system

Abstract

We provide the system. [Solution] A means of filming work procedures using a video acquisition device, Means for collecting audio data and text data, An analysis device for analyzing collected data and generating business procedure models, A program generation device that generates automation programs based on business procedure models, A means of distributing the generated automation program to the terminal, A system that includes this.

Description

Technical Field

[0005] ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] A "video acquisition device" refers to a device such as a camera or smartphone used to film work procedures.

[0007] "Audio data" refers to audio information such as instructions and explanations in work procedures, and is data collected through a microphone.

[0008] "Text data" refers to data that records work procedures and precautions as written information.

[0009] An "analysis device" is a device that generates business procedure models using collected video, audio, and text data, and has the function of analyzing data.

[0010] A "business procedure model" is an abstract model that represents a series of business procedures, obtained by an analysis device.

[0011] A "program generation device" is a device that has the function of generating automation programs based on business procedure models.

[0012] "Means of distribution" refers to the methods and mechanisms for sending the generated automation program to a terminal and making it available for use. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention relates to a system for automating work procedures, which begins with capturing the workflow using a video acquisition device. The user captures the work procedure using a smartphone or dedicated camera and simultaneously collects audio data. If necessary, the user inputs an overview of the work procedure and points to note as text data, and all collected data is saved on the terminal.

[0035] The terminal sends the collected data to the server, where an analysis device processes the data. The server recognizes specific actions of the work procedure from the video data and converts the audio data into text. Then, it extracts work instructions using natural language processing technology and generates a work procedure model that integrates visual information, audio instructions, and text information.

[0036] Based on this model, the server automatically generates RPA programs using a program generation device. The generated programs are sent to terminals, and the tasks are automated according to the user's instructions. Specifically, if there is data entry work using Excel, a program is created that automatically processes the repetitive tasks that the user previously performed manually.

[0037] In this way, the system of the present invention can provide an environment in which even users without programming skills can easily automate business processes. This leads to increased efficiency in business operations and contributes to improving the competitiveness of companies.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The user films the work procedure using a camera, which is a video acquisition device. During filming, the user also explains the procedure verbally, simultaneously collecting audio data. The terminal records this video and audio data and inputs notes about the work procedure as text data as needed.

[0041] Step 2:

[0042] The terminal transmits the collected video, audio, and text data to the server. The server prepares the received data for input into the analysis device for analysis.

[0043] Step 3:

[0044] The server first begins analyzing the video data to recognize each action in the work procedure. In this process, it uses visual information to identify hand and finger movements and changes in the applications being used.

[0045] Step 4:

[0046] The server then processes the audio data into text and uses natural language processing technology to extract work instructions and explanations. This reveals the content of the audio instructions.

[0047] Step 5:

[0048] The server integrates the analyzed video, audio, and text information to generate a business process model. This model represents the entire business flow and includes the information necessary for business automation.

[0049] Step 6:

[0050] The server uses a program generation device to create an RPA program based on the generated business procedure model. This generates a script that can automate manual operations.

[0051] Step 7:

[0052] The server sends the generated RPA program to the terminal. The user checks the program received on the terminal and prepares for business process automation.

[0053] Step 8:

[0054] The user runs a program on their terminal, and the specified business procedures are automated. The terminal executes the RPA program sequentially, replacing manual work.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In automating business processes, it is difficult for users without specialized programming skills to efficiently automate their own work procedures. Furthermore, existing systems have challenges in integrating different information formats (video, audio, text) and accurately generating work instructions. This often leads to delays in creating automation programs necessary for improving business efficiency and productivity.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for collecting video information using an information acquisition device for recording business procedures, means for acquiring and recording audio and text information, and means for transmitting the acquired information to a data processing device using communication means. As a result, users can integrate video, audio, and text information, automatically construct a business procedure model, and generate efficient business automation programs without requiring complex programming.

[0060] An "information acquisition device" is a device used to collect video information in the recording of work procedures.

[0061] "Means for acquiring and recording voice and text information" refers to a system that collects voice commands and instructions in business procedures and records them as text information as needed.

[0062] "Means of transmitting data to a data processing device using communication means" refers to transmission technology that sends acquired information to a data processing device on the server side, making it ready for analysis.

[0063] A "data processing device" is a device that analyzes collected video and audio information to recognize and organize business procedures.

[0064] A "processing device for recognizing behavioral processes" is a specialized device that identifies specific actions from video information and analyzes business processes.

[0065] "Natural language processing technology" is a technology that uses machine learning and artificial intelligence to convert speech information into text and extract business instructions.

[0066] A "model generation device" is a device that generates a consistent business procedure format based on recognized behavioral processes and instructions extracted using natural language processing.

[0067] A "business process automation program" is a program designed to automate business processes, built according to a generated business procedure format.

[0068] "Means of distribution to terminal devices" refers to a mechanism for delivering the constructed business automation program to the user's operating environment and making it executable.

[0069] This invention relates to a system that generates automation programs from records of business operations using an information acquisition device. This system integrates video, audio, and text information to form an automated business procedure as a process.

[0070] Users record work procedures as video using smartphones or dedicated camera devices. By simultaneously recording voice instructions and comments, detailed work content is provided. This information is saved on the device, allowing users to easily prepare the data.

[0071] The terminal transmits collected video, audio, and additional text information to the server. The server uses image processing software to analyze the received video information. Computer vision technology is used to recognize specific actions, forming a framework for work procedures. Audio information is converted into text using speech recognition technology, and natural language processing technology is used based on this. This enables the extraction of work orders and understanding of their content.

[0072] Based on the analysis results above, the server utilizes a model generation system incorporating machine learning algorithms to generate a business procedure model. This model is designed to meet the visualized business processes and automation needs.

[0073] The generated business process model is processed through a program generator to design business automation programs. For example, a script is generated to automate data entry tasks in Excel. This program is delivered from the server to the terminal, allowing the user to perform the specified tasks in an automated form.

[0074] As a concrete example, consider automating product management. Users photograph the product receiving process with their smartphones and provide voice instructions for barcode scanning and quantity verification. Based on this data, the server generates RPA programs for order entry and inventory updates, significantly reducing manual work for the user.

[0075] An example of a prompt message is: "We will record the order process and read out information such as product ID and quantity. Based on this data, we will create a procedure to generate an RPA program and automatically input the data into Excel."

[0076] Thus, the system of the present invention integrates diverse information formats to enable business automation and functions as a powerful tool for improving business efficiency.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] Users record work procedures as video using a smartphone or a dedicated camera. Audio explanations are also recorded simultaneously. For example, they might video the process of preparing products for shipment and provide audio commentary such as, "Put the products in this cardboard box." The input consists of video and audio data, which are stored on the device.

[0080] Step 2:

[0081] The device transmits stored video and audio data to the server. Wi-Fi or mobile data communication is used for transmission. The input consists of video and audio files, which are then received by the server.

[0082] Step 3:

[0083] The server analyzes the received video data and performs processing to recognize specific actions. For example, it uses computer vision technology to identify product picking actions. This analysis requires video data as input and outputs the results of action identification.

[0084] Step 4:

[0085] The server converts audio data into text using speech recognition technology. In this process, "Put the products in the cardboard box" is converted into text data. The input is audio data, and the output is a transcript of the audio.

[0086] Step 5:

[0087] The server uses natural language processing techniques to extract work instructions using the converted text information and previously analyzed behavioral data. For example, the instruction "Put it in a cardboard box" might be extracted. Here, the input is the converted text and behavioral data, and the output is the extracted work instructions.

[0088] Step 6:

[0089] The server generates a business procedure model based on the extracted business instructions. This model includes a visualized business process and integrates actions and instructions at each stage. The input is the extracted instruction data, and the output is the business procedure model.

[0090] Step 7:

[0091] The server uses the generated business procedure model to construct a business automation program using a program generation device. For example, a script to automate data entry into Excel is generated. The input is a business procedure model, and the output is an executable program.

[0092] Step 8:

[0093] The server distributes the generated business automation program to the terminal. The distributed program is executed according to the user's instructions, automating the business process. The input for distribution is the generated program, and the output is the automation execution environment in the user's operating environment.

[0094] (Application Example 1)

[0095] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0096] In the workplace, there is a demand for efficient and accurate execution of work procedures. However, traditional methods for visualizing and automating work procedures are complex, making them difficult for workers without programming skills to use. Furthermore, manual work processes can lead to errors and wasted time, reducing overall work efficiency.

[0097] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0098] In this invention, the server includes a presentation device that uses a video acquisition device to film work procedures, recognizes the actions of workers, and visualizes efficient work procedures; an analysis device that analyzes the collected data and generates a work procedure model; and a program generation device that generates an automation program based on the work procedure model. This enables efficient execution of work procedures and reduction of errors.

[0099] A "video acquisition device" is a device used to record work procedures in detail and plays a role in acquiring visual data of the work.

[0100] "Audio data" refers to auditory information related to work activities, including instructions and conversations during work.

[0101] "Text data" refers to information that expresses an overview of business procedures and points to note in written form.

[0102] An "analysis device" is a device that processes collected video data, audio data, and text data to generate a business procedure model.

[0103] A "business procedure model" is generated by an analysis device and represents the flow and operation procedures of a business process in an integrated manner.

[0104] A "program generation device" is a device that constructs automation programs based on business procedure models.

[0105] A "presentation device" is a device that visually displays efficient work procedures to workers and supports their work activities.

[0106] An "automation program" is a set of instructions for automatically executing business processes that were previously performed manually.

[0107] A "terminal" is a device on which a generated automation program is transmitted and executed.

[0108] The system that realizes this application example consists of a video acquisition device, an analysis device, a program generation device, and a presentation device. First, the user wears a video acquisition device such as smart glasses and films the work procedure. This records visual information of the work site in real time.

[0109] Next, the terminal collects voice and text data. The voice data collects work instructions and conversations during work, and is converted into text data. The analysis device receives this data and recognizes the worker's actions from the video data. This generates a work procedure model. Image recognition technologies such as Amazon Rekognition can be used in this process.

[0110] The server processes text data using the Google® Cloud Natural Language API and extracts work instructions. Once the work procedure model is complete, an automation program is generated via a program generator. This program is used for automated data entry into applications such as Excel.

[0111] The generated automation program is delivered to the terminal via the cloud and used by the user when automating tasks. The display device visualizes efficient work procedures and provides work instructions through smart glasses. This allows users to reduce work errors and improve work efficiency.

[0112] As a concrete example, in a logistics center, when a worker retrieves an item from a shelf, information about the next item to be picked is visually displayed on their smart glasses. This allows the worker to pick items quickly and without making mistakes in the procedure.

[0113] Example prompt: "Develop an application that records video and audio of a worker wearing smart glasses picking items from shelves, and uses that data to automate efficient work procedures."

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The user uses smart glasses to film the work procedure. A video acquisition device records the work and generates video data from the user's point of view. The input is real-time work video, and the output is a video data file. This file forms the basis for subsequent processing.

[0117] Step 2:

[0118] The terminal collects audio data while it is working. Ambient sounds and user verbal instructions are recorded as audio files. Input is real-time audio information, and output is an audio data file. This data is used to transcribe work instructions into text.

[0119] Step 3:

[0120] The device converts audio data into text data. Speech recognition software is used to analyze the audio file and generate the corresponding text data. The input is an audio data file, and the output is a text file.

[0121] Step 4:

[0122] The server analyzes the worker's movements using video data. An image recognition algorithm is used to identify each movement. The input is a video data file, and the output is the movement recognition result. This clarifies each step of the work procedure.

[0123] Step 5:

[0124] The server analyzes text data and extracts work instructions. Natural language processing techniques are used to clarify the content of the instructions. The input is a text data file, and the output is a list of work instructions. This list becomes part of a business procedure model.

[0125] Step 6:

[0126] The server integrates video data, motion recognition results, and work instructions to generate a work procedure model. This records the workflow as a single model. Inputs are video data, motion recognition results, and work instructions, while output is the work procedure model.

[0127] Step 7:

[0128] The server generates an automation program based on a business procedure model. It constructs a set of action instructions to automate a specific task. The input is the business procedure model, and the output is the automation program. This program ultimately achieves business process automation.

[0129] Step 8:

[0130] The generated automation program is delivered to the terminal and presented to the user. The program is used as part of the user's workflow. The input is the automation program, and the output is the program in a user-ready state. This step allows the user to perform their tasks efficiently.

