentation-style document that summarizes business flow diagrams, issues, solutions, etc.

[1116] "Video" refers to visual and audio content generated based on slide materials.

[1117] A "smart device" is a device (e.g., smart glasses, smartphone, etc.) that allows a user to verbally explain a business process and display a business process diagram and improvement measures on the screen in real time.

[1118] The "voice input function" is a function that allows a smart device to collect the user's voice and pass it on to the system.

[1119] "Real-time display" refers to the function of instantly processing user operations and explanations and displaying the results immediately.

[1120] A "worker" is a person who performs work at a logistics center.

[1121] This invention provides a system for streamlining workflow management in logistics centers. A user verbally explains the workflow, and a voice recognition AI analyzes the explanation, automatically generates and modifies a workflow diagram, and suggests issues and improvements.

[1122] First, the user puts on a smart device (e.g., smart glasses or a smartphone) and verbally explains the workflow. This explanation is collected as voice data through the smart device's microphone. The collected voice data is then sent directly to the server.

[1123] When the server receives the voice data, it converts it into text data using a speech recognition AI. This speech recognition AI can be, for example, the Google Cloud Speech-to-Text API. The converted text data is analyzed by a generative AI model for workflow analysis, and an initial workflow diagram is generated. An example of this generative AI model is the OpenAI API.

[1124] The generated initial flow diagram is sent from the server to the smart device and displayed to the user. The user checks the flow diagram and provides additional explanations by voice if necessary. The additional explanations are also collected through the smart device's microphone and sent to the server. The server converts the additional voice data into text data and corrects the flow diagram.

[1125] Furthermore, the server uses a generative AI model based on data from past business reform projects to propose issues and improvement measures. The proposed issues and improvement measures are displayed in real time on the smart device screen, allowing users to quickly implement countermeasures on-site.

[1126] Based on the generated business flow diagram and improvement measures, the server automatically creates slides. These slides are generated using, for example, the Python-pptx library. Finally, the server converts the slides into video format and generates a video using the MoviePy library. This video is then sent to the smart device and provided to the user.

[1127] As a concrete example, consider a situation where a user verbally explains, "First, we accept the cargo at the reception desk, then we sort it in the warehouse and prepare it for delivery." This system collects the voice data of the explanation and automatically generates a flow diagram such as "Reception -> Cargo Reception -> Sorting -> Delivery Preparation." The generative AI model then proposes "the issue of improving the efficiency of sorting is a problem, and an improvement plan to automate it."

[1128] An example of a prompt is:

[1129] Flowchart generation prompt:

[1130] "Translate the following workflow into a flow diagram: First, cargo is received at the reception desk, then it is sorted in the warehouse and prepared for delivery."

[1131] This system uses smart glasses or a smartphone to smoothly carry out the entire process from explaining the work flow to visualizing it and presenting improvement measures, significantly improving work efficiency at logistics centers.

[1132] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1133] Step 1:

[1134] The user verbally explains the workflow. The user verbally explains the workflow into the microphone on the smart device (smart glasses or smartphone). For example, the user might explain, "First, the cargo is received at the reception desk, then it is sorted in the warehouse and prepared for delivery."

[1135] Step 2:

[1136] The terminal collects the user's explanation as voice data. The terminal uses the smart device's microphone to collect the voice data in real time and transmits the voice data as is to the server. The output includes the collected voice data.

[1137] Step 3:

[1138] The server converts the voice data into text data using a voice recognition AI. The server then inputs the received voice data into a voice recognition AI such as Google Cloud Speech-to-Text API, and obtains text data as output, which is the voice converted into a string of characters. The converted text data then proceeds to the next analysis step.

[1139] Step 4:

[1140] The server analyzes the text data and generates an initial flow diagram. The server uses OpenAI's generative AI model to generate a flow diagram by inputting a prompt. Specifically, by inputting "Convert the following business flow into a flow diagram: text data," the server outputs an initial flow diagram such as "Reception -> Cargo Reception -> Sorting -> Delivery Preparation."

[1141] Step 5:

[1142] The terminal displays the initial flow diagram. The generated initial flow diagram is sent from the server to the smart device and displayed on the terminal display in real time, allowing the user to visually check the flow diagram.

[1143] Step 6:

[1144] The user provides additional explanations about branches and missing parts. While looking at the initial flow diagram, the user provides additional explanations (e.g., "After data entry, once confirmation work is completed, a decision will be made on whether to approve or reject the request.") by voice.

[1145] Step 7:

[1146] The terminal collects the additional explanation as voice data and transmits it again to the server. The microphone of the terminal collects the additional explanation and transmits it again to the server as voice data. The collected additional voice data is output.

[1147] Step 8:

[1148] The server converts the additional voice data into text data and modifies the flow diagram. The server again converts the additional voice data into text data using the Google Cloud Speech-to-Text API, and uses OpenAI's generative AI model to add and modify branches and missing parts of the flow diagram.

[1149] Step 9:

[1150] The server generates issues and solutions based on data from past business reform projects. The server references past data sets and uses a generative AI model to automatically generate issues in business flows and their solutions.

[1151] Step 10:

[1152] The server creates slides based on the generated flow diagrams, problems, and solutions. The server uses the python-pptx library to compile the flow diagrams, problems, and solutions into slide-format materials.

[1153] Step 11:

[1154] The server generates a video based on the slides. The server uses the moviepy library to convert the slides into a video, creating a video that conveys the content visually and audibly.

[1155] Step 12:

[1156] The terminal provides the video to the user. The generated video is sent from the server to the smart device and provided in a format that the user can easily view.

[1157] 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.

[1158] This invention combines a system in which a user verbally explains a business process, a voice recognition AI converts the explanation into text data, analyzes it, generates and modifies a business process diagram, and presents business issues and improvement measures, with an emotion engine that recognizes the user's emotions. This system consists of a user, a terminal, a server, and an emotion engine.

[1159] Initial Setup

[1160] First, as an initial setup of the system, the user accesses a terminal (e.g., a PC or smartphone) and launches an interface to begin explaining the business flow. This assumes that the terminal has a microphone for voice input.

[1161] Workflow explanation and voice recognition

[1162] The user verbally explains the workflow into the device's microphone. For example, the user might say, "First, I submit the application form at the reception desk, and then I enter the data for confirmation." This voice data is collected by the device and sent to the server. At the same time, the emotion engine runs, analyzing the user's emotions in real time.

[1163] Collecting Emotional Data

[1164] When the device collects voice data, the emotion engine analyzes the user's emotional state and generates emotion data. For example, if the user is feeling stressed, the emotion data is collected as additional information.

[1165] Conversion to text data and initial generation of flow diagrams

[1166] The server receives the voice data and converts it into text using speech recognition AI. For example, it may be converted into text that reads, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[1167] The server generates an initial version of the workflow diagram based on the text data. For example, it generates an initial workflow diagram called "Reception -> Application Submission -> Data Entry." This initial workflow diagram is sent from the server to the terminal, which displays it to the user.

[1168] Flowchart revision and emotional feedback

[1169] The user checks the initial flow diagram and adds or modifies it as necessary. For example, they might add, "After data entry, we will make a decision on whether to approve or reject the request once the review process is complete." This additional explanation is also collected by the device's microphone and sent to the server.

[1170] The server converts the additional voice data into text and adds branches and missing parts to the original flow diagram. This completes the flow diagram, for example, "Data Entry -> Confirmation -> (Approval or Rejection)." At the same time, it adjusts the revised flow diagram to avoid stress for the user, taking into account the emotional data generated by the emotion engine.

[1171] Presenting the problem and solution

[1172] The server uses a generative AI model to generate issues and improvement measures based on data from past business reform projects. For example, the server generates an improvement suggestion such as "data entry can be automated," and the terminal displays this suggestion to the user.

[1173] Furthermore, based on the emotional data, we propose solutions that take into account the user's emotional state, for example, by proposing automation of processes that tend to cause stress to the user.

[1174] Creating slide decks and videos

[1175] The server creates slide decks based on the generated workflow diagrams, problems, and solutions. These slide decks are created using Microsoft tools and sent to the terminal, which displays them to the user.

[1176] Finally, the server generates a video based on the slides. This video includes an explanation of the business flow, the challenges, and solutions. The generated video is sent to the terminal and provided to the user.

[1177] Specific examples

[1178] For example, if the user explains, "First, submit the application form at the reception desk, then enter the data for confirmation. After entering the data, once the confirmation process is complete, we will make a decision to approve or reject the application," the flow would be as follows:

[1179] 1. The user gives an explanation into the device's microphone.

[1180] 2. The device collects the voice data and sends it to the server. At the same time, the emotion engine analyzes the user's emotions and recognizes that they are feeling stressed.

[1181] 3. The server uses voice recognition AI to convert the voice data into text.

[1182] 4. The server generates the initial flow diagram "Reception -> Application submission -> Data entry" and the terminal displays it.

[1183] 5. The user provides additional explanation and adds a branch of "Data entry -> Confirmation -> (Approve or Reject)".

[1184] 6. The server modifies the flow chart and suggests a less stressful work sequence based on the emotion data. The modified flow chart is then displayed on the device.

[1185] 7. The server generates problems and solutions based on past data, and the device displays them.

[1186] 8. The server creates the slides and the terminal displays them.

[1187] 9. Finally, the server generates the video and the device provides it to the user.

[1188] The above is a specific description of the embodiment of the present invention. By combining an emotion engine, it is possible to advance business reform while taking into consideration the emotional state of the user.

[1189] The processing flow will be explained below.

[1190] Step 1:

[1191] The user speaks into the device's microphone to explain the work flow verbally. For example, they might explain, "First, submit the application form at the reception desk, and then enter the data for confirmation."

[1192] Step 2:

[1193] The device collects the user's explanation as voice data and sends it to the server. At the same time, the emotion engine analyzes the user's emotions in real time and generates emotion data.

[1194] Step 3:

[1195] The server receives the voice data, passes it to a speech recognition AI, and converts it into text data. For example, it converts it into text such as, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[1196] Step 4:

[1197] The server analyzes the text data and generates an initial version of a workflow diagram. For example, it generates an initial workflow diagram called "Reception -> Application Submission -> Data Entry." It then sends this workflow diagram to the terminal, which displays it to the user.

[1198] Step 5:

[1199] The user checks the initial flow diagram and adds explanations of branches and missing parts as necessary. For example, they might add, "After data entry and confirmation, a decision will be made on whether to approve or reject the request." At the same time, the emotion engine continues to evaluate the user's emotions.

[1200] Step 6:

[1201] The terminal collects the user's additional explanation as voice data and transmits it again to the server.

[1202] Step 7:

[1203] The server passes the additional voice data to a voice recognition AI, converts it into text data, and adds branches or missing parts to the original flow diagram. For example, it generates a revised flow diagram such as "Data entry -> Confirmation work -> (Approval or rejection)."

[1204] Step 8:

[1205] The server sends the modified flow diagram to the terminal, which displays it to the user. At this time, the emotion engine provides an optimal flow diagram that is adjusted based on the emotional data analyzed to prevent the user from feeling stressed.

[1206] Step 9:

[1207] The server uses the generated AI model to generate issues and improvement measures based on data from past business reform projects. For example, the server may generate an improvement suggestion such as "data entry can be automated." Furthermore, it proposes solutions to issues that take into account the user's emotional state based on emotional data.

[1208] Step 10:

[1209] The server sends the generated issues and improvement measures to the device, which then displays them to the user. For example, the device may suggest, "By promoting automation of data entry, we can reduce stress."

[1210] Step 11:

[1211] The server uses Microsoft tools to create slides based on the generated workflow diagram, issues, and solutions, and then sends the slides to the terminal, which displays them to the user.

[1212] Step 12:

[1213] The server generates a video based on the slides. The generated video is sent to the terminal, which then provides it to the user. For example, a video containing an explanation of a business process, problems, and solutions is provided.

[1214] The above are the specific processing steps for implementing the invention in combination with the emotion engine. By utilizing emotion data, it is possible to advance business reform while taking into account the user's emotional state.

[1215] Example 2

[1216] Next, a description will be given of 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."

[1217] The main function of conventional workflow creation systems is to convert a user's verbal explanation into text data and generate a workflow diagram. However, if workflows or solutions to problems are proposed without taking the user's emotional state into consideration, the user may feel stressed or the workflow may not be applicable in the actual workplace. Furthermore, proposals for automating parts of a process that the user is unfamiliar with are insufficient, resulting in issues with the inability to achieve business process optimization. Against this background, the present invention aims to provide a system that proposes more flexible and considerate workflows and solutions to problems, taking into account the user's emotional data.

[1218] 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.

[1219] In this invention, the server includes: means for a user to verbally explain a business process; means for a terminal to collect the user's explanation as voice data; means for the server to convert the voice data into text data using a voice recognition AI; means for the server to analyze the text data and generate an initial flow diagram; means for the terminal to display the initial flow diagram; means for the user to add explanations regarding branches and missing parts; means for the terminal to collect the additional explanation as voice data and send it back to the server; means for the server to convert the additional voice data into text data and correct the flow diagram; means for the server to generate problems and solutions based on past business process improvement case data using a generative AI model; means for the server to create slides containing the generated flow diagram, problems, and solutions; means for the server to generate videos based on the slide documents; means for the terminal to provide the videos to the user; means for an emotion engine installed in the terminal to analyze and collect user emotion data simultaneously with the voice data; and means for the server to adjust the business process diagram and problem-solving solutions based on the emotion data. This enables the generation of business process diagrams and problem-solving solutions that take user emotion data into consideration.

[1220] "Business flow" refers to a series of work procedures and processes for progressing a business.

[1221] "Verbal explanation" refers to the act of a user explaining a business flow or task using voice.

[1222] "Terminal" refers to an electronic device (such as a PC, smartphone, or tablet) that allows users to input voice and display information.

[1223] "Voice data" refers to data that is a digital record of voice information input by a user through a terminal.

[1224] "Voice recognition AI" refers to artificial intelligence technology that analyzes voice data and converts it into text data.

[1225] "Text data" refers to character information converted by voice recognition.

[1226] An "initial flow diagram" refers to a diagram showing an initial version of a business flow process generated based on a user's description.

[1227] "Branch" refers to a point within a business flow where processes branch off into different steps or outcomes.

[1228] "Modification" refers to the act of adding new information or changes to an existing Workflow diagram.

[1229] A "generative AI model" refers to an artificial intelligence model that generates new problems and solutions based on past business data.

[1230] "Issues" refer to problems found within the business flow or points that require improvement.

[1231] "Solution" refers to a specific method or proposal for solving the problem that has been discovered.

[1232] "Slide materials" refers to materials used to visually organize and present information such as business flow diagrams, issues, and solutions.

[1233] "Video" refers to visual content that visually depicts the contents of slide materials, explanations of business processes, issues, and solutions.

[1234] "Emotion engine" refers to software or hardware for analyzing a user's emotional state and generating emotion data.

[1235] "Emotion data" refers to data that indicates the user's emotional state as analyzed by the emotion engine.

[1236] "Adjustment" refers to the act of improving workflow diagrams and solutions based on user emotional data.

[1237] This invention combines a system in which a user verbally explains a business process, a voice recognition AI converts the explanation into text data, and then analyzes it to generate and modify a business process diagram, presenting business issues and improvement measures, with an emotion engine that recognizes the user's emotions. This system consists of a user, a terminal, a server, and an emotion engine. The system configuration and operation are explained in detail below.

[1238] System configuration

[1239] The system uses the following hardware and software:

[1240] Device: An electronic device such as a PC, smartphone, or tablet that is equipped with a microphone for voice input and a display.

[1241] Server: A high-performance computer server that contains the software environment for running speech recognition AI and generative AI models.

[1242] Emotion engine: Software or hardware that analyzes emotional data from a user's voice in real time.

[1243] Workflow explanation and voice recognition

[1244] The user verbally explains the workflow using the device's microphone. For example, they might say, "First, submit the application form at the reception desk, and then enter the data for confirmation." The device collects this voice data and sends it to the server. At the same time, the device's built-in emotion engine analyzes the user's emotional state in real time, generating and collecting emotion data.

[1245] Conversion to text data and generation of flow diagrams

[1246] The server receives the voice data and converts it into text data using speech recognition AI. Based on the converted text data, the server generates an initial version of the business flow diagram. For example, a flow diagram of "Reception -> Application submission -> Data entry" is generated. This initial flow diagram is sent to the terminal and displayed to the user.

[1247] Flowchart revision and emotional feedback

[1248] The user checks the initial flow diagram and provides additional explanations or corrections. For example, they might explain, "After data entry, we will make a decision on whether to approve or reject the request once the review process is complete." This additional explanation is also collected by the device's microphone and resent to the server. The server converts the additional voice data into text data and reflects the corrections in the original flow diagram. At the same time, it suggests a work order that is less stressful based on emotional data.

[1249] Presenting the problem and solution

[1250] The server uses a generative AI model to extract issues and solutions from past business data. For example, it generates specific improvement measures, such as "data entry can be automated," and displays these to the user on the device. It also makes suggestions based on emotional data, such as automating parts that cause stress to the user.

[1251] Creating slide decks and videos

[1252] The server creates slides based on the generated workflow diagram, issues, and solutions. The slides are created using Microsoft software. The created slides are sent to the terminal and displayed to the user. Finally, the server generates a video based on the slides, which is also sent to the terminal and provided to the user.

[1253] Specific examples

[1254] For example, if the user explains, "First, submit the application form at the reception desk, then enter the data for confirmation. After the data is entered, once the confirmation process is complete, we will make a decision on whether to approve or reject the application," the following is an example of a prompt sentence:

[1255] User: "I'll first submit the application form at the reception desk, then I'll enter the data for verification."

[1256] User: "After entering the data, we will make a decision on whether to approve or reject it once the review process is complete."

[1257] In this way, by combining an emotion engine, the present invention can generate and improve workflows while taking into account the emotional state of the user.

[1258] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1259] Step 1: Initial Setup

[1260] To begin explaining a business flow, a user accesses a terminal (such as a PC or smartphone), confirms that the microphone for voice input is properly connected, and then launches the interface. The terminal displays the interface, and the user confirms that it is ready. This operation itself does not involve any specific input, and the output is the interface's startup status.