[0131] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0132] This invention is a system for streamlining work procedures, which begins by capturing the workflow with a camera and collecting audio and text data. The user films their own work procedures using a video acquisition device. Furthermore, it collects audio instructions and explanations given during work, and the terminal records this video and audio data, as well as manually entered text data.

[0133] The terminal sends the collected data to the server, where an analysis device processes the data. By analyzing the video data, actions and operations within the work procedure are recognized, and the audio data is converted into text using natural language processing technology to extract work instructions. Then, this information is integrated to generate a work procedure model.

[0134] Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions. The server analyzes the user's facial expressions and tone of voice using cameras and sensors to infer their emotional state. This makes it possible to identify areas that need improvement, such as which parts of the work procedures are causing the user stress.

[0135] The emotion engine generates automated business processes on the server based on the emotional information it receives, adapting the program to the user's emotions. For example, in sections where the user feels anxious, it may add detailed explanations or prioritize presenting simplified work procedures. The generated program is then delivered to the terminal, enabling the user to effectively utilize automated business processes while reducing their workload.

[0136] Thus, the system of the present invention not only improves the efficiency of operations but also enables flexible work support that takes into account the user's emotional state. As a specific example, in telephone support operations, the system could automatically detect situations in which the user feels stressed and provide real-time advice or stress reduction measures.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] Users film their work procedures using a smartphone or dedicated camera. During filming, they provide instructions and explanations related to the work via voice, and the device records this video and audio data. It is also possible to manually input important procedures and points to note as text data.

[0140] Step 2:

[0141] The terminal sends recorded video, audio, and text data to the server. The server receives this data and prepares it for business analysis.

[0142] Step 3:

[0143] The server analyzes video data to recognize each action in the work procedure. The analysis is performed by capturing hand and finger movements and changes in the display shown on the camera from visual information.

[0144] Step 4:

[0145] The server converts the audio data into text and extracts work instructions using natural language processing technology. This natural language processing ensures that the content of the audio instructions is clearly understood.

[0146] Step 5:

[0147] The server integrates the analyzed visual, audio, and text information to generate a business process model. This model contains all the information necessary for business process automation.

[0148] Step 6:

[0149] The server uses an emotion engine to analyze the user's emotions. It evaluates the user's facial expressions and voice intonation obtained through the camera and microphone to infer emotional states such as stress, anxiety, and satisfaction.

[0150] Step 7:

[0151] The server generates RPA programs adapted to the user's emotions based on emotional information and business procedure models. For example, if the user is confused, it may add detailed help messages.

[0152] Step 8:

[0153] The server sends the generated RPA program to the terminal. The user reviews the program delivered to the terminal and prepares to run it in a format that suits their work.

[0154] Step 9:

[0155] Users execute programs on the terminal, and automated work procedures are carried out. The terminal performs emotionally sensitive workflows and provides support to reduce the workload.

[0156] (Example 2)

[0157] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0158] Current systems designed to streamline business procedures lack flexible support that reflects user emotions, resulting in insufficient reduction of user stress and anxiety. This can lead to a decline in the quality of the user experience, not just a decrease in operational efficiency.

[0159] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0160] In this invention, the server includes means for analyzing the user's facial expressions and tone of voice to infer their emotional state, means for generating an automated program adapted to the user based on the emotional information, and means for distributing the generated automated program to a terminal. This makes it possible to provide work support adapted to the user's emotions, improve work efficiency, and reduce the user's stress and anxiety.

[0161] A "video acquisition device" is a device used to visually record work procedures.

[0162] "Audio data" refers to information recorded as sound, such as instructions or explanations required during work.

[0163] "Text data" refers to information obtained by converting audio into a document format.

[0164] An "analysis device" is a device used to analyze collected data and generate business procedure models.

[0165] A "business procedure model" is a model of procedures created to streamline business processes.

[0166] A "program generation device" is a device that generates automation programs based on business procedure models.

[0167] An "emotion recognition device" is a device that analyzes a user's facial expressions and tone of voice to infer their emotional state.

[0168] An "automation program" is a program that contains a series of instructions for automating business procedures.

[0169] "Distribution method" refers to the means of sending a program generated on a server to a terminal.

[0170] This invention provides a system that streamlines work procedures and offers support that responds to user emotions. This system consists of a video acquisition device, an audio data processing device, an analysis device and an emotion recognition device in a server, a program generation device, and a user terminal.

[0171] Users film work procedures with a camera and collect voice instructions and explanations spoken during work as audio data using a microphone. This data is integrated on the terminal and sent to the server. The analysis device on the server analyzes the video data and uses image recognition technology to recognize actions and operations during work. In addition, the audio data is converted into text data through natural language processing technology, and work instructions are extracted.

[0172] The server generates a business procedure model from these analysis results and builds an automation program based on this model. Furthermore, the server's emotion recognition device uses cameras and voice sensors to analyze the user's facial expressions and tone of voice and infer their emotional state. This allows the server to understand how the user feels during specific business procedures and generate an automation program adapted to the user based on the emotional information.

[0173] The generated programs are delivered to the user's terminal to support the efficient execution of tasks. For example, the system provides detailed explanations and simplified procedures for sections of work that cause the user anxiety. Specifically, in telephone support tasks, the system detects the user's stress in real time and provides timely advice to alleviate that stress.

[0174] Examples of prompts include, "Combine video and audio data to analyze the business procedure," and "Analyze the user's facial expressions and tone of voice to infer their emotions." Based on these prompts, the server processes the data as needed to provide the user with the best possible support.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] Users film work procedures with a camera and record voice instructions and explanations during work using a microphone. The input data consists of visual video and audio data. The recorded video and audio data are temporarily stored on the device. This initial data collection by the user forms the basis for subsequent data analysis.

[0178] Step 2:

[0179] The terminal sends the collected video and audio data to the server. At this stage, the input is the data held within the terminal, and the output is the data sent to the server. Once the data transmission is complete, the server is ready for analysis.

[0180] Step 3:

[0181] The server analyzes the received video data to identify actions and operations in the work procedure. The input is the video data received by the server, and the output is the recognized action information. The server uses image recognition technology to analyze the user's actions frame by frame and extract the operation procedure.

[0182] Step 4:

[0183] The server converts audio data into text and extracts important work instructions. The input is audio data, and the output is text data obtained using natural language processing technology. The server uses speech recognition technology to analyze the text extracted from the audio and creates a list of the work instructions.

[0184] Step 5:

[0185] The server integrates the analysis results and generates a business procedure model. The input consists of motion information obtained from video analysis and work instructions from audio analysis, while the output is the business procedure model. Based on this data, the server assembles a model for creating efficient business procedures.

[0186] Step 6:

[0187] The server uses cameras and sensors to analyze facial expressions and voice tone to infer the user's emotional state. The input is real-time acquired facial expression data and voice tone, and the output is the inferred emotional state of the user. This allows the server to identify where the user is experiencing stress.

[0188] Step 7:

[0189] The server generates automated programs based on emotional states. Inputs are business procedure models and emotional information, and output is an automated program adapted to the user. The server adds explanations and simplified procedures to areas where anxiety is felt.

[0190] Step 8:

[0191] The server distributes the generated automation program to the terminal, which receives and executes the program. The input is the automation program received from the server, and the output is the program actually used by the user. This allows the user to perform their tasks efficiently and without stress.

[0192] (Application Example 2)

[0193] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0194] There is a need to improve the efficiency of work procedures within factories and manage the emotional state of workers through new technologies. However, conventional systems have difficulty simultaneously optimizing work procedures and appropriately monitoring workers' emotional states, resulting in the challenge of not being able to improve work efficiency while reducing the burden on workers.

[0195] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0196] In this invention, the server includes means for capturing work procedures using a video acquisition device, means for collecting audio and text data, and an emotion recognition device for performing emotion analysis. This enables the streamlining of work procedures and flexible work support based on emotions.

[0197] A "video acquisition device" is a device used to visually record the procedures of work or tasks, and is equipped with a camera or other recording function.

[0198] "Audio data" refers to audio information, including instructions and explanations given during work, recorded in digital format.

[0199] "Text data" refers to data that expresses information related to business procedures in text format.

[0200] An "analysis device" is a device that analyzes video and audio data to generate a business procedure model.

[0201] An "emotion recognition device" is a device that analyzes a worker's facial expressions, tone of voice, etc., to infer their emotional state.

[0202] A "program generation device" is a device for generating automation programs based on business procedure models and emotional states.

[0203] An "information terminal" is a device that receives generated automation programs and makes them available for use by workers.

[0204] A "prompt message" is a formatted text used to present generated work instructions or solutions.

[0205] To realize this invention, first, a video acquisition device is used to film the work procedure using equipment installed at the work site. The user uses a microphone and sensors to collect audio data in real time. The acquired video and audio data are transmitted to a server via an information terminal. On the server, dedicated video analysis software is used to analyze the video data, extract the work procedure, and generate a procedure model.

[0206] The voice data is converted into text data using natural language processing technology, and the work instructions are analyzed. Specifically, conversion software such as Google Cloud Speech-to-Text can be used.

[0207] Furthermore, an emotion recognition device detects the worker's emotional state from their facial expressions and tone of voice. This uses hardware such as cameras and acoustic analysis systems. Based on the emotional data, the server identifies which work procedures the user is experiencing stress from.

[0208] The program generation device generates an automation program based on the work procedure model and emotional state, and distributes this program to an information terminal. The information terminal presents instructions to the worker visually or audibly. In situations where the worker is experiencing stress, for example, it might provide instructions such as, "Shall we reconfirm the quality standards for this part?" Another example of a prompt message could be, "Please provide a simplified procedure for the process that tends to cause fatigue during quality inspection on the conveyor belt."

[0209] This allows workers to enjoy a comfortable working environment while efficiently executing procedures. The system also has the flexibility to automatically suggest improvements to work processes by integrating with a generative AI model.

[0210] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0211] Step 1:

[0212] The user films the work procedure using a video acquisition device. The input is video data captured by the camera. The user applies the attached camera to record the entire necessary work process. The output is detailed visual data of the work procedure.

[0213] Step 2:

[0214] The terminal collects audio data at the work site. The input is audio information generated at the site, recorded in real time using a microphone. Data processing involves digitizing the audio files and preparing them for analysis. The output is a digital file of the audio data.

[0215] Step 3:

[0216] The terminal transfers the collected video and audio data to the server. The input is the digital video and audio files stored on the terminal. The output is the state in which this data has been prepared for analysis on the server side.

[0217] Step 4:

[0218] The server analyzes video data using video analysis software. The input is the video data arriving at the server. During data processing, the actions of each frame are identified and a business procedure model is generated. The output is the extracted business procedure results and model data.

[0219] Step 5:

[0220] The server converts speech data into text data using natural language processing techniques. The input is digitized speech data. The process includes speech recognition from the audio file and data calculations to generate text information. The output is text data extracted from the speech.

[0221] Step 6:

[0222] The server analyzes the user's emotional state using an emotion recognition device. The input consists of emotion-related feature information obtained from video and audio data. Data processing is performed using a machine learning algorithm to infer the emotional state. The output is the inferred result of the emotional state.

[0223] Step 7:

[0224] The program generation device generates an automated program based on a business procedure model and emotional state. The inputs are model data and emotional inference results. The process includes data processing to generate prompt statements using a generation AI model and write the optimal procedure. The output is the generated automated program.

[0225] Step 8:

[0226] The terminal receives automated programs generated from the server. The input is the automated program from the server. The terminal displays this program to the user via an interface, making it available for use. The output is business support information that the user can use.

[0227] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0228] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0229] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0233] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0234] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0235] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0236] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0237] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0238] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0239] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0240] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0241] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0242] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0243] This invention relates to a system for automating work procedures, which begins with capturing the workflow using a video acquisition device. The user captures the work procedure using a smartphone or dedicated camera and simultaneously collects audio data. If necessary, the user inputs an overview of the work procedure and points to note as text data, and all collected data is saved on the terminal.

[0244] The terminal sends the collected data to the server, where an analysis device processes the data. The server recognizes specific actions of the work procedure from the video data and converts the audio data into text. Then, it extracts work instructions using natural language processing technology and generates a work procedure model that integrates visual information, audio instructions, and text information.