[1261] Step 2: Explanation of the business flow and voice recognition

[1262] The user verbally explains the workflow into the device's microphone. The input is the user's voice, and for example, an explanation such as "First, submit the application form at the reception desk, and then enter the data for confirmation" is collected as voice data. The device sends the voice data to the server. The device's emotion engine also analyzes the user's emotional state in real time and generates emotion data. The output is the voice data and emotion data sent to the server.

[1263] Step 3: Convert to text data

[1264] The server converts the received voice data into text data using voice recognition AI. The input is voice data, and voice recognition is performed as data processing, generating text data such as "First, submit the application form at the reception desk, then enter the data for confirmation." The output is the converted text data.

[1265] Step 4: Generate the initial flow diagram

[1266] The server analyzes the generated text data and generates an initial version of the workflow diagram. The input is text data, and the workflow is analyzed as data processing, generating a flow diagram of "Reception -> Application submission -> Data entry." The output is the initial flow diagram, which is sent to the terminal and displayed.

[1267] Step 5: Add explanations and modify the flow diagram

[1268] The user checks the initial flow diagram displayed on the terminal and provides additional explanations as necessary. The input is the user's additional voice explanation, for example, "After data entry, once confirmation work is completed, a decision will be made on whether to approve or reject." This voice data is also collected by the terminal and sent back to the server. The server converts the additional voice data into text data and reflects the corrections in the original flow diagram. The corrected flow diagram will be "Data entry -> Confirmation work -> (Approval or rejection)." The output is the corrected flow diagram.

[1269] Step 6: Emotional feedback and regulation

[1270] The server analyzes the emotion data generated by the emotion engine and adjusts the revised flow diagram so that the user feels less stressed. The input is the emotion data and the revised flow diagram, and emotion analysis is performed as data processing. For example, stress points are identified and adjustments are made based on that. The output is the adjusted flow diagram that takes the emotion data into account.

[1271] Step 7: Generate problems and solutions

[1272] The server uses a generative AI model to generate issues and solutions based on past business data. The input is the modified flow diagram and past business data, and data analysis generates specific solutions, such as "data entry can be automated." The output is the issue and solution, which is sent to the terminal and displayed to the user.

[1273] Step 8: Create your slide deck

[1274] The server creates slides based on the generated business flow diagram, issues, and solutions. The inputs are the flow diagram, issues, and solutions, and slides are created using Microsoft software. The output is the slides, which are sent to the terminal and displayed to the user.

[1275] Step 9: Create and deliver your video

[1276] The server generates a video based on the slides. The input is the slides, and the video is generated using video creation software. The output is the completed video, which is sent to the terminal and presented to the user.

[1277] (Application example 2)

[1278] Next, a description will be given of Application 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."

[1279] Conventional workflow diagram generation systems lack feedback that takes into account the user's emotional state, which can lead to stressful processes, especially in factory operations. This can lead to insufficient optimization of factory robot operations, resulting in reduced productivity and increased risk of errors. Furthermore, there is a lack of a way to effectively incorporate the workflow explained by on-site managers into the robots.

[1280] 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.

[1281] In this invention, the server includes a means for converting voice data into text data using a voice recognition AI, a means for an emotion engine to analyze the user's emotion data and reflect the result as feedback when generating and modifying a workflow diagram, and a means for a factory robot to perform work based on the generated workflow diagram. This allows a more optimized workflow diagram to be generated taking into account the user's emotional state, enabling the factory robot to perform work efficiently based on the workflow diagram.

[1282] "User" refers to a person who verbally explains the business flow.

[1283] "Terminal" refers to a device that collects user explanations as voice data and displays or transmits them.

[1284] "Audio data" refers to a conversion of a user's verbal description into digital data.

[1285] A "server" refers to a device that converts voice data into text data using voice recognition AI and performs processes such as analysis, generation, and transmission.

[1286] "Voice recognition AI" refers to artificial intelligence technology that converts voice data into text data.

[1287] "Text data" refers to text-format data converted by voice recognition AI.

[1288] "Initial flow diagram" refers to the initial version of the business flow generated by analyzing text data.

[1289] "Display" refers to the terminal visually presenting information such as a workflow diagram to the user.

[1290] "Additional explanation" refers to new verbal explanation given by the user to the flow diagram.

[1291] "Emotion engine" refers to an engine that analyzes the user's emotion data and reflects it as feedback in the generation and modification of business flow diagrams.

[1292] "Feedback" refers to the process of reflecting the analysis results of the emotion engine in the generation and modification of business flow diagrams.

[1293] A "factory robot" refers to a machine that actually carries out work based on the generated business flow diagram.

[1294] "Issues" refer to problems that need to be solved within the business flow.

[1295] "Solution" refers to a proposal or method for solving a problem.

[1296] "Slide deck" refers to a presentation-style deck that includes the generated flow diagram, problem, and solution.

[1297] "Video" refers to a dynamic file that provides visual information based on slide presentations.

[1298] The system for implementing this invention utilizes voice recognition AI and an emotion engine to efficiently convert the business flow explained orally by the user into text data, analyze it, and generate, modify, and display a business flow diagram, which factory robots use to carry out their work.

[1299] Hardware and software used

[1300] Hardware:

[1301] microphone

[1302] Factory robots

[1303] Device (e.g. PC, smartphone)

[1304] software:

[1305] Python

[1306] SpeechRecognition Library

[1307] EmotionRecognition Library

[1308] TextToFlowchart Library

[1309] ImprovementSuggestions Library

[1310] Processing flow

[1311] Step 1: A user verbally explains the workflow, and audio data is collected using a microphone. This audio data is sent to the server via the terminal.

[1312] Step 2: The server uses speech recognition AI to convert the voice data into text data, which is then analyzed to generate an initial flow diagram. This initial flow diagram is then sent to the device and displayed to the user.

[1313] Step 3: The user checks the initial flow diagram on the terminal and adds explanations for branches or missing parts as needed. This is also collected as voice data using a microphone and sent back to the server.

[1314] Step 4: The server converts the additional voice data into text data and modifies the original workflow diagram. Furthermore, the emotion engine analyzes the user's emotional state and reflects emotional data such as stress as feedback in modifying the workflow diagram.

[1315] Step 5: Based on the revised workflow diagram, the server generates issues and solutions using data from past business reform projects. The generated workflow diagram, issues, and solutions are created as slides and sent to the terminal.

[1316] Step 6: The server generates a video based on the slides, and the device provides the video to the user. Finally, the factory robot performs the work based on the generated workflow diagram.

[1317] Specific examples

[1318] For example, a factory manager might explain his work as follows:

[1319] "We first receive the raw materials, then we inspect them for quality. If there are no problems, we start assembling them into parts."

[1320] Prompt Sentence Examples

[1321] Explain verbally the workflow of your factory, for example, "We first receive the raw materials, then inspect them for quality. If there are no problems, we start assembling them into parts."

[1322] This system takes into account the user's emotional state to generate more optimized workflow diagrams, enabling factory robots to carry out their work efficiently based on these diagrams.

[1323] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1324] Step 1:

[1325] The user verbally explains the workflow. The microphone is used to collect voice data and send it to the terminal. The user's voice is taken as input and digital voice data is generated as output.

[1326] Step 2:

[1327] The terminal sends the collected voice data to the server. The input is the voice data, and the output is the voice data transferred to the server.

[1328] Step 3:

[1329] The server uses voice recognition AI to convert the voice data into text data. The input is the voice data, and the output is the corresponding text data. The text data represents an outline of the business flow.

[1330] Step 4:

[1331] The server analyzes the text data and generates an initial flow diagram. The input is text data and the output is the initial flow diagram. Natural Language Processing technology is used for the analysis.

[1332] Step 5:

[1333] The server sends the generated initial flow diagram to the terminal. The input is the initial flow diagram, and the output is the flow diagram transferred to the terminal.

[1334] Step 6:

[1335] The terminal displays the initial flow diagram to the user, with the input being the initial flow diagram and the output being the visual representation that the user can see.

[1336] Step 7:

[1337] The user adds explanations to the flow diagram for branches and missing parts. The explanations are collected as voice data using a microphone and sent to the terminal. The input is the voice of the explanations, and the output is digital voice data.

[1338] Step 8:

[1339] The terminal sends additional audio data to the server. The input is the audio data, and the output is the audio data transferred to the server.

[1340] Step 9:

[1341] The server converts the additional voice data into text data and modifies the original flow diagram, with the additional voice data as input and the modified text data and flow diagram as output.

[1342] Step 10:

[1343] The emotion engine analyzes the user's voice data and generates emotion data. The input is voice data and the output is emotion data. The revised flow diagram is optimized based on this emotion data.

[1344] Step 11:

[1345] The server generates issues and solutions based on the optimized flow diagram and using data from past business reform projects. The input is the optimized flow diagram, and the output is the issues and solutions.

[1346] Step 12:

[1347] The flow diagram, problem, and solution generated by the server are created as slides. The input is the optimized flow diagram and solution, and the output is the slides.

[1348] Step 13:

[1349] The server generates a video based on the slides. The input is the slides, and the output is a video file.

[1350] Step 14:

[1351] The device provides the generated video to the user. The input is a video file, and the output is a visual representation of the video.

[1352] Step 15:

[1353] Factory robots carry out tasks based on the generated workflow diagram. The input is the optimized workflow diagram, and the output is the business process to be executed.

[1354] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1355] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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.

[1356] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1357] [Fourth embodiment]

[1358] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1359] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1360] 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).

[1361] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1362] 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.

[1363] 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).

[1364] 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.

[1365] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1366] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1367] 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.

[1368] 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.

[1369] In the robot 414, 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.

[1370] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1371] This invention relates to a system in which a user verbally explains a workflow, a voice recognition AI converts the explanation into text data, and then analyzes it to generate and modify a workflow diagram, presenting business issues and improvement measures. This system is composed of a user, a terminal, and a server.

[1372] Initial Setup

[1373] First, as an initial setup of the system, the user accesses a terminal (e.g., a PC or smartphone) and launches an interface to begin explaining the business flow. This assumes that the terminal has a microphone for voice input.

[1374] Workflow explanation and voice recognition

[1375] The user verbally explains the workflow into the device's microphone. For example, the user might say, "First, submit the application form at the reception desk, and then enter the data for confirmation." This voice data is collected by the device and sent to the server.

[1376] The server receives the voice data and converts it into text using speech recognition AI, for example, "First, submit your application form at the reception desk, then enter the data for confirmation."

[1377] Initial generation of flow diagram

[1378] The server generates an initial version of the workflow diagram based on the text data. For example, the server automatically generates a workflow diagram in the format of "Reception -> Application Submission -> Data Entry." This initial workflow diagram is sent from the server to the terminal, which then displays it to the user.

[1379] Modifying the flow diagram

[1380] The user checks the initial flow diagram and adds or modifies it as necessary. For example, the user may add an explanation such as, "After entering the data, I will decide whether to approve or reject it once the confirmation process is complete." This explanation is also collected by the device's microphone and sent to the server.

[1381] The server converts the additional voice data into text and adds branches and missing parts to the original flow diagram. This completes the flow diagram, for example, "Data entry -> Confirmation work -> (Approval or rejection)." The corrected flow diagram is then sent back to the terminal from the server and displayed to the user.

[1382] Presenting the problem and solution

[1383] The server uses a generative AI model to generate issues and improvement measures based on data from past business reform projects. For example, the server generates an improvement suggestion such as "data entry can be automated," and the terminal displays this suggestion to the user.

[1384] Creating slide decks and videos

[1385] The server creates slide decks based on the generated workflow diagrams, problems, and solutions. These slide decks are created using Microsoft tools and sent to the terminal, which displays them to the user.

[1386] Finally, the server generates a video based on the slides. This video includes an explanation of the business flow, the challenges, and solutions. The generated video is sent to the terminal and provided to the user.

[1387] Specific examples

[1388] For example, if the user explains, "First, submit the application form at the reception desk, then enter the data for confirmation. After entering the data, once the confirmation process is complete, we will make a decision to approve or reject the application," the flow would be as follows:

[1389] 1. The user gives an explanation into the device's microphone.

[1390] 2. The device collects the voice data and sends it to the server.

[1391] 3. The server uses voice recognition AI to convert the voice data into text.

[1392] 4. The server generates the initial flow diagram "Reception -> Application submission -> Data entry" and the terminal displays it.

[1393] 5. The user provides additional explanation and adds a branch of "Data entry -> Confirmation -> (Approve or Reject)".

[1394] 6. The server modifies the flow diagram, and the terminal displays the modified flow diagram.

[1395] 7. The server generates problems and solutions based on past data, and the device displays them.

[1396] 8. The server creates the slides and the terminal displays them.

[1397] 9. Finally, the server generates the video and the device provides it to the user.

[1398] The above is a specific description of the embodiment for carrying out the present invention.

[1399] The processing flow will be explained below.

[1400] Step 1:

[1401] The user speaks into the device's microphone to explain the work flow verbally. For example, they might explain, "First, submit the application form at the reception desk, and then enter the data for confirmation."

[1402] Step 2:

[1403] The terminal collects the user's explanation as voice data and transmits the voice data to the server.

[1404] Step 3:

[1405] The server receives the voice data, passes it to a voice recognition AI, and converts it into text data. For example, it converts it into text such as, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[1406] Step 4:

[1407] The server analyzes the text data and generates an initial version of the workflow diagram. For example, it generates an initial workflow diagram called "Reception -> Application Submission -> Data Entry."

[1408] Step 5:

[1409] The server sends the generated initial flow diagram to the terminal, which displays it to the user.

[1410] Step 6:

[1411] The user checks the initial flow diagram and adds explanations of branches and missing parts. For example, "After data entry, once the confirmation work is completed, a decision will be made on whether to approve or reject."

[1412] Step 7:

[1413] The terminal collects the user's additional explanation as voice data and transmits it again to the server.

[1414] Step 8:

[1415] The server passes the additional voice data to a voice recognition AI, converts it into text data, and adds branches or missing parts to the original flow diagram. For example, it generates a revised flow diagram such as "Data entry -> Confirmation work -> (Approval or rejection)."

[1416] Step 9:

[1417] The server sends the modified flow diagram to the terminal, which displays it to the user.

[1418] Step 10:

[1419] The server uses the generated AI model to generate issues and improvement measures based on data from past business reform projects. For example, it generates an improvement suggestion that "data entry can be automated."

[1420] Step 11:

[1421] The server sends the generated issues and solutions to the terminal, which then displays them to the user.

[1422] Step 12:

[1423] The server creates slide decks using Microsoft tools based on the generated business flow diagrams, issues, and solutions.

[1424] Step 13:

[1425] The server transmits the created slide material to the terminal, which then displays the slide material to the user.

[1426] Step 14:

[1427] The server generates a video based on the slides.

[1428] Step 15:

[1429] The server transmits the generated video to the terminal, which then provides the video to the user.

[1430] Example 1

[1431] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1432] Conventional methods for creating business flowcharts require time and effort to collect and record business procedures, making it difficult to do so efficiently. Furthermore, when reflecting changes or improvements to procedures, it is often necessary to recreate them from scratch, which is also inefficient. Furthermore, there is also the problem that it is difficult to effectively utilize past data when identifying issues or proposing improvements.

[1433] 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.

[1434] In this invention, the server includes means for converting voice data into text data using acoustic analysis artificial intelligence, means for analyzing the text data to generate an initial procedure diagram, and means for creating an electronic document containing the generated procedure diagram, problems, and solutions. This makes it possible to efficiently generate a flowchart using only an oral explanation of the business procedure, and to quickly identify and propose problems and improvements.

[1435] "User" refers to a person who verbally explains business procedures.

[1436] "Terminal" refers to an electronic device for collecting voice data and displaying information to a user.

[1437] "Acoustic analysis artificial intelligence" refers to an intelligent system that uses technology to convert voice data into text data.

[1438] "Text data" refers to character information converted from audio data.

[1439] "Initial procedure diagram" refers to the first version of the business flow generated by analyzing text data.

[1440] A "procedure diagram" is a diagram that visually represents each step of a task.

[1441] "Branch" refers to an element in a procedure diagram that indicates multiple options or directions of progression.

[1442] "Missing parts" refer to elements or information that need to be added to the procedure diagram.

[1443] "Past work reform case data" refers to records and information relating to work reforms that have been implemented in the past.

[1444] "Issues" refer to problems in current business procedures that need improvement.

[1445] "Solution" refers to the improvement measures or methods proposed for a problem.

[1446] "Electronic document" refers to materials or reports created in digital format.

[1447] "Video" refers to materials in digital format that contain both audio and video.

[1448] This invention relates to a system in which a user verbally explains a business procedure, and an acoustic analysis AI converts the explanation into text data, which is then analyzed to generate and modify a business flow diagram, and presents business issues and improvement measures. This system is composed of a user, a terminal, and a server.

[1449] First, the user accesses a device such as a PC or smartphone and launches an interface to begin explaining the business flow. The device must have a microphone for voice input.

[1450] The user verbally explains the workflow into the device's microphone. For example, the user might say, "First, submit the application form at the reception desk, and then enter the data for confirmation." This voice data is collected by the device and sent to the server.

[1451] The server receives the voice data and converts it into text data using acoustic analysis artificial intelligence (e.g., a voice recognition algorithm), for example, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[1452] The server generates an initial version of the workflow diagram based on the text data. For example, the server automatically generates a workflow diagram in the format of "Reception -> Application Submission -> Data Entry." This initial workflow diagram is sent from the server to the terminal, which then displays it to the user.

[1453] The user checks the initial flow diagram and adds or modifies it as necessary. For example, the user may add an explanation such as, "After entering the data, I will decide whether to approve or reject it once the confirmation process is complete." This explanation is also collected by the device's microphone and sent to the server.

[1454] The server converts the additional voice data into text and adds branches and missing parts to the original flow diagram. This completes the flow diagram, for example, "Data entry -> Confirmation work -> (Approval or rejection)." The corrected flow diagram is then sent back to the terminal from the server and displayed to the user.

[1455] The server uses a generative AI model (such as an advanced natural language processing model) to generate issues and improvement measures based on data from past business reform projects. For example, the server generates an improvement suggestion such as "data entry can be automated," and the terminal displays this suggestion to the user.

[1456] Finally, the server creates an electronic document based on the generated business flow diagram, problems, and solutions. This electronic document is created using a general presentation tool and sent to the terminal, where it is displayed to the user.