[0245] Based on this model, the server automatically generates RPA programs using a program generation device. The generated programs are sent to terminals, and the tasks are automated according to the user's instructions. Specifically, if there is data entry work using Excel, a program is created that automatically processes the repetitive tasks that the user previously performed manually.

[0246] In this way, the system of the present invention can provide an environment in which even users without programming skills can easily automate business processes. This leads to increased efficiency in business operations and contributes to improving the competitiveness of companies.

[0247] The following describes the processing flow.

[0248] Step 1:

[0249] The user films the work procedure using a camera, which is a video acquisition device. During filming, the user also explains the procedure verbally, simultaneously collecting audio data. The terminal records this video and audio data and inputs notes about the work procedure as text data as needed.

[0250] Step 2:

[0251] The terminal transmits the collected video, audio, and text data to the server. The server prepares the received data for input into the analysis device for analysis.

[0252] Step 3:

[0253] The server first begins analyzing the video data to recognize each action in the work procedure. In this process, it uses visual information to identify hand and finger movements and changes in the applications being used.

[0254] Step 4:

[0255] The server then processes the audio data into text and uses natural language processing technology to extract work instructions and explanations. This reveals the content of the audio instructions.

[0256] Step 5:

[0257] The server integrates the analyzed video, audio, and text information to generate a business process model. This model represents the entire business flow and includes the information necessary for business automation.

[0258] Step 6:

[0259] The server uses a program generation device to create an RPA program based on the generated business procedure model. This generates a script that can automate manual operations.

[0260] Step 7:

[0261] The server sends the generated RPA program to the terminal. The user checks the program received on the terminal and prepares for business process automation.

[0262] Step 8:

[0263] The user runs a program on their terminal, and the specified business procedures are automated. The terminal executes the RPA program sequentially, replacing manual work.

[0264] (Example 1)

[0265] Next, we will describe Example 1. 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."

[0266] In automating business processes, it is difficult for users without specialized programming skills to efficiently automate their own work procedures. Furthermore, existing systems have challenges in integrating different information formats (video, audio, text) and accurately generating work instructions. This often leads to delays in creating automation programs necessary for improving business efficiency and productivity.

[0267] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0268] In this invention, the server includes means for collecting video information using an information acquisition device for recording business procedures, means for acquiring and recording audio and text information, and means for transmitting the acquired information to a data processing device using communication means. As a result, users can integrate video, audio, and text information, automatically construct a business procedure model, and generate efficient business automation programs without requiring complex programming.

[0269] An "information acquisition device" is a device used to collect video information in the recording of work procedures.

[0270] "Means for acquiring and recording voice and text information" refers to a system that collects voice commands and instructions in business procedures and records them as text information as needed.

[0271] "Means of transmitting data to a data processing device using communication means" refers to transmission technology that sends acquired information to a data processing device on the server side, making it ready for analysis.

[0272] A "data processing device" is a device that analyzes collected video and audio information to recognize and organize business procedures.

[0273] A "processing device for recognizing behavioral processes" is a specialized device that identifies specific actions from video information and analyzes business processes.

[0274] "Natural language processing technology" is a technology that uses machine learning and artificial intelligence to convert speech information into text and extract business instructions.

[0275] A "model generation device" is a device that generates a consistent business procedure format based on recognized behavioral processes and instructions extracted using natural language processing.

[0276] A "business process automation program" is a program designed to automate business processes, built according to a generated business procedure format.

[0277] "Means of distribution to terminal devices" refers to a mechanism for delivering the constructed business automation program to the user's operating environment and making it executable.

[0278] This invention relates to a system that generates automation programs from records of business operations using an information acquisition device. This system integrates video, audio, and text information to form an automated business procedure as a process.

[0279] Users record work procedures as video using smartphones or dedicated camera devices. By simultaneously recording voice instructions and comments, detailed work content is provided. This information is saved on the device, allowing users to easily prepare the data.

[0280] The terminal sends the collected video information, audio information, and added text information to the server. The server uses image processing software to analyze the received video information. By using computer vision technology to recognize specific operations, a framework for business procedures is formed. Also, the audio information is converted into text information using speech recognition technology, and natural language processing technology is utilized based on this. As a result, extraction of business instructions and understanding of instruction contents are realized.

[0281] Based on the above analysis results, the server utilizes a model generation device incorporating a machine learning algorithm to generate a business procedure model. This model is designed to meet visualized business processes and automation needs.

[0282] The generated business procedure model is processed through a program generation device to design a business automation program. For example, a script for automating data entry work in Excel is generated. This program is distributed from the server to the terminal, and the user can execute the specified business in an automated form.

[0283] As a specific example, consider the automation of product management. The user takes a photo of the product receiving operation with a smartphone and verbally explains procedures such as barcode scanning and quantity confirmation. Based on this data, the server generates an RPA program for order reception input and inventory update, and the user can significantly reduce manual work.

[0284] Examples of prompt sentences include the following. "Take a photo of the order receiving process and read out information such as product ID and quantity. Based on this data, generate an RPA program and create a procedure for automatic input into Excel."

[0285] In this way, the system of the present invention integrates various information formats to enable business automation and functions as a powerful tool for improving business efficiency.

[0286] The flow of the specific process in Example 1 will be described using FIG. 11.

[0287] Step 1:

[0288] The user records the business procedures as a video using a smartphone or a dedicated camera. At this time, voice explanations are also recorded simultaneously. For example, the preparation work for shipping goods is video-recorded, and it is explained verbally as "Put the goods in this cardboard box." The inputs are video and voice data, which are stored in the terminal.

[0289] Step 2:

[0290] The terminal transmits the stored video and voice data to the server. Wi-Fi or mobile data communication is used for transmission. As the amount of data input, video files and voice files are transmitted and received on the server.

[0291] Step 3:

[0292] The server analyzes the received video data and performs a process to recognize specific actions. For example, using computer vision technology, the picking action of the goods is identified. For this analysis, video data is required as input, and the specific result of the action is obtained as output.

[0293] Step 4:

[0294] The server converts the voice data into character information using voice recognition technology. In this process, "Put the goods in the cardboard box" is converted into character data. The input is voice data, and the transcribed text of the voice is generated as output.

[0295] Step 5:

[0296] The server uses natural language processing techniques to extract work instructions using the converted text information and previously analyzed behavioral data. For example, the instruction "Put it in a cardboard box" might be extracted. Here, the input is the converted text and behavioral data, and the output is the extracted work instructions.

[0297] Step 6:

[0298] The server generates a business procedure model based on the extracted business instructions. This model includes a visualized business process and integrates actions and instructions at each stage. The input is the extracted instruction data, and the output is the business procedure model.

[0299] Step 7:

[0300] The server uses the generated business procedure model to construct a business automation program using a program generation device. For example, a script to automate data entry into Excel is generated. The input is a business procedure model, and the output is an executable program.

[0301] Step 8:

[0302] The server distributes the generated business automation program to the terminal. The distributed program is executed according to the user's instructions, automating the business process. The input for distribution is the generated program, and the output is the automation execution environment in the user's operating environment.

[0303] (Application Example 1)

[0304] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0305] At the work site, it is required to perform work procedures efficiently and accurately. However, in the conventional method, the processes of visualizing and automating work procedures are complex, and there is a problem that it is difficult for workers without programming skills to use. In addition, manual business processes may cause mistakes and time losses, which are factors that reduce the efficiency of the entire business.

[0306] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0307] In this invention, the server includes a presentation device that uses a video acquisition device to shoot work procedures, recognizes the actions of workers, and visualizes efficient work procedures, an analysis device that analyzes the collected data and generates a work procedure model, and a program generation device that generates an automation program based on the work procedure model. Thereby, it becomes possible to efficiently perform work procedures and reduce mistakes.

[0308] The "video acquisition device" is a device for recording work procedures in detail and plays a role in acquiring visual data of the work.

[0309] "Audio data" refers to auditory information related to business activities, including instructions and conversations during work.

[0310] "Text data" refers to an outline and precautions regarding work procedures expressed as character information.

[0311] The "analysis device" is a device that processes the collected video data, audio data, and text data and generates a work procedure model.

[0312] The "work procedure model" is generated by the analysis device and integrally represents the flow of work and operation procedures.

[0313] The "program generation device" is a device that constructs an automation program based on the work procedure model.

[0314] A "presentation device" is a device that visually displays efficient work procedures to workers and supports their work activities.

[0315] An "automation program" is a set of instructions for automatically executing business processes that were previously performed manually.

[0316] A "terminal" is a device on which a generated automation program is transmitted and executed.

[0317] The system that realizes this application example consists of a video acquisition device, an analysis device, a program generation device, and a presentation device. First, the user wears a video acquisition device such as smart glasses and films the work procedure. This records visual information of the work site in real time.

[0318] Next, the terminal collects voice and text data. The voice data collects work instructions and conversations during work, and is converted into text data. The analysis device receives this data and recognizes the worker's actions from the video data. This generates a work procedure model. Image recognition technologies such as Amazon Rekognition can be used in this process.

[0319] The server processes text data using the Google Cloud Natural Language API and extracts work instructions. Once the work procedure model is complete, an automation program is generated via a program generator. This program is used for automated data entry into applications such as Excel.

[0320] The generated automation program is delivered to the terminal via the cloud and used by the user when automating tasks. The display device visualizes efficient work procedures and provides work instructions through smart glasses. This allows users to reduce work errors and improve work efficiency.

[0321] As a concrete example, in a logistics center, when a worker retrieves an item from a shelf, information about the next item to be picked is visually displayed on their smart glasses. This allows the worker to pick items quickly and without making mistakes in the procedure.

[0322] Example prompt: "Develop an application that records video and audio of a worker wearing smart glasses picking items from shelves, and uses that data to automate efficient work procedures."

[0323] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0324] Step 1:

[0325] The user uses smart glasses to film the work procedure. A video acquisition device records the work and generates video data from the user's point of view. The input is real-time work video, and the output is a video data file. This file forms the basis for subsequent processing.

[0326] Step 2:

[0327] The terminal collects audio data while it is working. Ambient sounds and user verbal instructions are recorded as audio files. Input is real-time audio information, and output is an audio data file. This data is used to transcribe work instructions into text.

[0328] Step 3:

[0329] The device converts audio data into text data. Speech recognition software is used to analyze the audio file and generate the corresponding text data. The input is an audio data file, and the output is a text file.

[0330] Step 4:

[0331] The server analyzes the worker's movements using video data. An image recognition algorithm is used to identify each movement. The input is a video data file, and the output is the movement recognition result. This clarifies each step of the work procedure.

[0332] Step 5:

[0333] The server analyzes text data and extracts work instructions. Natural language processing techniques are used to clarify the content of the instructions. The input is a text data file, and the output is a list of work instructions. This list becomes part of a business procedure model.

[0334] Step 6:

[0335] The server integrates video data, motion recognition results, and work instructions to generate a work procedure model. This records the workflow as a single model. Inputs are video data, motion recognition results, and work instructions, while output is the work procedure model.

[0336] Step 7:

[0337] The server generates an automation program based on a business procedure model. It constructs a set of action instructions to automate a specific task. The input is the business procedure model, and the output is the automation program. This program ultimately achieves business process automation.

[0338] Step 8:

[0339] The generated automation program is delivered to the terminal and presented to the user. The program is used as part of the user's workflow. The input is the automation program, and the output is the program in a user-ready state. This step allows the user to perform their tasks efficiently.

[0340] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0341] This invention is a system for streamlining work procedures, which begins by capturing the workflow with a camera and collecting audio and text data. The user films their own work procedures using a video acquisition device. Furthermore, it collects audio instructions and explanations given during work, and the terminal records this video and audio data, as well as manually entered text data.

[0342] The terminal sends the collected data to the server, where an analysis device processes the data. By analyzing the video data, actions and operations within the work procedure are recognized, and the audio data is converted into text using natural language processing technology to extract work instructions. Then, this information is integrated to generate a work procedure model.

[0343] Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions. The server analyzes the user's facial expressions and tone of voice using cameras and sensors to infer their emotional state. This makes it possible to identify areas that need improvement, such as which parts of the work procedures are causing the user stress.

[0344] The emotion engine generates automated business processes on the server based on the emotional information it receives, adapting the program to the user's emotions. For example, in sections where the user feels anxious, it may add detailed explanations or prioritize presenting simplified work procedures. The generated program is then delivered to the terminal, enabling the user to effectively utilize automated business processes while reducing their workload.