[1457] Finally, the server generates a video based on the electronic document. This video contains an explanation of the business flow, the challenges, and solutions. The generated video is sent to the terminal and provided to the user.

[1458] As a concrete example, the following prompt sentence is input to the generative AI model:

[1459] User workflow description:

[1460] "First, you submit an application form at the reception desk, and then the data is entered for verification. After the data is entered and the verification process is completed, a decision is made as to whether the application will be approved or rejected."

[1461] Based on this workflow, please create an initial workflow diagram, present the issues and solutions, and also create an electronic document and video.

[1462] In this manner, the present invention enables a user to quickly and efficiently generate a business flowchart, identify problems, and propose improvements simply by verbally explaining the business procedures.

[1463] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1464] Step 1:

[1465] The user launches the terminal interface.

[1466] Input: User initiated interface action.

[1467] How it works: The user launches an interface to begin explaining the business flow from an application or web browser on a device such as a PC or smartphone.

[1468] Output: The interface is displayed on the terminal.

[1469] Step 2:

[1470] The user verbally explains the business flow.

[1471] Input: User's voice.

[1472] Operation: The user verbally explains the workflow steps into the device's microphone. For example, "First, submit the application form at the reception desk, and then enter the data for confirmation."

[1473] Output: The device collects the audio data of the explanation.

[1474] Step 3:

[1475] The terminal transmits the voice data to the server.

[1476] Input: Audio data.

[1477] Operation: The device sends the collected voice data to the server. Before sending, the data is reformatted and transferred to the server via the network.

[1478] Output: The audio data arrives at the server.

[1479] Step 4:

[1480] The server converts the voice data into text data.

[1481] Input: Audio data.

[1482] How it works: The server uses acoustic analysis artificial intelligence (voice recognition AI) to convert the received voice data into text data. For example, it generates text data such as "First, submit the application form at the reception desk, then enter the data for confirmation."

[1483] Output: Text data.

[1484] Step 5:

[1485] The server analyzes the text data and generates an initial procedure diagram.

[1486] Input: Text data.

[1487] Operation: The server analyzes the text data and extracts each step of the process for each sentence. Based on the extracted steps, it generates an initial version of the workflow diagram. For example, it creates a flow diagram called "Reception -> Application Submission -> Data Entry."

[1488] Output: Initial procedure diagram.

[1489] Step 6:

[1490] The server sends the initial procedure diagram to the terminal, which displays it.

[1491] Input: Initial procedure diagram.

[1492] Operation: The server sends the generated initial procedure diagram to the terminal, which then displays the received procedure diagram to the user.

[1493] Output: User confirms initial procedure diagram.

[1494] Step 7:

[1495] The user provides additional explanations for the initial procedure diagram.

[1496] Input: Initial procedure diagram, additional user explanation voice.

[1497] Action: The user reviews the initial procedure diagram and provides additional information or corrections as needed. For example, they might explain, "After data entry, we will make a decision on whether to approve or reject the request once the review process is complete." The device collects this additional voice data.

[1498] Output: Collected audio data.

[1499] Step 8:

[1500] The terminal transmits the audio data of the additional explanation to the server.

[1501] Input: Additional audio data.

[1502] Operation: The device sends the collected additional voice data to the server. Before sending, the data is reformatted and transferred to the server via the network.

[1503] Output: Additional audio data arrives at the server.

[1504] Step 9:

[1505] The server converts the additional voice data into text data and corrects the procedure diagram.

[1506] Input: Additional audio data.

[1507] How it works: The server uses acoustic analysis AI to convert the additional voice data into text data. It then adds branches and missing parts to the existing flow diagram and modifies the procedure diagram. For example, it generates a final flow diagram that looks like "Data entry -> Confirmation work -> (Approval or rejection)."

[1508] Output: Revised procedure diagram.

[1509] Step 10:

[1510] The server transmits the correction procedure diagram to the terminal, which displays it.

[1511] Input: Correction procedure diagram.

[1512] Operation: The server sends the modified procedure diagram to the terminal, which displays the received procedure diagram to the user.

[1513] Output: The user checks the correction procedure diagram.

[1514] Step 11:

[1515] The server generates problems and solutions.

[1516] Input: Correction procedure diagram, past work reform case data.

[1517] How it works: The server uses a generative AI model to generate issues and solutions based on past work reform project data. For example, it generates improvement proposals such as "data entry can be automated."

[1518] Output: Challenges and solutions.

[1519] Step 12:

[1520] The server sends the problem and solution to the terminal, which displays it.

[1521] Input: Challenges and solutions.

[1522] Operation: The server sends the generated problem and solution to the terminal, which displays it to the user.

[1523] Output: User sees the problem and solution.

[1524] Step 13:

[1525] The server creates the electronic document.

[1526] Input: Procedure diagram, problem, solution.

[1527] Operation: The server creates an electronic document based on the generated procedure diagram, problem, and solution. This electronic document is created using a common presentation tool.

[1528] Output: Electronic document.

[1529] Step 14:

[1530] The server transmits the electronic document to the terminal, which displays it.

[1531] Input: Electronic document.

[1532] Operation: The server sends the completed electronic document to the terminal, which displays it to the user.

[1533] Output: The user reviews the electronic document.

[1534] Step 15:

[1535] The server generates the video.

[1536] Input: Electronic document.

[1537] How it works: The server generates a video based on the electronic document, which includes an explanation of the business process, the problem, and the solution.

[1538] Output: Video.

[1539] Step 16:

[1540] The server sends the video to the terminal and provides it to the user.

[1541] Input: Video.

[1542] Operation: The server sends the generated video to the device, which then provides it to the user, who then watches the video.

[1543] Output: User watches a video.

[1544] (Application example 1)

[1545] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1546] Managing workflows at logistics centers is complex, and presenting clear workflows and improvement measures is essential for on-site workers to work efficiently and accurately. However, existing systems do not automatically generate workflows using voice input or provide real-time improvement suggestions, which places a heavy burden on workers and reduces work efficiency. Given this background, there is a need for a system that can quickly generate workflow diagrams using voice input and present improvement measures in real time.

[1547] 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.

[1548] In this invention, the server includes a means for a user to verbally explain a workflow, a means for a terminal to collect the user's explanation as voice data, a means for the server to convert the voice data into text data using voice recognition AI, a means for linking with a voice input function installed in a smart device, a means for displaying a workflow diagram on the smart device in real time, and a means for presenting improvement measures to a worker using the smart device. This enables a worker to simply explain a workflow through voice input, which is visualized in real time and immediately presented with improvement measures.

[1549] A "user" is a person who uses the system to explain and modify business processes.

[1550] A "terminal" is a device (such as a PC or smart device) that collects voice data, displays flow diagrams, and interfaces with the user.

[1551] A "server" is a computer system that performs a wide range of data processing, including converting and analyzing audio data, creating and modifying flow charts, presenting problems and solutions, and even creating slides and videos.

[1552] "Voice recognition AI" is an artificial intelligence technology that converts input voice data into text data.

[1553] "Text data" is character information obtained by converting voice data.

[1554] The "initial flow diagram" is the first version of the business flow generated by the server based on the voice description.

[1555] "Additional explanation" refers to the user verbally explaining further details or branches to the initial flow diagram.

[1556] "Past business process reform case data" refers to a data set of previously collected and analyzed business processes, and serves as reference material for generating issues and solutions.

[1557] "Issues" refer to problems in the current business flow or areas that need improvement.

[1558] "Solutions" refer to specific proposals and measures to resolve issues and improve business flow.

[1559] A "slide deck" is a presentation-style document that summarizes business flow diagrams, issues, solutions, etc.

[1560] "Video" refers to visual and audio content generated based on slide materials.

[1561] A "smart device" is a device (e.g., smart glasses, smartphone, etc.) that allows a user to verbally explain a business process and display a business process diagram and improvement measures on the screen in real time.

[1562] The "voice input function" is a function that allows a smart device to collect the user's voice and pass it on to the system.

[1563] "Real-time display" refers to the function of instantly processing user operations and explanations and displaying the results immediately.

[1564] A "worker" is a person who performs work at a logistics center.

[1565] This invention provides a system for streamlining workflow management in logistics centers. A user verbally explains the workflow, and a voice recognition AI analyzes the explanation, automatically generates and modifies a workflow diagram, and suggests issues and improvements.

[1566] First, the user puts on a smart device (e.g., smart glasses or a smartphone) and verbally explains the workflow. This explanation is collected as voice data through the smart device's microphone. The collected voice data is then sent directly to the server.

[1567] When the server receives the voice data, it converts it into text data using a speech recognition AI. This speech recognition AI can be, for example, the Google Cloud Speech-to-Text API. The converted text data is analyzed by a generative AI model for workflow analysis, and an initial workflow diagram is generated. An example of this generative AI model is the OpenAI API.

[1568] The generated initial flow diagram is sent from the server to the smart device and displayed to the user. The user checks the flow diagram and provides additional explanations by voice if necessary. The additional explanations are also collected through the smart device's microphone and sent to the server. The server converts the additional voice data into text data and corrects the flow diagram.

[1569] Furthermore, the server uses a generative AI model based on data from past business reform projects to propose issues and improvement measures. The proposed issues and improvement measures are displayed in real time on the smart device screen, allowing users to quickly implement countermeasures on-site.

[1570] Based on the generated business flow diagram and improvement measures, the server automatically creates slides. These slides are generated using, for example, the Python-pptx library. Finally, the server converts the slides into video format and generates a video using the MoviePy library. This video is then sent to the smart device and provided to the user.

[1571] As a concrete example, consider a situation where a user verbally explains, "First, we accept the cargo at the reception desk, then we sort it in the warehouse and prepare it for delivery." This system collects the voice data of the explanation and automatically generates a flow diagram such as "Reception -> Cargo Reception -> Sorting -> Delivery Preparation." The generative AI model then proposes "the issue of improving the efficiency of sorting is a problem, and an improvement plan to automate it."

[1572] An example of a prompt is:

[1573] Flowchart generation prompt:

[1574] "Translate the following workflow into a flow diagram: First, cargo is received at the reception desk, then it is sorted in the warehouse and prepared for delivery."

[1575] This system uses smart glasses or a smartphone to smoothly carry out the entire process from explaining the work flow to visualizing it and presenting improvement measures, significantly improving work efficiency at logistics centers.

[1576] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1577] Step 1:

[1578] The user verbally explains the workflow. The user verbally explains the workflow into the microphone on the smart device (smart glasses or smartphone). For example, the user might explain, "First, the cargo is received at the reception desk, then it is sorted in the warehouse and prepared for delivery."

[1579] Step 2:

[1580] The terminal collects the user's explanation as voice data. The terminal uses the smart device's microphone to collect the voice data in real time and transmits the voice data as is to the server. The output includes the collected voice data.

[1581] Step 3:

[1582] The server converts the voice data into text data using a voice recognition AI. The server then inputs the received voice data into a voice recognition AI such as Google Cloud Speech-to-Text API, and obtains text data as output, which is the voice converted into a string of characters. The converted text data then proceeds to the next analysis step.

[1583] Step 4:

[1584] The server analyzes the text data and generates an initial flow diagram. The server uses OpenAI's generative AI model to generate a flow diagram by inputting a prompt. Specifically, by inputting "Convert the following business flow into a flow diagram: text data," the server outputs an initial flow diagram such as "Reception -> Cargo Reception -> Sorting -> Delivery Preparation."

[1585] Step 5:

[1586] The terminal displays the initial flow diagram. The generated initial flow diagram is sent from the server to the smart device and displayed on the terminal display in real time, allowing the user to visually check the flow diagram.

[1587] Step 6:

[1588] The user provides additional explanations about branches and missing parts. While looking at the initial flow diagram, the user provides additional explanations (e.g., "After data entry, once confirmation work is completed, a decision will be made on whether to approve or reject the request.") by voice.

[1589] Step 7:

[1590] The terminal collects the additional explanation as voice data and transmits it again to the server. The microphone of the terminal collects the additional explanation and transmits it again to the server as voice data. The collected additional voice data is output.

[1591] Step 8:

[1592] The server converts the additional voice data into text data and modifies the flow diagram. The server again converts the additional voice data into text data using the Google Cloud Speech-to-Text API, and uses OpenAI's generative AI model to add and modify branches and missing parts of the flow diagram.

[1593] Step 9:

[1594] The server generates issues and solutions based on data from past business reform projects. The server references past data sets and uses a generative AI model to automatically generate issues in business flows and their solutions.

[1595] Step 10:

[1596] The server creates slides based on the generated flow diagrams, problems, and solutions. The server uses the python-pptx library to compile the flow diagrams, problems, and solutions into slide-format materials.

[1597] Step 11:

[1598] The server generates a video based on the slides. The server uses the moviepy library to convert the slides into a video, creating a video that conveys the content visually and audibly.

[1599] Step 12:

[1600] The terminal provides the video to the user. The generated video is sent from the server to the smart device and provided in a format that the user can easily view.

[1601] 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.

[1602] This invention combines a system in which a user verbally explains a business process, a voice recognition AI converts the explanation into text data, analyzes it, generates and modifies a business process diagram, and presents business issues and improvement measures, with an emotion engine that recognizes the user's emotions. This system consists of a user, a terminal, a server, and an emotion engine.

[1603] Initial Setup

[1604] First, as an initial setup of the system, the user accesses a terminal (e.g., a PC or smartphone) and launches an interface to begin explaining the business flow. This assumes that the terminal has a microphone for voice input.

[1605] Workflow explanation and voice recognition

[1606] The user verbally explains the workflow into the device's microphone. For example, the user might say, "First, I submit the application form at the reception desk, and then I enter the data for confirmation." This voice data is collected by the device and sent to the server. At the same time, the emotion engine runs, analyzing the user's emotions in real time.

[1607] Collecting Emotional Data

[1608] When the device collects voice data, the emotion engine analyzes the user's emotional state and generates emotion data. For example, if the user is feeling stressed, the emotion data is collected as additional information.

[1609] Conversion to text data and initial generation of flow diagrams

[1610] The server receives the voice data and converts it into text using speech recognition AI. For example, it may be converted into text that reads, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[1611] The server generates an initial version of the workflow diagram based on the text data. For example, it generates an initial workflow diagram called "Reception -> Application Submission -> Data Entry." This initial workflow diagram is sent from the server to the terminal, which displays it to the user.

[1612] Flowchart revision and emotional feedback

[1613] The user checks the initial flow diagram and adds or modifies it as necessary. For example, they might add, "After data entry, we will make a decision on whether to approve or reject the request once the review process is complete." This additional explanation is also collected by the device's microphone and sent to the server.

[1614] The server converts the additional voice data into text and adds branches and missing parts to the original flow diagram. This completes the flow diagram, for example, "Data Entry -> Confirmation -> (Approval or Rejection)." At the same time, it adjusts the revised flow diagram to avoid stress for the user, taking into account the emotional data generated by the emotion engine.

[1615] Presenting the problem and solution

[1616] The server uses a generative AI model to generate issues and improvement measures based on data from past business reform projects. For example, the server generates an improvement suggestion such as "data entry can be automated," and the terminal displays this suggestion to the user.

[1617] Furthermore, based on the emotional data, we propose solutions that take into account the user's emotional state, for example, by proposing automation of processes that tend to cause stress to the user.

[1618] Creating slide decks and videos

[1619] The server creates slide decks based on the generated workflow diagrams, problems, and solutions. These slide decks are created using Microsoft tools and sent to the terminal, which displays them to the user.

[1620] Finally, the server generates a video based on the slides. This video includes an explanation of the business flow, the challenges, and solutions. The generated video is sent to the terminal and provided to the user.

[1621] Specific examples

[1622] For example, if the user explains, "First, submit the application form at the reception desk, then enter the data for confirmation. After entering the data, once the confirmation process is complete, we will make a decision to approve or reject the application," the flow would be as follows:

[1623] 1. The user gives an explanation into the device's microphone.

[1624] 2. The device collects the voice data and sends it to the server. At the same time, the emotion engine analyzes the user's emotions and recognizes that they are feeling stressed.

[1625] 3. The server uses voice recognition AI to convert the voice data into text.

[1626] 4. The server generates the initial flow diagram "Reception -> Application submission -> Data entry" and the terminal displays it.

[1627] 5. The user provides additional explanation and adds a branch of "Data entry -> Confirmation -> (Approve or Reject)".

[1628] 6. The server modifies the flow chart and suggests a less stressful work sequence based on the emotion data. The modified flow chart is then displayed on the device.

[1629] 7. The server generates problems and solutions based on past data, and the device displays them.

[1630] 8. The server creates the slides and the terminal displays them.

[1631] 9. Finally, the server generates the video and the device provides it to the user.

[1632] The above is a specific description of the embodiment of the present invention. By combining an emotion engine, it is possible to advance business reform while taking into consideration the emotional state of the user.

[1633] The processing flow will be explained below.

[1634] Step 1:

[1635] The user speaks into the device's microphone to explain the work flow verbally. For example, they might explain, "First, submit the application form at the reception desk, and then enter the data for confirmation."

[1636] Step 2:

[1637] The device collects the user's explanation as voice data and sends it to the server. At the same time, the emotion engine analyzes the user's emotions in real time and generates emotion data.

[1638] Step 3:

[1639] The server receives the voice data, passes it to a speech recognition AI, and converts it into text data. For example, it converts it into text such as, "First, submit your application form at the reception desk, and then enter the data for confirmation."

[1640] Step 4:

[1641] The server analyzes the text data and generates an initial version of a workflow diagram. For example, it generates an initial workflow diagram called "Reception -> Application Submission -> Data Entry." It then sends this workflow diagram to the terminal, which displays it to the user.

[1642] Step 5:

[1643] The user checks the initial flow diagram and adds explanations of branches and missing parts as necessary. For example, they might add, "After data entry and confirmation, a decision will be made on whether to approve or reject the request." At the same time, the emotion engine continues to evaluate the user's emotions.

[1644] Step 6:

[1645] The terminal collects the user's additional explanation as voice data and transmits it again to the server.

[1646] Step 7:

[1647] The server passes the additional voice data to a voice recognition AI, converts it into text data, and adds branches or missing parts to the original flow diagram. For example, it generates a revised flow diagram such as "Data entry -> Confirmation work -> (Approval or rejection)."