[0345] Thus, the system of the present invention not only improves the efficiency of operations but also enables flexible work support that takes into account the user's emotional state. As a specific example, in telephone support operations, the system could automatically detect situations in which the user feels stressed and provide real-time advice or stress reduction measures.

[0346] The following describes the processing flow.

[0347] Step 1:

[0348] Users film their work procedures using a smartphone or dedicated camera. During filming, they provide instructions and explanations related to the work via voice, and the device records this video and audio data. It is also possible to manually input important procedures and points to note as text data.

[0349] Step 2:

[0350] The terminal sends recorded video, audio, and text data to the server. The server receives this data and prepares it for business analysis.

[0351] Step 3:

[0352] The server analyzes video data to recognize each action in the work procedure. The analysis is performed by capturing hand and finger movements and changes in the display shown on the camera from visual information.

[0353] Step 4:

[0354] The server converts the audio data into text and extracts work instructions using natural language processing technology. This natural language processing ensures that the content of the audio instructions is clearly understood.

[0355] Step 5:

[0356] The server integrates the analyzed visual, audio, and text information to generate a business process model. This model contains all the information necessary for business process automation.

[0357] Step 6:

[0358] The server uses an emotion engine to analyze the user's emotions. It evaluates the user's facial expressions and voice intonation obtained through the camera and microphone to infer emotional states such as stress, anxiety, and satisfaction.

[0359] Step 7:

[0360] The server generates RPA programs adapted to the user's emotions based on emotional information and business procedure models. For example, if the user is confused, it may add detailed help messages.

[0361] Step 8:

[0362] The server sends the generated RPA program to the terminal. The user reviews the program delivered to the terminal and prepares to run it in a format that suits their work.

[0363] Step 9:

[0364] Users execute programs on the terminal, and automated work procedures are carried out. The terminal performs emotionally sensitive workflows and provides support to reduce the workload.

[0365] (Example 2)

[0366] Next, we will describe Example 2. 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".

[0367] Current systems designed to streamline business procedures lack flexible support that reflects user emotions, resulting in insufficient reduction of user stress and anxiety. This can lead to a decline in the quality of the user experience, not just a decrease in operational efficiency.

[0368] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0369] In this invention, the server includes means for analyzing the user's facial expressions and tone of voice to infer their emotional state, means for generating an automated program adapted to the user based on the emotional information, and means for distributing the generated automated program to a terminal. This makes it possible to provide work support adapted to the user's emotions, improve work efficiency, and reduce the user's stress and anxiety.

[0370] A "video acquisition device" is a device used to visually record work procedures.

[0371] "Audio data" refers to information recorded as sound, such as instructions or explanations required during work.

[0372] "Text data" refers to information obtained by converting audio into a document format.

[0373] An "analysis device" is a device used to analyze collected data and generate business procedure models.

[0374] A "business procedure model" is a model of procedures created to streamline business processes.

[0375] A "program generation device" is a device that generates automation programs based on business procedure models.

[0376] An "emotion recognition device" is a device that analyzes a user's facial expressions and tone of voice to infer their emotional state.

[0377] An "automation program" is a program that contains a series of instructions for automating business procedures.

[0378] "Distribution method" refers to the means of sending a program generated on a server to a terminal.

[0379] This invention provides a system that streamlines work procedures and offers support that responds to user emotions. This system consists of a video acquisition device, an audio data processing device, an analysis device and an emotion recognition device in a server, a program generation device, and a user terminal.

[0380] Users film work procedures with a camera and collect voice instructions and explanations spoken during work as audio data using a microphone. This data is integrated on the terminal and sent to the server. The analysis device on the server analyzes the video data and uses image recognition technology to recognize actions and operations during work. In addition, the audio data is converted into text data through natural language processing technology, and work instructions are extracted.

[0381] The server generates a business procedure model from these analysis results and builds an automation program based on this model. Furthermore, the server's emotion recognition device uses cameras and voice sensors to analyze the user's facial expressions and tone of voice and infer their emotional state. This allows the server to understand how the user feels during specific business procedures and generate an automation program adapted to the user based on the emotional information.

[0382] The generated programs are delivered to the user's terminal to support the efficient execution of tasks. For example, the system provides detailed explanations and simplified procedures for sections of work that cause the user anxiety. Specifically, in telephone support tasks, the system detects the user's stress in real time and provides timely advice to alleviate that stress.

[0383] Examples of prompts include, "Combine video and audio data to analyze the business procedure," and "Analyze the user's facial expressions and tone of voice to infer their emotions." Based on these prompts, the server processes the data as needed to provide the user with the best possible support.

[0384] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0385] Step 1:

[0386] Users film work procedures with a camera and record voice instructions and explanations during work using a microphone. The input data consists of visual video and audio data. The recorded video and audio data are temporarily stored on the device. This initial data collection by the user forms the basis for subsequent data analysis.

[0387] Step 2:

[0388] The terminal sends the collected video and audio data to the server. At this stage, the input is the data held within the terminal, and the output is the data sent to the server. Once the data transmission is complete, the server is ready for analysis.

[0389] Step 3:

[0390] The server analyzes the received video data to identify actions and operations in the work procedure. The input is the video data received by the server, and the output is the recognized action information. The server uses image recognition technology to analyze the user's actions frame by frame and extract the operation procedure.

[0391] Step 4:

[0392] The server converts audio data into text and extracts important work instructions. The input is audio data, and the output is text data obtained using natural language processing technology. The server uses speech recognition technology to analyze the text extracted from the audio and creates a list of the work instructions.

[0393] Step 5:

[0394] The server integrates the analysis results and generates a business procedure model. The input consists of motion information obtained from video analysis and work instructions from audio analysis, while the output is the business procedure model. Based on this data, the server assembles a model for creating efficient business procedures.

[0395] Step 6:

[0396] The server uses cameras and sensors to analyze facial expressions and voice tone to infer the user's emotional state. The input is real-time acquired facial expression data and voice tone, and the output is the inferred emotional state of the user. This allows the server to identify where the user is experiencing stress.

[0397] Step 7:

[0398] The server generates automated programs based on emotional states. Inputs are business procedure models and emotional information, and output is an automated program adapted to the user. The server adds explanations and simplified procedures to areas where anxiety is felt.

[0399] Step 8:

[0400] The server distributes the generated automation program to the terminal, which receives and executes the program. The input is the automation program received from the server, and the output is the program actually used by the user. This allows the user to perform their tasks efficiently and without stress.

[0401] (Application Example 2)

[0402] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0403] There is a need to improve the efficiency of work procedures within factories and manage the emotional state of workers through new technologies. However, conventional systems have difficulty simultaneously optimizing work procedures and appropriately monitoring workers' emotional states, resulting in the challenge of not being able to improve work efficiency while reducing the burden on workers.

[0404] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0405] In this invention, the server includes means for capturing work procedures using a video acquisition device, means for collecting audio and text data, and an emotion recognition device for performing emotion analysis. This enables the streamlining of work procedures and flexible work support based on emotions.

[0406] A "video acquisition device" is a device used to visually record the procedures of work or tasks, and is equipped with a camera or other recording function.

[0407] "Audio data" refers to audio information, including instructions and explanations given during work, recorded in digital format.

[0408] "Text data" refers to data that expresses information related to business procedures in text format.

[0409] An "analysis device" is a device that analyzes video and audio data to generate a business procedure model.

[0410] An "emotion recognition device" is a device that analyzes a worker's facial expressions, tone of voice, etc., to infer their emotional state.

[0411] A "program generation device" is a device for generating automation programs based on business procedure models and emotional states.

[0412] An "information terminal" is a device that receives generated automation programs and makes them available for use by workers.

[0413] A "prompt message" is a formatted text used to present generated work instructions or solutions.

[0414] To realize this invention, first, a video acquisition device is used to film the work procedure using equipment installed at the work site. The user uses a microphone and sensors to collect audio data in real time. The acquired video and audio data are transmitted to a server via an information terminal. On the server, dedicated video analysis software is used to analyze the video data, extract the work procedure, and generate a procedure model.

[0415] The voice data is converted into text data using natural language processing technology, and the work instructions are analyzed. Specifically, conversion software such as Google Cloud Speech-to-Text can be used.

[0416] Furthermore, an emotion recognition device detects the worker's emotional state from their facial expressions and tone of voice. This uses hardware such as cameras and acoustic analysis systems. Based on the emotional data, the server identifies which work procedures the user is experiencing stress from.

[0417] The program generation device generates an automation program based on the work procedure model and emotional state, and distributes this program to an information terminal. The information terminal presents instructions to the worker visually or audibly. In situations where the worker is experiencing stress, for example, it might provide instructions such as, "Shall we reconfirm the quality standards for this part?" Another example of a prompt message could be, "Please provide a simplified procedure for the process that tends to cause fatigue during quality inspection on the conveyor belt."

[0418] This allows workers to enjoy a comfortable working environment while efficiently executing procedures. The system also has the flexibility to automatically suggest improvements to work processes by integrating with a generative AI model.

[0419] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0420] Step 1:

[0421] The user films the work procedure using a video acquisition device. The input is video data captured by the camera. The user applies the attached camera to record the entire necessary work process. The output is detailed visual data of the work procedure.

[0422] Step 2:

[0423] The terminal collects audio data at the work site. The input is audio information generated at the site, recorded in real time using a microphone. Data processing involves digitizing the audio files and preparing them for analysis. The output is a digital file of the audio data.

[0424] Step 3:

[0425] The terminal transfers the collected video and audio data to the server. The input is the digital video and audio files stored on the terminal. The output is the state in which this data has been prepared for analysis on the server side.

[0426] Step 4:

[0427] The server analyzes video data using video analysis software. The input is the video data arriving at the server. During data processing, the actions of each frame are identified and a business procedure model is generated. The output is the extracted business procedure results and model data.

[0428] Step 5:

[0429] The server converts speech data into text data using natural language processing techniques. The input is digitized speech data. The process includes speech recognition from the audio file and data calculations to generate text information. The output is text data extracted from the speech.

[0430] Step 6:

[0431] The server analyzes the user's emotional state using an emotion recognition device. The input consists of emotion-related feature information obtained from video and audio data. Data processing is performed using a machine learning algorithm to infer the emotional state. The output is the inferred result of the emotional state.

[0432] Step 7:

[0433] The program generation device generates an automated program based on a business procedure model and emotional state. The inputs are model data and emotional inference results. The process includes data processing to generate prompt statements using a generation AI model and write the optimal procedure. The output is the generated automated program.

[0434] Step 8:

[0435] The terminal receives automated programs generated from the server. The input is the automated program from the server. The terminal displays this program to the user via an interface, making it available for use. The output is business support information that the user can use.

[0436] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0437] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0438] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0439] [Third Embodiment]

[0440] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0441] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0442] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0443] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0444] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0445] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0446] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0447] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0448] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0449] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0450] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0451] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0452] This invention relates to a system for automating work procedures, which begins with capturing the workflow using a video acquisition device. The user captures the work procedure using a smartphone or dedicated camera and simultaneously collects audio data. If necessary, the user inputs an overview of the work procedure and points to note as text data, and all collected data is saved on the terminal.

[0453] The terminal sends the collected data to the server, where an analysis device processes the data. The server recognizes specific actions of the work procedure from the video data and converts the audio data into text. Then, it extracts work instructions using natural language processing technology and generates a work procedure model that integrates visual information, audio instructions, and text information.

[0454] Based on this model, the server automatically generates RPA programs using a program generation device. The generated programs are sent to terminals, and the tasks are automated according to the user's instructions. Specifically, if there is data entry work using Excel, a program is created that automatically processes the repetitive tasks that the user previously performed manually.

[0455] In this way, the system of the present invention can provide an environment in which even users without programming skills can easily automate business processes. This leads to increased efficiency in business operations and contributes to improving the competitiveness of companies.

[0456] The following describes the processing flow.

[0457] Step 1:

[0458] The user films the work procedure using a camera, which is a video acquisition device. During filming, the user also explains the procedure verbally, simultaneously collecting audio data. The terminal records this video and audio data and inputs notes about the work procedure as text data as needed.

[0459] Step 2:

[0460] The terminal transmits the collected video, audio, and text data to the server. The server prepares the received data for input into the analysis device for analysis.

[0461] Step 3:

[0462] The server first begins analyzing the video data to recognize each action in the work procedure. In this process, it uses visual information to identify hand and finger movements and changes in the applications being used.

[0463] Step 4:

[0464] The server then processes the audio data into text and uses natural language processing technology to extract work instructions and explanations. This reveals the content of the audio instructions.

[0465] Step 5:

[0466] The server integrates the analyzed video, audio, and text information to generate a business process model. This model represents the entire business flow and includes the information necessary for business automation.

[0467] Step 6:

[0468] The server uses a program generation device to create an RPA program based on the generated business procedure model. This generates a script that can automate manual operations.

[0469] Step 7:

[0470] The server sends the generated RPA program to the terminal. The user checks the program received on the terminal and prepares for business process automation.

[0471] Step 8:

[0472] The user runs a program on their terminal, and the specified business procedures are automated. The terminal executes the RPA program sequentially, replacing manual work.

[0473] (Example 1)

[0474] Next, we will describe Example 1. 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."

[0475] In automating business processes, it is difficult for users without specialized programming skills to efficiently automate their own work procedures. Furthermore, existing systems have challenges in integrating different information formats (video, audio, text) and accurately generating work instructions. This often leads to delays in creating automation programs necessary for improving business efficiency and productivity.

[0476] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0477] In this invention, the server includes means for collecting video information using an information acquisition device for recording business procedures, means for acquiring and recording audio and text information, and means for transmitting the acquired information to a data processing device using communication means. As a result, users can integrate video, audio, and text information, automatically construct a business procedure model, and generate efficient business automation programs without requiring complex programming.

[0478] An "information acquisition device" is a device used to collect video information in the recording of work procedures.

[0479] "Means for acquiring and recording voice and text information" refers to a system that collects voice commands and instructions in business procedures and records them as text information as needed.

[0480] "Means of transmitting data to a data processing device using communication means" refers to transmission technology that sends acquired information to a data processing device on the server side, making it ready for analysis.

[0481] A "data processing device" is a device that analyzes collected video and audio information to recognize and organize business procedures.

[0482] A "processing device for recognizing behavioral processes" is a specialized device that identifies specific actions from video information and analyzes business processes.

[0483] "Natural language processing technology" is a technology that uses machine learning and artificial intelligence to convert speech information into text and extract business instructions.

[0484] A "model generation device" is a device that generates a consistent business procedure format based on recognized behavioral processes and instructions extracted using natural language processing.

[0485] A "business process automation program" is a program designed to automate business processes, built according to a generated business procedure format.

[0486] "Means of distribution to terminal devices" refers to a mechanism for delivering the constructed business automation program to the user's operating environment and making it executable.

[0487] This invention relates to a system that generates automation programs from records of business operations using an information acquisition device. This system integrates video, audio, and text information to form an automated business procedure as a process.

[0488] Users record work procedures as video using smartphones or dedicated camera devices. By simultaneously recording voice instructions and comments, detailed work content is provided. This information is saved on the device, allowing users to easily prepare the data.

[0489] The terminal transmits collected video, audio, and additional text information to the server. The server uses image processing software to analyze the received video information. Computer vision technology is used to recognize specific actions, forming a framework for work procedures. Audio information is converted into text using speech recognition technology, and natural language processing technology is used based on this. This enables the extraction of work orders and understanding of their content.

[0490] Based on the analysis results above, the server utilizes a model generation system incorporating machine learning algorithms to generate a business procedure model. This model is designed to meet the visualized business processes and automation needs.

[0491] The generated business process model is processed through a program generator to design business automation programs. For example, a script is generated to automate data entry tasks in Excel. This program is delivered from the server to the terminal, allowing the user to perform the specified tasks in an automated form.

[0492] As a concrete example, consider automating product management. Users photograph the product receiving process with their smartphones and provide voice instructions for barcode scanning and quantity verification. Based on this data, the server generates RPA programs for order entry and inventory updates, significantly reducing manual work for the user.

[0493] An example of a prompt message is: "We will record the order process and read out information such as product ID and quantity. Based on this data, we will create a procedure to generate an RPA program and automatically input the data into Excel."

[0494] Thus, the system of the present invention integrates diverse information formats to enable business automation and functions as a powerful tool for improving business efficiency.

[0495] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0496] Step 1:

[0497] Users record work procedures as video using a smartphone or a dedicated camera. Audio explanations are also recorded simultaneously. For example, they might video the process of preparing products for shipment and provide audio commentary such as, "Put the products in this cardboard box." The input consists of video and audio data, which are stored on the device.

[0498] Step 2:

[0499] The device transmits stored video and audio data to the server. Wi-Fi or mobile data communication is used for transmission. The input consists of video and audio files, which are then received by the server.

[0500] Step 3:

[0501] The server analyzes the received video data and performs processing to recognize specific actions. For example, it uses computer vision technology to identify product picking actions. This analysis requires video data as input and outputs the results of action identification.

[0502] Step 4:

[0503] The server converts audio data into text using speech recognition technology. In this process, "Put the products in the cardboard box" is converted into text data. The input is audio data, and the output is a transcript of the audio.

[0504] Step 5:

[0505] The server uses natural language processing techniques to extract work instructions using the converted text information and previously analyzed behavioral data. For example, the instruction "Put it in a cardboard box" might be extracted. Here, the input is the converted text and behavioral data, and the output is the extracted work instructions.

[0506] Step 6:

[0507] The server generates a business procedure model based on the extracted business instructions. This model includes a visualized business process and integrates actions and instructions at each stage. The input is the extracted instruction data, and the output is the business procedure model.

[0508] Step 7:

[0509] The server uses the generated business procedure model to construct a business automation program using a program generation device. For example, a script to automate data entry into Excel is generated. The input is a business procedure model, and the output is an executable program.

[0510] Step 8:

[0511] The server distributes the generated business automation program to the terminal. The distributed program is executed according to the user's instructions, automating the business process. The input for distribution is the generated program, and the output is the automation execution environment in the user's operating environment.

[0512] (Application Example 1)

[0513] Next, we will explain Application Example 1. In the following explanation, 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."

[0514] In the workplace, there is a demand for efficient and accurate execution of work procedures. However, traditional methods for visualizing and automating work procedures are complex, making them difficult for workers without programming skills to use. Furthermore, manual work processes can lead to errors and wasted time, reducing overall work efficiency.

[0515] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0516] In this invention, the server includes a presentation device that uses a video acquisition device to film work procedures, recognizes the actions of workers, and visualizes efficient work procedures; an analysis device that analyzes the collected data and generates a work procedure model; and a program generation device that generates an automation program based on the work procedure model. This enables efficient execution of work procedures and reduction of errors.

[0517] A "video acquisition device" is a device used to record work procedures in detail and plays a role in acquiring visual data of the work.

[0518] "Audio data" refers to auditory information related to work activities, including instructions and conversations during work.

[0519] "Text data" refers to information that expresses an overview of business procedures and points to note in written form.

[0520] An "analysis device" is a device that processes collected video data, audio data, and text data to generate a business procedure model.

[0521] A "business procedure model" is generated by an analysis device and represents the flow and operation procedures of a business process in an integrated manner.

[0522] A "program generation device" is a device that constructs automation programs based on business procedure models.

[0523] A "presentation device" is a device that visually displays efficient work procedures to workers and supports their work activities.

[0524] An "automation program" is a set of instructions for automatically executing business processes that were previously performed manually.

[0525] A "terminal" is a device on which a generated automation program is transmitted and executed.

[0526] The system that realizes this application example consists of a video acquisition device, an analysis device, a program generation device, and a presentation device. First, the user wears a video acquisition device such as smart glasses and films the work procedure. This records visual information of the work site in real time.

[0527] Next, the terminal collects voice and text data. The voice data collects work instructions and conversations during work, and is converted into text data. The analysis device receives this data and recognizes the worker's actions from the video data. This generates a work procedure model. Image recognition technologies such as Amazon Rekognition can be used in this process.

[0528] The server processes text data using the Google Cloud Natural Language API and extracts work instructions. Once the work procedure model is complete, an automation program is generated via a program generator. This program is used for automated data entry into applications such as Excel.

[0529] The generated automation program is delivered to the terminal via the cloud and used by the user when automating tasks. The display device visualizes efficient work procedures and provides work instructions through smart glasses. This allows users to reduce work errors and improve work efficiency.

[0530] As a concrete example, in a logistics center, when a worker retrieves an item from a shelf, information about the next item to be picked is visually displayed on their smart glasses. This allows the worker to pick items quickly and without making mistakes in the procedure.

[0531] Example prompt: "Develop an application that records video and audio of a worker wearing smart glasses picking items from shelves, and uses that data to automate efficient work procedures."

[0532] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0533] Step 1:

[0534] The user uses smart glasses to film the work procedure. A video acquisition device records the work and generates video data from the user's point of view. The input is real-time work video, and the output is a video data file. This file forms the basis for subsequent processing.

[0535] Step 2:

[0536] The terminal collects audio data while it is working. Ambient sounds and user verbal instructions are recorded as audio files. Input is real-time audio information, and output is an audio data file. This data is used to transcribe work instructions into text.

[0537] Step 3:

[0538] The device converts audio data into text data. Speech recognition software is used to analyze the audio file and generate the corresponding text data. The input is an audio data file, and the output is a text file.

[0539] Step 4:

[0540] The server analyzes the worker's movements using video data. An image recognition algorithm is used to identify each movement. The input is a video data file, and the output is the movement recognition result. This clarifies each step of the work procedure.

[0541] Step 5:

[0542] The server analyzes text data and extracts work instructions. Natural language processing techniques are used to clarify the content of the instructions. The input is a text data file, and the output is a list of work instructions. This list becomes part of a business procedure model.

[0543] Step 6:

[0544] The server integrates video data, motion recognition results, and work instructions to generate a work procedure model. This records the workflow as a single model. Inputs are video data, motion recognition results, and work instructions, while output is the work procedure model.

[0545] Step 7:

[0546] The server generates an automation program based on a business procedure model. It constructs a set of action instructions to automate a specific task. The input is the business procedure model, and the output is the automation program. This program ultimately achieves business process automation.

[0547] Step 8:

[0548] The generated automation program is delivered to the terminal and presented to the user. The program is used as part of the user's workflow. The input is the automation program, and the output is the program in a user-ready state. This step allows the user to perform their tasks efficiently.

[0549] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0550] This invention is a system for streamlining work procedures, which begins by capturing the workflow with a camera and collecting audio and text data. The user films their own work procedures using a video acquisition device. Furthermore, it collects audio instructions and explanations given during work, and the terminal records this video and audio data, as well as manually entered text data.

[0551] The terminal sends the collected data to the server, where an analysis device processes the data. By analyzing the video data, actions and operations within the work procedure are recognized, and the audio data is converted into text using natural language processing technology to extract work instructions. Then, this information is integrated to generate a work procedure model.

[0552] Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions. The server analyzes the user's facial expressions and tone of voice using cameras and sensors to infer their emotional state. This makes it possible to identify areas that need improvement, such as which parts of the work procedures are causing the user stress.

[0553] The emotion engine generates automated business processes on the server based on the emotional information it receives, adapting the program to the user's emotions. For example, in sections where the user feels anxious, it may add detailed explanations or prioritize presenting simplified work procedures. The generated program is then delivered to the terminal, enabling the user to effectively utilize automated business processes while reducing their workload.

[0554] Thus, the system of the present invention not only improves the efficiency of operations but also enables flexible work support that takes into account the user's emotional state. As a specific example, in telephone support operations, the system could automatically detect situations in which the user feels stressed and provide real-time advice or stress reduction measures.

[0555] The following describes the processing flow.

[0556] Step 1:

[0557] Users film their work procedures using a smartphone or dedicated camera. During filming, they provide instructions and explanations related to the work via voice, and the device records this video and audio data. It is also possible to manually input important procedures and points to note as text data.

[0558] Step 2:

[0559] The terminal sends recorded video, audio, and text data to the server. The server receives this data and prepares it for business analysis.

[0560] Step 3:

[0561] The server analyzes video data to recognize each action in the work procedure. The analysis is performed by capturing hand and finger movements and changes in the display shown on the camera from visual information.

[0562] Step 4:

[0563] The server converts the audio data into text and extracts work instructions using natural language processing technology. This natural language processing ensures that the content of the audio instructions is clearly understood.

[0564] Step 5:

[0565] The server integrates the analyzed visual, audio, and text information to generate a business process model. This model contains all the information necessary for business process automation.