[1648] Step 8:

[1649] The server sends the modified flow diagram to the terminal, which displays it to the user. At this time, the emotion engine provides an optimal flow diagram that is adjusted based on the emotional data analyzed to prevent the user from feeling stressed.

[1650] Step 9:

[1651] The server uses the generated AI model to generate issues and improvement measures based on data from past business reform projects. For example, the server may generate an improvement suggestion such as "data entry can be automated." Furthermore, it proposes solutions to issues that take into account the user's emotional state based on emotional data.

[1652] Step 10:

[1653] The server sends the generated issues and improvement measures to the device, which then displays them to the user. For example, the device may suggest, "By promoting automation of data entry, we can reduce stress."

[1654] Step 11:

[1655] The server uses Microsoft tools to create slides based on the generated workflow diagram, issues, and solutions, and then sends the slides to the terminal, which displays them to the user.

[1656] Step 12:

[1657] The server generates a video based on the slides. The generated video is sent to the terminal, which then provides it to the user. For example, a video containing an explanation of a business process, problems, and solutions is provided.

[1658] The above are the specific processing steps for implementing the invention in combination with the emotion engine. By utilizing emotion data, it is possible to advance business reform while taking into account the user's emotional state.

[1659] Example 2

[1660] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1661] The main function of conventional workflow creation systems is to convert a user's verbal explanation into text data and generate a workflow diagram. However, if workflows or solutions to problems are proposed without taking the user's emotional state into consideration, the user may feel stressed or the workflow may not be applicable in the actual workplace. Furthermore, proposals for automating parts of a process that the user is unfamiliar with are insufficient, resulting in issues with the inability to achieve business process optimization. Against this background, the present invention aims to provide a system that proposes more flexible and considerate workflows and solutions to problems, taking into account the user's emotional data.

[1662] 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.

[1663] In this invention, the server includes: means for a user to verbally explain a business process; means for a terminal to collect the user's explanation as voice data; means for the server to convert the voice data into text data using a voice recognition AI; means for the server to analyze the text data and generate an initial flow diagram; means for the terminal to display the initial flow diagram; means for the user to add explanations regarding branches and missing parts; means for the terminal to collect the additional explanation as voice data and send it back to the server; means for the server to convert the additional voice data into text data and correct the flow diagram; means for the server to generate problems and solutions based on past business process improvement case data using a generative AI model; means for the server to create slides containing the generated flow diagram, problems, and solutions; means for the server to generate videos based on the slide documents; means for the terminal to provide the videos to the user; means for an emotion engine installed in the terminal to analyze and collect user emotion data simultaneously with the voice data; and means for the server to adjust the business process diagram and problem-solving solutions based on the emotion data. This enables the generation of business process diagrams and problem-solving solutions that take user emotion data into consideration.

[1664] "Business flow" refers to a series of work procedures and processes for progressing a business.

[1665] "Verbal explanation" refers to the act of a user explaining a business flow or task using voice.

[1666] "Terminal" refers to an electronic device (such as a PC, smartphone, or tablet) that allows users to input voice and display information.

[1667] "Voice data" refers to data that is a digital record of voice information input by a user through a terminal.

[1668] "Voice recognition AI" refers to artificial intelligence technology that analyzes voice data and converts it into text data.

[1669] "Text data" refers to character information converted by voice recognition.

[1670] An "initial flow diagram" refers to a diagram showing an initial version of a business flow process generated based on a user's description.

[1671] "Branch" refers to a point within a business flow where processes branch off into different steps or outcomes.

[1672] "Modification" refers to the act of adding new information or changes to an existing Workflow diagram.

[1673] A "generative AI model" refers to an artificial intelligence model that generates new problems and solutions based on past business data.

[1674] "Issues" refer to problems found within the business flow or points that require improvement.

[1675] "Solution" refers to a specific method or proposal for solving the problem that has been discovered.

[1676] "Slide materials" refers to materials used to visually organize and present information such as business flow diagrams, issues, and solutions.

[1677] "Video" refers to visual content that visually depicts the contents of slide materials, explanations of business processes, issues, and solutions.

[1678] "Emotion engine" refers to software or hardware for analyzing a user's emotional state and generating emotion data.

[1679] "Emotion data" refers to data that indicates the user's emotional state as analyzed by the emotion engine.

[1680] "Adjustment" refers to the act of improving workflow diagrams and solutions based on user emotional data.

[1681] This invention combines a system in which a user verbally explains a business process, a voice recognition AI converts the explanation into text data, and then analyzes it to generate and modify a business process diagram, presenting business issues and improvement measures, with an emotion engine that recognizes the user's emotions. This system consists of a user, a terminal, a server, and an emotion engine. The system configuration and operation are explained in detail below.

[1682] System configuration

[1683] The system uses the following hardware and software:

[1684] Device: An electronic device such as a PC, smartphone, or tablet that is equipped with a microphone for voice input and a display.

[1685] Server: A high-performance computer server that contains the software environment for running speech recognition AI and generative AI models.

[1686] Emotion engine: Software or hardware that analyzes emotional data from a user's voice in real time.

[1687] Workflow explanation and voice recognition

[1688] The user verbally explains the workflow using the device's microphone. For example, they might say, "First, submit the application form at the reception desk, and then enter the data for confirmation." The device collects this voice data and sends it to the server. At the same time, the device's built-in emotion engine analyzes the user's emotional state in real time, generating and collecting emotion data.

[1689] Conversion to text data and generation of flow diagrams

[1690] The server receives the voice data and converts it into text data using speech recognition AI. Based on the converted text data, the server generates an initial version of the business flow diagram. For example, a flow diagram of "Reception -> Application submission -> Data entry" is generated. This initial flow diagram is sent to the terminal and displayed to the user.

[1691] Flowchart revision and emotional feedback

[1692] The user checks the initial flow diagram and provides additional explanations or corrections. For example, they might explain, "After data entry, we will make a decision on whether to approve or reject the request once the review process is complete." This additional explanation is also collected by the device's microphone and resent to the server. The server converts the additional voice data into text data and reflects the corrections in the original flow diagram. At the same time, it suggests a work order that is less stressful based on emotional data.

[1693] Presenting the problem and solution

[1694] The server uses a generative AI model to extract issues and solutions from past business data. For example, it generates specific improvement measures, such as "data entry can be automated," and displays these to the user on the device. It also makes suggestions based on emotional data, such as automating parts that cause stress to the user.

[1695] Creating slide decks and videos

[1696] The server creates slides based on the generated workflow diagram, issues, and solutions. The slides are created using Microsoft software. The created slides are sent to the terminal and displayed to the user. Finally, the server generates a video based on the slides, which is also sent to the terminal and provided to the user.

[1697] Specific examples

[1698] For example, if the user explains, "First, submit the application form at the reception desk, then enter the data for confirmation. After the data is entered, once the confirmation process is complete, we will make a decision on whether to approve or reject the application," the following is an example of a prompt sentence:

[1699] User: "I'll first submit the application form at the reception desk, then I'll enter the data for verification."

[1700] User: "After entering the data, we will make a decision on whether to approve or reject it once the review process is complete."

[1701] In this way, by combining an emotion engine, the present invention can generate and improve workflows while taking into account the emotional state of the user.

[1702] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1703] Step 1: Initial Setup

[1704] To begin explaining a business flow, a user accesses a terminal (such as a PC or smartphone), confirms that the microphone for voice input is properly connected, and then launches the interface. The terminal displays the interface, and the user confirms that it is ready. This operation itself does not involve any specific input, and the output is the interface's startup status.

[1705] Step 2: Explanation of the business flow and voice recognition

[1706] The user verbally explains the workflow into the device's microphone. The input is the user's voice, and for example, an explanation such as "First, submit the application form at the reception desk, and then enter the data for confirmation" is collected as voice data. The device sends the voice data to the server. The device's emotion engine also analyzes the user's emotional state in real time and generates emotion data. The output is the voice data and emotion data sent to the server.

[1707] Step 3: Convert to text data

[1708] The server converts the received voice data into text data using voice recognition AI. The input is voice data, and voice recognition is performed as data processing, generating text data such as "First, submit the application form at the reception desk, then enter the data for confirmation." The output is the converted text data.

[1709] Step 4: Generate the initial flow diagram

[1710] The server analyzes the generated text data and generates an initial version of the workflow diagram. The input is text data, and the workflow is analyzed as data processing, generating a flow diagram of "Reception -> Application submission -> Data entry." The output is the initial flow diagram, which is sent to the terminal and displayed.

[1711] Step 5: Add explanations and modify the flow diagram

[1712] The user checks the initial flow diagram displayed on the terminal and provides additional explanations as necessary. The input is the user's additional voice explanation, for example, "After data entry, once confirmation work is completed, a decision will be made on whether to approve or reject." This voice data is also collected by the terminal and sent back to the server. The server converts the additional voice data into text data and reflects the corrections in the original flow diagram. The corrected flow diagram will be "Data entry -> Confirmation work -> (Approval or rejection)." The output is the corrected flow diagram.

[1713] Step 6: Emotional feedback and regulation

[1714] The server analyzes the emotion data generated by the emotion engine and adjusts the revised flow diagram so that the user feels less stressed. The input is the emotion data and the revised flow diagram, and emotion analysis is performed as data processing. For example, stress points are identified and adjustments are made based on that. The output is the adjusted flow diagram that takes the emotion data into account.