[0566] Step 6:

[0567] The server uses an emotion engine to analyze the user's emotions. It evaluates the user's facial expressions and voice intonation obtained through the camera and microphone to infer emotional states such as stress, anxiety, and satisfaction.

[0568] Step 7:

[0569] The server generates RPA programs adapted to the user's emotions based on emotional information and business procedure models. For example, if the user is confused, it may add detailed help messages.

[0570] Step 8:

[0571] The server sends the generated RPA program to the terminal. The user reviews the program delivered to the terminal and prepares to run it in a format that suits their work.

[0572] Step 9:

[0573] Users execute programs on the terminal, and automated work procedures are carried out. The terminal performs emotionally sensitive workflows and provides support to reduce the workload.

[0574] (Example 2)

[0575] Next, we will describe Example 2. 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."

[0576] Current systems designed to streamline business procedures lack flexible support that reflects user emotions, resulting in insufficient reduction of user stress and anxiety. This can lead to a decline in the quality of the user experience, not just a decrease in operational efficiency.

[0577] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0578] In this invention, the server includes means for analyzing the user's facial expressions and tone of voice to infer their emotional state, means for generating an automated program adapted to the user based on the emotional information, and means for distributing the generated automated program to a terminal. This makes it possible to provide work support adapted to the user's emotions, improve work efficiency, and reduce the user's stress and anxiety.

[0579] A "video acquisition device" is a device used to visually record work procedures.

[0580] "Audio data" refers to information recorded as sound, such as instructions or explanations required during work.

[0581] "Text data" refers to information obtained by converting audio into a document format.

[0582] An "analysis device" is a device used to analyze collected data and generate business procedure models.

[0583] A "business procedure model" is a model of procedures created to streamline business processes.

[0584] A "program generation device" is a device that generates automation programs based on business procedure models.

[0585] An "emotion recognition device" is a device that analyzes a user's facial expressions and tone of voice to infer their emotional state.

[0586] An "automation program" is a program that contains a series of instructions for automating business procedures.

[0587] "Distribution method" refers to the means of sending a program generated on a server to a terminal.

[0588] This invention provides a system that streamlines work procedures and offers support that responds to user emotions. This system consists of a video acquisition device, an audio data processing device, an analysis device and an emotion recognition device in a server, a program generation device, and a user terminal.

[0589] Users film work procedures with a camera and collect voice instructions and explanations spoken during work as audio data using a microphone. This data is integrated on the terminal and sent to the server. The analysis device on the server analyzes the video data and uses image recognition technology to recognize actions and operations during work. In addition, the audio data is converted into text data through natural language processing technology, and work instructions are extracted.

[0590] The server generates a business procedure model from these analysis results and builds an automation program based on this model. Furthermore, the server's emotion recognition device uses cameras and voice sensors to analyze the user's facial expressions and tone of voice and infer their emotional state. This allows the server to understand how the user feels during specific business procedures and generate an automation program adapted to the user based on the emotional information.

[0591] The generated programs are delivered to the user's terminal to support the efficient execution of tasks. For example, the system provides detailed explanations and simplified procedures for sections of work that cause the user anxiety. Specifically, in telephone support tasks, the system detects the user's stress in real time and provides timely advice to alleviate that stress.

[0592] Examples of prompts include, "Combine video and audio data to analyze the business procedure," and "Analyze the user's facial expressions and tone of voice to infer their emotions." Based on these prompts, the server processes the data as needed to provide the user with the best possible support.

[0593] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0594] Step 1:

[0595] Users film work procedures with a camera and record voice instructions and explanations during work using a microphone. The input data consists of visual video and audio data. The recorded video and audio data are temporarily stored on the device. This initial data collection by the user forms the basis for subsequent data analysis.

[0596] Step 2:

[0597] The terminal sends the collected video and audio data to the server. At this stage, the input is the data held within the terminal, and the output is the data sent to the server. Once the data transmission is complete, the server is ready for analysis.

[0598] Step 3:

[0599] The server analyzes the received video data to identify actions and operations in the work procedure. The input is the video data received by the server, and the output is the recognized action information. The server uses image recognition technology to analyze the user's actions frame by frame and extract the operation procedure.

[0600] Step 4:

[0601] The server converts audio data into text and extracts important work instructions. The input is audio data, and the output is text data obtained using natural language processing technology. The server uses speech recognition technology to analyze the text extracted from the audio and creates a list of the work instructions.

[0602] Step 5:

[0603] The server integrates the analysis results and generates a business procedure model. The input consists of motion information obtained from video analysis and work instructions from audio analysis, while the output is the business procedure model. Based on this data, the server assembles a model for creating efficient business procedures.

[0604] Step 6:

[0605] The server uses cameras and sensors to analyze facial expressions and voice tone to infer the user's emotional state. The input is real-time acquired facial expression data and voice tone, and the output is the inferred emotional state of the user. This allows the server to identify where the user is experiencing stress.

[0606] Step 7:

[0607] The server generates automated programs based on emotional states. Inputs are business procedure models and emotional information, and output is an automated program adapted to the user. The server adds explanations and simplified procedures to areas where anxiety is felt.

[0608] Step 8:

[0609] The server distributes the generated automation program to the terminal, which receives and executes the program. The input is the automation program received from the server, and the output is the program actually used by the user. This allows the user to perform their tasks efficiently and without stress.

[0610] (Application Example 2)

[0611] Next, we will explain application example 2. In the following explanation, 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."

[0612] There is a need to improve the efficiency of work procedures within factories and manage the emotional state of workers through new technologies. However, conventional systems have difficulty simultaneously optimizing work procedures and appropriately monitoring workers' emotional states, resulting in the challenge of not being able to improve work efficiency while reducing the burden on workers.

[0613] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0614] In this invention, the server includes means for capturing work procedures using a video acquisition device, means for collecting audio and text data, and an emotion recognition device for performing emotion analysis. This enables the streamlining of work procedures and flexible work support based on emotions.

[0615] A "video acquisition device" is a device used to visually record the procedures of work or tasks, and is equipped with a camera or other recording function.

[0616] "Audio data" refers to audio information, including instructions and explanations given during work, recorded in digital format.

[0617] "Text data" refers to data that expresses information related to business procedures in text format.

[0618] An "analysis device" is a device that analyzes video and audio data to generate a business procedure model.

[0619] An "emotion recognition device" is a device that analyzes a worker's facial expressions, tone of voice, etc., to infer their emotional state.

[0620] A "program generation device" is a device for generating automation programs based on business procedure models and emotional states.

[0621] An "information terminal" is a device that receives generated automation programs and makes them available for use by workers.

[0622] A "prompt message" is a formatted text used to present generated work instructions or solutions.

[0623] To realize this invention, first, a video acquisition device is used to film the work procedure using equipment installed at the work site. The user uses a microphone and sensors to collect audio data in real time. The acquired video and audio data are transmitted to a server via an information terminal. On the server, dedicated video analysis software is used to analyze the video data, extract the work procedure, and generate a procedure model.

[0624] The voice data is converted into text data using natural language processing technology, and the work instructions are analyzed. Specifically, conversion software such as Google Cloud Speech-to-Text can be used.

[0625] Furthermore, an emotion recognition device detects the worker's emotional state from their facial expressions and tone of voice. This uses hardware such as cameras and acoustic analysis systems. Based on the emotional data, the server identifies which work procedures the user is experiencing stress from.

[0626] The program generation device generates an automation program based on the work procedure model and emotional state, and distributes this program to an information terminal. The information terminal presents instructions to the worker visually or audibly. In situations where the worker is experiencing stress, for example, it might provide instructions such as, "Shall we reconfirm the quality standards for this part?" Another example of a prompt message could be, "Please provide a simplified procedure for the process that tends to cause fatigue during quality inspection on the conveyor belt."

[0627] This allows workers to enjoy a comfortable working environment while efficiently executing procedures. The system also has the flexibility to automatically suggest improvements to work processes by integrating with a generative AI model.

[0628] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0629] Step 1:

[0630] The user films the work procedure using a video acquisition device. The input is video data captured by the camera. The user applies the attached camera to record the entire necessary work process. The output is detailed visual data of the work procedure.

[0631] Step 2:

[0632] The terminal collects audio data at the work site. The input is audio information generated at the site, recorded in real time using a microphone. Data processing involves digitizing the audio files and preparing them for analysis. The output is a digital file of the audio data.

[0633] Step 3:

[0634] The terminal transfers the collected video and audio data to the server. The input is the digital video and audio files stored on the terminal. The output is the state in which this data has been prepared for analysis on the server side.

[0635] Step 4:

[0636] The server analyzes video data using video analysis software. The input is the video data arriving at the server. During data processing, the actions of each frame are identified and a business procedure model is generated. The output is the extracted business procedure results and model data.

[0637] Step 5:

[0638] The server converts speech data into text data using natural language processing techniques. The input is digitized speech data. The process includes speech recognition from the audio file and data calculations to generate text information. The output is text data extracted from the speech.

[0639] Step 6:

[0640] The server analyzes the user's emotional state using an emotion recognition device. The input consists of emotion-related feature information obtained from video and audio data. Data processing is performed using a machine learning algorithm to infer the emotional state. The output is the inferred result of the emotional state.

[0641] Step 7:

[0642] The program generation device generates an automated program based on a business procedure model and emotional state. The inputs are model data and emotional inference results. The process includes data processing to generate prompt statements using a generation AI model and write the optimal procedure. The output is the generated automated program.

[0643] Step 8:

[0644] The terminal receives automated programs generated from the server. The input is the automated program from the server. The terminal displays this program to the user via an interface, making it available for use. The output is business support information that the user can use.

[0645] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0646] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0647] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0648] [Fourth Embodiment]

[0649] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0650] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0651] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0652] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0653] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0654] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0655] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0656] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0657] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0658] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0659] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0660] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0661] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0662] This invention relates to a system for automating work procedures, which begins with capturing the workflow using a video acquisition device. The user captures the work procedure using a smartphone or dedicated camera and simultaneously collects audio data. If necessary, the user inputs an overview of the work procedure and points to note as text data, and all collected data is saved on the terminal.

[0663] The terminal sends the collected data to the server, where an analysis device processes the data. The server recognizes specific actions of the work procedure from the video data and converts the audio data into text. Then, it extracts work instructions using natural language processing technology and generates a work procedure model that integrates visual information, audio instructions, and text information.

[0664] Based on this model, the server automatically generates RPA programs using a program generation device. The generated programs are sent to terminals, and the tasks are automated according to the user's instructions. Specifically, if there is data entry work using Excel, a program is created that automatically processes the repetitive tasks that the user previously performed manually.

[0665] In this way, the system of the present invention can provide an environment in which even users without programming skills can easily automate business processes. This leads to increased efficiency in business operations and contributes to improving the competitiveness of companies.

[0666] The following describes the processing flow.

[0667] Step 1:

[0668] The user films the work procedure using a camera, which is a video acquisition device. During filming, the user also explains the procedure verbally, simultaneously collecting audio data. The terminal records this video and audio data and inputs notes about the work procedure as text data as needed.

[0669] Step 2:

[0670] The terminal transmits the collected video, audio, and text data to the server. The server prepares the received data for input into the analysis device for analysis.

[0671] Step 3:

[0672] The server first begins analyzing the video data to recognize each action in the work procedure. In this process, it uses visual information to identify hand and finger movements and changes in the applications being used.

[0673] Step 4:

[0674] The server then processes the audio data into text and uses natural language processing technology to extract work instructions and explanations. This reveals the content of the audio instructions.

[0675] Step 5:

[0676] The server integrates the analyzed video, audio, and text information to generate a business process model. This model represents the entire business flow and includes the information necessary for business automation.

[0677] Step 6:

[0678] The server uses a program generation device to create an RPA program based on the generated business procedure model. This generates a script that can automate manual operations.

[0679] Step 7:

[0680] The server sends the generated RPA program to the terminal. The user checks the program received on the terminal and prepares for business process automation.

[0681] Step 8:

[0682] The user runs a program on their terminal, and the specified business procedures are automated. The terminal executes the RPA program sequentially, replacing manual work.

[0683] (Example 1)

[0684] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0685] In automating business processes, it is difficult for users without specialized programming skills to efficiently automate their own work procedures. Furthermore, existing systems have challenges in integrating different information formats (video, audio, text) and accurately generating work instructions. This often leads to delays in creating automation programs necessary for improving business efficiency and productivity.

[0686] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0687] In this invention, the server includes means for collecting video information using an information acquisition device for recording business procedures, means for acquiring and recording audio and text information, and means for transmitting the acquired information to a data processing device using communication means. As a result, users can integrate video, audio, and text information, automatically construct a business procedure model, and generate efficient business automation programs without requiring complex programming.

[0688] An "information acquisition device" is a device used to collect video information in the recording of work procedures.

[0689] "Means for acquiring and recording voice and text information" refers to a system that collects voice commands and instructions in business procedures and records them as text information as needed.

[0690] "Means of transmitting data to a data processing device using communication means" refers to transmission technology that sends acquired information to a data processing device on the server side, making it ready for analysis.

[0691] A "data processing device" is a device that analyzes collected video and audio information to recognize and organize business procedures.

[0692] A "processing device for recognizing behavioral processes" is a specialized device that identifies specific actions from video information and analyzes business processes.

[0693] "Natural language processing technology" is a technology that uses machine learning and artificial intelligence to convert speech information into text and extract business instructions.

[0694] A "model generation device" is a device that generates a consistent business procedure format based on recognized behavioral processes and instructions extracted using natural language processing.

[0695] A "business process automation program" is a program designed to automate business processes, built according to a generated business procedure format.

[0696] "Means of distribution to terminal devices" refers to a mechanism for delivering the constructed business automation program to the user's operating environment and making it executable.

[0697] This invention relates to a system that generates automation programs from records of business operations using an information acquisition device. This system integrates video, audio, and text information to form an automated business procedure as a process.

[0698] Users record work procedures as video using smartphones or dedicated camera devices. By simultaneously recording voice instructions and comments, detailed work content is provided. This information is saved on the device, allowing users to easily prepare the data.

[0699] The terminal transmits collected video, audio, and additional text information to the server. The server uses image processing software to analyze the received video information. Computer vision technology is used to recognize specific actions, forming a framework for work procedures. Audio information is converted into text using speech recognition technology, and natural language processing technology is used based on this. This enables the extraction of work orders and understanding of their content.

[0700] Based on the analysis results above, the server utilizes a model generation system incorporating machine learning algorithms to generate a business procedure model. This model is designed to meet the visualized business processes and automation needs.

[0701] The generated business process model is processed through a program generator to design business automation programs. For example, a script is generated to automate data entry tasks in Excel. This program is delivered from the server to the terminal, allowing the user to perform the specified tasks in an automated form.

[0702] As a concrete example, consider automating product management. Users photograph the product receiving process with their smartphones and provide voice instructions for barcode scanning and quantity verification. Based on this data, the server generates RPA programs for order entry and inventory updates, significantly reducing manual work for the user.

[0703] An example of a prompt message is: "We will record the order process and read out information such as product ID and quantity. Based on this data, we will create a procedure to generate an RPA program and automatically input the data into Excel."

[0704] Thus, the system of the present invention integrates diverse information formats to enable business automation and functions as a powerful tool for improving business efficiency.

[0705] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0706] Step 1:

[0707] Users record work procedures as video using a smartphone or a dedicated camera. Audio explanations are also recorded simultaneously. For example, they might video the process of preparing products for shipment and provide audio commentary such as, "Put the products in this cardboard box." The input consists of video and audio data, which are stored on the device.

[0708] Step 2:

[0709] The device transmits stored video and audio data to the server. Wi-Fi or mobile data communication is used for transmission. The input consists of video and audio files, which are then received by the server.

[0710] Step 3:

[0711] The server analyzes the received video data and performs processing to recognize specific actions. For example, it uses computer vision technology to identify product picking actions. This analysis requires video data as input and outputs the results of action identification.

[0712] Step 4:

[0713] The server converts audio data into text using speech recognition technology. In this process, "Put the products in the cardboard box" is converted into text data. The input is audio data, and the output is a transcript of the audio.

[0714] Step 5:

[0715] The server uses natural language processing techniques to extract work instructions using the converted text information and previously analyzed behavioral data. For example, the instruction "Put it in a cardboard box" might be extracted. Here, the input is the converted text and behavioral data, and the output is the extracted work instructions.

[0716] Step 6:

[0717] The server generates a business procedure model based on the extracted business instructions. This model includes a visualized business process and integrates actions and instructions at each stage. The input is the extracted instruction data, and the output is the business procedure model.

[0718] Step 7:

[0719] The server uses the generated business procedure model to construct a business automation program using a program generation device. For example, a script to automate data entry into Excel is generated. The input is a business procedure model, and the output is an executable program.

[0720] Step 8:

[0721] The server distributes the generated business automation program to the terminal. The distributed program is executed according to the user's instructions, automating the business process. The input for distribution is the generated program, and the output is the automation execution environment in the user's operating environment.

[0722] (Application Example 1)

[0723] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0724] In the workplace, there is a demand for efficient and accurate execution of work procedures. However, traditional methods for visualizing and automating work procedures are complex, making them difficult for workers without programming skills to use. Furthermore, manual work processes can lead to errors and wasted time, reducing overall work efficiency.

[0725] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0726] In this invention, the server includes a presentation device that uses a video acquisition device to film work procedures, recognizes the actions of workers, and visualizes efficient work procedures; an analysis device that analyzes the collected data and generates a work procedure model; and a program generation device that generates an automation program based on the work procedure model. This enables efficient execution of work procedures and reduction of errors.

[0727] A "video acquisition device" is a device used to record work procedures in detail and plays a role in acquiring visual data of the work.

[0728] "Audio data" refers to auditory information related to work activities, including instructions and conversations during work.

[0729] "Text data" refers to information that expresses an overview of business procedures and points to note in written form.

[0730] An "analysis device" is a device that processes collected video data, audio data, and text data to generate a business procedure model.

[0731] A "business procedure model" is generated by an analysis device and represents the flow and operation procedures of a business process in an integrated manner.

[0732] A "program generation device" is a device that constructs automation programs based on business procedure models.

[0733] A "presentation device" is a device that visually displays efficient work procedures to workers and supports their work activities.

[0734] An "automation program" is a set of instructions for automatically executing business processes that were previously performed manually.

[0735] A "terminal" is a device on which a generated automation program is transmitted and executed.

[0736] The system that realizes this application example consists of a video acquisition device, an analysis device, a program generation device, and a presentation device. First, the user wears a video acquisition device such as smart glasses and films the work procedure. This records visual information of the work site in real time.

[0737] Next, the terminal collects voice and text data. The voice data collects work instructions and conversations during work, and is converted into text data. The analysis device receives this data and recognizes the worker's actions from the video data. This generates a work procedure model. Image recognition technologies such as Amazon Rekognition can be used in this process.

[0738] The server processes text data using the Google Cloud Natural Language API and extracts work instructions. Once the work procedure model is complete, an automation program is generated via a program generator. This program is used for automated data entry into applications such as Excel.

[0739] The generated automation program is delivered to the terminal via the cloud and used by the user when automating tasks. The display device visualizes efficient work procedures and provides work instructions through smart glasses. This allows users to reduce work errors and improve work efficiency.

[0740] As a concrete example, in a logistics center, when a worker retrieves an item from a shelf, information about the next item to be picked is visually displayed on their smart glasses. This allows the worker to pick items quickly and without making mistakes in the procedure.

[0741] Example prompt: "Develop an application that records video and audio of a worker wearing smart glasses picking items from shelves, and uses that data to automate efficient work procedures."

[0742] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0743] Step 1:

[0744] The user uses smart glasses to film the work procedure. A video acquisition device records the work and generates video data from the user's point of view. The input is real-time work video, and the output is a video data file. This file forms the basis for subsequent processing.

[0745] Step 2:

[0746] The terminal collects audio data while it is working. Ambient sounds and user verbal instructions are recorded as audio files. Input is real-time audio information, and output is an audio data file. This data is used to transcribe work instructions into text.

[0747] Step 3:

[0748] The device converts audio data into text data. Speech recognition software is used to analyze the audio file and generate the corresponding text data. The input is an audio data file, and the output is a text file.

[0749] Step 4:

[0750] The server analyzes the worker's movements using video data. An image recognition algorithm is used to identify each movement. The input is a video data file, and the output is the movement recognition result. This clarifies each step of the work procedure.

[0751] Step 5:

[0752] The server analyzes text data and extracts work instructions. Natural language processing techniques are used to clarify the content of the instructions. The input is a text data file, and the output is a list of work instructions. This list becomes part of a business procedure model.

[0753] Step 6:

[0754] The server integrates video data, motion recognition results, and work instructions to generate a work procedure model. This records the workflow as a single model. Inputs are video data, motion recognition results, and work instructions, while output is the work procedure model.

[0755] Step 7:

[0756] The server generates an automation program based on a business procedure model. It constructs a set of action instructions to automate a specific task. The input is the business procedure model, and the output is the automation program. This program ultimately achieves business process automation.

[0757] Step 8:

[0758] The generated automation program is delivered to the terminal and presented to the user. The program is used as part of the user's workflow. The input is the automation program, and the output is the program in a user-ready state. This step allows the user to perform their tasks efficiently.

[0759] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0760] This invention is a system for streamlining work procedures, which begins by capturing the workflow with a camera and collecting audio and text data. The user films their own work procedures using a video acquisition device. Furthermore, it collects audio instructions and explanations given during work, and the terminal records this video and audio data, as well as manually entered text data.

[0761] The terminal sends the collected data to the server, where an analysis device processes the data. By analyzing the video data, actions and operations within the work procedure are recognized, and the audio data is converted into text using natural language processing technology to extract work instructions. Then, this information is integrated to generate a work procedure model.

[0762] Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions. The server analyzes the user's facial expressions and tone of voice using cameras and sensors to infer their emotional state. This makes it possible to identify areas that need improvement, such as which parts of the work procedures are causing the user stress.

[0763] The emotion engine generates automated business processes on the server based on the emotional information it receives, adapting the program to the user's emotions. For example, in sections where the user feels anxious, it may add detailed explanations or prioritize presenting simplified work procedures. The generated program is then delivered to the terminal, enabling the user to effectively utilize automated business processes while reducing their workload.

[0764] Thus, the system of the present invention not only improves the efficiency of operations but also enables flexible work support that takes into account the user's emotional state. As a specific example, in telephone support operations, the system could automatically detect situations in which the user feels stressed and provide real-time advice or stress reduction measures.

[0765] The following describes the processing flow.

[0766] Step 1:

[0767] Users film their work procedures using a smartphone or dedicated camera. During filming, they provide instructions and explanations related to the work via voice, and the device records this video and audio data. It is also possible to manually input important procedures and points to note as text data.

[0768] Step 2:

[0769] The terminal sends recorded video, audio, and text data to the server. The server receives this data and prepares it for business analysis.

[0770] Step 3:

[0771] The server analyzes video data to recognize each action in the work procedure. The analysis is performed by capturing hand and finger movements and changes in the display shown on the camera from visual information.

[0772] Step 4:

[0773] The server converts the audio data into text and extracts work instructions using natural language processing technology. This natural language processing ensures that the content of the audio instructions is clearly understood.

[0774] Step 5:

[0775] The server integrates the analyzed visual, audio, and text information to generate a business process model. This model contains all the information necessary for business process automation.

[0776] Step 6:

[0777] The server uses an emotion engine to analyze the user's emotions. It evaluates the user's facial expressions and voice intonation obtained through the camera and microphone to infer emotional states such as stress, anxiety, and satisfaction.

[0778] Step 7:

[0779] The server generates RPA programs adapted to the user's emotions based on emotional information and business procedure models. For example, if the user is confused, it may add detailed help messages.

[0780] Step 8:

[0781] The server sends the generated RPA program to the terminal. The user reviews the program delivered to the terminal and prepares to run it in a format that suits their work.

[0782] Step 9:

[0783] Users execute programs on the terminal, and automated work procedures are carried out. The terminal performs emotionally sensitive workflows and provides support to reduce the workload.

[0784] (Example 2)

[0785] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0786] Current systems designed to streamline business procedures lack flexible support that reflects user emotions, resulting in insufficient reduction of user stress and anxiety. This can lead to a decline in the quality of the user experience, not just a decrease in operational efficiency.