[1715] Step 7: Generate problems and solutions

[1716] The server uses a generative AI model to generate issues and solutions based on past business data. The input is the modified flow diagram and past business data, and data analysis generates specific solutions, such as "data entry can be automated." The output is the issue and solution, which is sent to the terminal and displayed to the user.

[1717] Step 8: Create your slide deck

[1718] The server creates slides based on the generated business flow diagram, issues, and solutions. The inputs are the flow diagram, issues, and solutions, and slides are created using Microsoft software. The output is the slides, which are sent to the terminal and displayed to the user.

[1719] Step 9: Create and deliver your video

[1720] The server generates a video based on the slides. The input is the slides, and the video is generated using video creation software. The output is the completed video, which is sent to the terminal and presented to the user.

[1721] (Application example 2)

[1722] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1723] Conventional workflow diagram generation systems lack feedback that takes into account the user's emotional state, which can lead to stressful processes, especially in factory operations. This can lead to insufficient optimization of factory robot operations, resulting in reduced productivity and increased risk of errors. Furthermore, there is a lack of a way to effectively incorporate the workflow explained by on-site managers into the robots.

[1724] 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.

[1725] In this invention, the server includes a means for converting voice data into text data using a voice recognition AI, a means for an emotion engine to analyze the user's emotion data and reflect the result as feedback when generating and modifying a workflow diagram, and a means for a factory robot to perform work based on the generated workflow diagram. This allows a more optimized workflow diagram to be generated taking into account the user's emotional state, enabling the factory robot to perform work efficiently based on the workflow diagram.

[1726] "User" refers to a person who verbally explains the business flow.

[1727] "Terminal" refers to a device that collects user explanations as voice data and displays or transmits them.

[1728] "Audio data" refers to a conversion of a user's verbal description into digital data.

[1729] A "server" refers to a device that converts voice data into text data using voice recognition AI and performs processes such as analysis, generation, and transmission.

[1730] "Voice recognition AI" refers to artificial intelligence technology that converts voice data into text data.

[1731] "Text data" refers to text-format data converted by voice recognition AI.

[1732] "Initial flow diagram" refers to the initial version of the business flow generated by analyzing text data.

[1733] "Display" refers to the terminal visually presenting information such as a workflow diagram to the user.

[1734] "Additional explanation" refers to new verbal explanation given by the user to the flow diagram.

[1735] "Emotion engine" refers to an engine that analyzes the user's emotion data and reflects it as feedback in the generation and modification of business flow diagrams.

[1736] "Feedback" refers to the process of reflecting the analysis results of the emotion engine in the generation and modification of business flow diagrams.

[1737] A "factory robot" refers to a machine that actually carries out work based on the generated business flow diagram.

[1738] "Issues" refer to problems that need to be solved within the business flow.

[1739] "Solution" refers to a proposal or method for solving a problem.

[1740] "Slide deck" refers to a presentation-style deck that includes the generated flow diagram, problem, and solution.

[1741] "Video" refers to a dynamic file that provides visual information based on slide presentations.

[1742] The system for implementing this invention utilizes voice recognition AI and an emotion engine to efficiently convert the business flow explained orally by the user into text data, analyze it, and generate, modify, and display a business flow diagram, which factory robots use to carry out their work.

[1743] Hardware and software used

[1744] Hardware:

[1745] microphone

[1746] Factory robots

[1747] Device (e.g. PC, smartphone)

[1748] software:

[1749] Python

[1750] SpeechRecognition Library

[1751] EmotionRecognition Library

[1752] TextToFlowchart Library

[1753] ImprovementSuggestions Library

[1754] Processing flow

[1755] Step 1: A user verbally explains the workflow, and audio data is collected using a microphone. This audio data is sent to the server via the terminal.

[1756] Step 2: The server uses speech recognition AI to convert the voice data into text data, which is then analyzed to generate an initial flow diagram. This initial flow diagram is then sent to the device and displayed to the user.

[1757] Step 3: The user checks the initial flow diagram on the terminal and adds explanations for branches or missing parts as needed. This is also collected as voice data using a microphone and sent back to the server.

[1758] Step 4: The server converts the additional voice data into text data and modifies the original workflow diagram. Furthermore, the emotion engine analyzes the user's emotional state and reflects emotional data such as stress as feedback in modifying the workflow diagram.

[1759] Step 5: Based on the revised workflow diagram, the server generates issues and solutions using data from past business reform projects. The generated workflow diagram, issues, and solutions are created as slides and sent to the terminal.

[1760] Step 6: The server generates a video based on the slides, and the device provides the video to the user. Finally, the factory robot performs the work based on the generated workflow diagram.

[1761] Specific examples

[1762] For example, a factory manager might explain his work as follows:

[1763] "We first receive the raw materials, then we inspect them for quality. If there are no problems, we start assembling them into parts."

[1764] Prompt Sentence Examples

[1765] Explain verbally the workflow of your factory, for example, "We first receive the raw materials, then inspect them for quality. If there are no problems, we start assembling them into parts."

[1766] This system takes into account the user's emotional state to generate more optimized workflow diagrams, enabling factory robots to carry out their work efficiently based on these diagrams.

[1767] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1768] Step 1:

[1769] The user verbally explains the workflow. The microphone is used to collect voice data and send it to the terminal. The user's voice is taken as input and digital voice data is generated as output.

[1770] Step 2:

[1771] The terminal sends the collected voice data to the server. The input is the voice data, and the output is the voice data transferred to the server.

[1772] Step 3:

[1773] The server uses voice recognition AI to convert the voice data into text data. The input is the voice data, and the output is the corresponding text data. The text data represents an outline of the business flow.

[1774] Step 4:

[1775] The server analyzes the text data and generates an initial flow diagram. The input is text data and the output is the initial flow diagram. Natural Language Processing technology is used for the analysis.

[1776] Step 5:

[1777] The server sends the generated initial flow diagram to the terminal. The input is the initial flow diagram, and the output is the flow diagram transferred to the terminal.

[1778] Step 6:

[1779] The terminal displays the initial flow diagram to the user, with the input being the initial flow diagram and the output being the visual representation that the user can see.

[1780] Step 7:

[1781] The user adds explanations to the flow diagram for branches and missing parts. The explanations are collected as voice data using a microphone and sent to the terminal. The input is the voice of the explanations, and the output is digital voice data.

[1782] Step 8:

[1783] The terminal sends additional audio data to the server. The input is the audio data, and the output is the audio data transferred to the server.

[1784] Step 9:

[1785] The server converts the additional voice data into text data and modifies the original flow diagram, with the additional voice data as input and the modified text data and flow diagram as output.

[1786] Step 10:

[1787] The emotion engine analyzes the user's voice data and generates emotion data. The input is voice data and the output is emotion data. The revised flow diagram is optimized based on this emotion data.

[1788] Step 11:

[1789] The server generates issues and solutions based on the optimized flow diagram and using data from past business reform projects. The input is the optimized flow diagram, and the output is the issues and solutions.

[1790] Step 12:

[1791] The flow diagram, problem, and solution generated by the server are created as slides. The input is the optimized flow diagram and solution, and the output is the slides.

[1792] Step 13:

[1793] The server generates a video based on the slides. The input is the slides, and the output is a video file.

[1794] Step 14:

[1795] The device provides the generated video to the user. The input is a video file, and the output is a visual representation of the video.

[1796] Step 15:

[1797] Factory robots carry out tasks based on the generated workflow diagram. The input is the optimized workflow diagram, and the output is the business process to be executed.

[1798] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1799] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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.

[1800] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1801] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1802] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1803] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1804] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1805] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1806] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1807] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1808] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1809] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1810] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1811] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1812] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1813] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1814] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1815] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1816] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1817] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1818] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if eac...

Claims

1. A means for a user to verbally explain a business flow; a means for collecting the user's explanation as voice data in the terminal; A server converts the voice data into text data using a voice recognition AI; A server analyzes the text data to generate an initial flow diagram; means for displaying the initial flow chart on a terminal; A means for users to add explanations of branches and missing parts, a means for the terminal to collect the additional explanation as voice data and transmit it again to the server; a means for converting the additional voice data into text data by the server and modifying the flow chart; A means for the server to generate issues and solutions based on past business reform project data, A means for creating slides containing the flow charts, problems, and solutions generated by the server; A server generates a video based on the slides; a means for the terminal to provide the video to the user; A system including:

2. A means for a user to verbally explain a business flow; a means for collecting the user's explanation as voice data in the terminal; A server converts the voice data into text data using a voice recognition AI; A server analyzes the text data to generate an initial flow diagram; means for displaying the initial flow chart on a terminal; means for modifying said flow chart on a terminal; A system including a means for a server to generate issues and solutions based on data on past business reform projects.

3. A means for a user to verbally explain a business flow; a means for collecting the user's explanation as voice data in the terminal; A server converts the voice data into text data using a voice recognition AI; A server analyzes the text data to generate an initial flow diagram; means for displaying the initial flow chart on a terminal; A server creates a slide presentation containing the flow chart, the problem, and the solution; The system includes a server that generates a video based on the slide materials.

Images