[0787] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0788] In this invention, the server includes means for analyzing the user's facial expressions and tone of voice to infer their emotional state, means for generating an automated program adapted to the user based on the emotional information, and means for distributing the generated automated program to a terminal. This makes it possible to provide work support adapted to the user's emotions, improve work efficiency, and reduce the user's stress and anxiety.

[0789] A "video acquisition device" is a device used to visually record work procedures.

[0790] "Audio data" refers to information recorded as sound, such as instructions or explanations required during work.

[0791] "Text data" refers to information obtained by converting audio into a document format.

[0792] An "analysis device" is a device used to analyze collected data and generate business procedure models.

[0793] A "business procedure model" is a model of procedures created to streamline business processes.

[0794] A "program generation device" is a device that generates automation programs based on business procedure models.

[0795] An "emotion recognition device" is a device that analyzes a user's facial expressions and tone of voice to infer their emotional state.

[0796] An "automation program" is a program that contains a series of instructions for automating business procedures.

[0797] "Distribution method" refers to the means of sending a program generated on a server to a terminal.

[0798] This invention provides a system that streamlines work procedures and offers support that responds to user emotions. This system consists of a video acquisition device, an audio data processing device, an analysis device and an emotion recognition device in a server, a program generation device, and a user terminal.

[0799] Users film work procedures with a camera and collect voice instructions and explanations spoken during work as audio data using a microphone. This data is integrated on the terminal and sent to the server. The analysis device on the server analyzes the video data and uses image recognition technology to recognize actions and operations during work. In addition, the audio data is converted into text data through natural language processing technology, and work instructions are extracted.

[0800] The server generates a business procedure model from these analysis results and builds an automation program based on this model. Furthermore, the server's emotion recognition device uses cameras and voice sensors to analyze the user's facial expressions and tone of voice and infer their emotional state. This allows the server to understand how the user feels during specific business procedures and generate an automation program adapted to the user based on the emotional information.

[0801] The generated programs are delivered to the user's terminal to support the efficient execution of tasks. For example, the system provides detailed explanations and simplified procedures for sections of work that cause the user anxiety. Specifically, in telephone support tasks, the system detects the user's stress in real time and provides timely advice to alleviate that stress.

[0802] Examples of prompts include, "Combine video and audio data to analyze the business procedure," and "Analyze the user's facial expressions and tone of voice to infer their emotions." Based on these prompts, the server processes the data as needed to provide the user with the best possible support.

[0803] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0804] Step 1:

[0805] Users film work procedures with a camera and record voice instructions and explanations during work using a microphone. The input data consists of visual video and audio data. The recorded video and audio data are temporarily stored on the device. This initial data collection by the user forms the basis for subsequent data analysis.

[0806] Step 2:

[0807] The terminal sends the collected video and audio data to the server. At this stage, the input is the data held within the terminal, and the output is the data sent to the server. Once the data transmission is complete, the server is ready for analysis.

[0808] Step 3:

[0809] The server analyzes the received video data to identify actions and operations in the work procedure. The input is the video data received by the server, and the output is the recognized action information. The server uses image recognition technology to analyze the user's actions frame by frame and extract the operation procedure.

[0810] Step 4:

[0811] The server converts audio data into text and extracts important work instructions. The input is audio data, and the output is text data obtained using natural language processing technology. The server uses speech recognition technology to analyze the text extracted from the audio and creates a list of the work instructions.

[0812] Step 5:

[0813] The server integrates the analysis results and generates a business procedure model. The input consists of motion information obtained from video analysis and work instructions from audio analysis, while the output is the business procedure model. Based on this data, the server assembles a model for creating efficient business procedures.

[0814] Step 6:

[0815] The server uses cameras and sensors to analyze facial expressions and voice tone to infer the user's emotional state. The input is real-time acquired facial expression data and voice tone, and the output is the inferred emotional state of the user. This allows the server to identify where the user is experiencing stress.

[0816] Step 7:

[0817] The server generates automated programs based on emotional states. Inputs are business procedure models and emotional information, and output is an automated program adapted to the user. The server adds explanations and simplified procedures to areas where anxiety is felt.

[0818] Step 8:

[0819] The server distributes the generated automation program to the terminal, which receives and executes the program. The input is the automation program received from the server, and the output is the program actually used by the user. This allows the user to perform their tasks efficiently and without stress.

[0820] (Application Example 2)

[0821] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0822] There is a need to improve the efficiency of work procedures within factories and manage the emotional state of workers through new technologies. However, conventional systems have difficulty simultaneously optimizing work procedures and appropriately monitoring workers' emotional states, resulting in the challenge of not being able to improve work efficiency while reducing the burden on workers.

[0823] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0824] In this invention, the server includes means for capturing work procedures using a video acquisition device, means for collecting audio and text data, and an emotion recognition device for performing emotion analysis. This enables the streamlining of work procedures and flexible work support based on emotions.

[0825] A "video acquisition device" is a device used to visually record the procedures of work or tasks, and is equipped with a camera or other recording function.

[0826] "Audio data" refers to audio information, including instructions and explanations given during work, recorded in digital format.

[0827] "Text data" refers to data that expresses information related to business procedures in text format.

[0828] An "analysis device" is a device that analyzes video and audio data to generate a business procedure model.

[0829] An "emotion recognition device" is a device that analyzes a worker's facial expressions, tone of voice, etc., to infer their emotional state.

[0830] A "program generation device" is a device for generating automation programs based on business procedure models and emotional states.

[0831] An "information terminal" is a device that receives generated automation programs and makes them available for use by workers.

[0832] A "prompt message" is a formatted text used to present generated work instructions or solutions.

[0833] To realize this invention, first, a video acquisition device is used to film the work procedure using equipment installed at the work site. The user uses a microphone and sensors to collect audio data in real time. The acquired video and audio data are transmitted to a server via an information terminal. On the server, dedicated video analysis software is used to analyze the video data, extract the work procedure, and generate a procedure model.

[0834] The voice data is converted into text data using natural language processing technology, and the work instructions are analyzed. Specifically, conversion software such as Google Cloud Speech-to-Text can be used.

[0835] Furthermore, an emotion recognition device detects the worker's emotional state from their facial expressions and tone of voice. This uses hardware such as cameras and acoustic analysis systems. Based on the emotional data, the server identifies which work procedures the user is experiencing stress from.

[0836] The program generation device generates an automation program based on the work procedure model and emotional state, and distributes this program to an information terminal. The information terminal presents instructions to the worker visually or audibly. In situations where the worker is experiencing stress, for example, it might provide instructions such as, "Shall we reconfirm the quality standards for this part?" Another example of a prompt message could be, "Please provide a simplified procedure for the process that tends to cause fatigue during quality inspection on the conveyor belt."

[0837] This allows workers to enjoy a comfortable working environment while efficiently executing procedures. The system also has the flexibility to automatically suggest improvements to work processes by integrating with a generative AI model.

[0838] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0839] Step 1:

[0840] The user films the work procedure using a video acquisition device. The input is video data captured by the camera. The user applies the attached camera to record the entire necessary work process. The output is detailed visual data of the work procedure.

[0841] Step 2:

[0842] The terminal collects audio data at the work site. The input is audio information generated at the site, recorded in real time using a microphone. Data processing involves digitizing the audio files and preparing them for analysis. The output is a digital file of the audio data.

[0843] Step 3:

[0844] The terminal transfers the collected video and audio data to the server. The input is the digital video and audio files stored on the terminal. The output is the state in which this data has been prepared for analysis on the server side.

[0845] Step 4:

[0846] The server analyzes video data using video analysis software. The input is the video data arriving at the server. During data processing, the actions of each frame are identified and a business procedure model is generated. The output is the extracted business procedure results and model data.

[0847] Step 5:

[0848] The server converts speech data into text data using natural language processing techniques. The input is digitized speech data. The process includes speech recognition from the audio file and data calculations to generate text information. The output is text data extracted from the speech.

[0849] Step 6:

[0850] The server analyzes the user's emotional state using an emotion recognition device. The input consists of emotion-related feature information obtained from video and audio data. Data processing is performed using a machine learning algorithm to infer the emotional state. The output is the inferred result of the emotional state.

[0851] Step 7:

[0852] The program generation device generates an automated program based on a business procedure model and emotional state. The inputs are model data and emotional inference results. The process includes data processing to generate prompt statements using a generation AI model and write the optimal procedure. The output is the generated automated program.

[0853] Step 8:

[0854] The terminal receives automated programs generated from the server. The input is the automated program from the server. The terminal displays this program to the user via an interface, making it available for use. The output is business support information that the user can use.

[0855] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0856] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0857] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0858] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0859] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0860] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0861] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0862] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0863] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0864] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0865] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0866] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0867] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0868] 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.

[0869] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0870] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0871] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0872] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0873] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0874] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0875] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0876] The following is further disclosed regarding the embodiments described above.

[0877] (Claim 1)

[0878] A means of filming work procedures using a video acquisition device,

[0879] Means for collecting audio data and text data,

[0880] An analysis device for analyzing collected data and generating business procedure models,

[0881] A program generation device that generates automation programs based on business procedure models,

[0882] A means of distributing the generated automation program to the terminal,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, which includes the step of recognizing the actions of a work procedure from video data and obtaining analysis results based on that.

[0886] (Claim 3)

[0887] The system according to claim 1, further comprising the step of converting audio data into text and extracting the content of work instructions using natural language processing technology.

[0888] "Example 1"

[0889] (Claim 1)

[0890] A means for collecting video information using an information acquisition device for recording work procedures,

[0891] Means for acquiring and recording audio and text information,

[0892] A means for transmitting acquired information to a data processing device using communication means,

[0893] A data processing device for analyzing video information and recognizing the process of action,

[0894] A processing unit for converting audio information into text information and extracting work instructions using natural language processing technology,

[0895] A model generation device for generating business procedure formats from recognized behavioral processes and extracted work orders,

[0896] A program generation device for constructing business automation programs based on the generated business procedure format,

[0897] A means of distributing the constructed business automation program to terminal devices,

[0898] A system that includes this.

[0899] (Claim 2)

[0900] The system according to claim 1, comprising the step of identifying actions in a work procedure from video information and generating analysis results.

[0901] (Claim 3)

[0902] The system according to claim 1, comprising the step of converting audio information into text information and deriving a business description using natural language processing technology.

[0903] "Application Example 1"

[0904] (Claim 1)

[0905] A means of filming work procedures using a video acquisition device,

[0906] Means for collecting audio data and text data,

[0907] An analysis device for analyzing collected data and generating business procedure models,

[0908] A program generation device that generates automation programs based on business procedure models,

[0909] A means of distributing the generated automation program to the terminal,

[0910] A display device that recognizes the movements of workers and visualizes efficient work procedures,

[0911] A system that includes this.

[0912] (Claim 2)

[0913] The system according to claim 1, which includes the step of recognizing the actions of a work procedure from video data and obtaining analysis results based on that.

[0914] (Claim 3)

[0915] The system according to claim 1, further comprising the step of converting audio data into text and extracting the content of work instructions using natural language processing technology.

[0916] "Example 2 of combining an emotion engine"

[0917] (Claim 1)

[0918] A means of filming work procedures using a video acquisition device,

[0919] Means for collecting audio data and text data,

[0920] An analysis device for analyzing collected data and generating business procedure models,

[0921] A program generation device that generates automation programs based on business procedure models,

[0922] An emotion recognition device that analyzes the user's facial expressions and tone of voice to infer their emotional state,

[0923] A device that generates an automated program adapted to the user based on emotional information,

[0924] A means of distributing the generated automation program to the terminal,

[0925] A system that includes this.

[0926] (Claim 2)

[0927] The system according to claim 1, comprising the step of recognizing the actions of a work procedure from video data and obtaining analysis results.

[0928] (Claim 3)

[0929] The system according to claim 1, further comprising the step of converting audio data into text and extracting the content of work instructions using natural language processing technology.

[0930] "Application example 2 when combining with an emotional engine"

[0931] (Claim 1)

[0932] A means of filming work procedures using a video acquisition device,

[0933] Means for collecting audio data and text data,

[0934] An analysis device for analyzing collected data and generating business procedure models,

[0935] An emotion recognition device for performing emotion analysis,

[0936] A program generation device that generates an automation program based on a work procedure model and emotional state,

[0937] A means of distributing the generated automation program to an information terminal,

[0938] A system that includes this.

[0939] (Claim 2)

[0940] The system according to claim 1, comprising the step of recognizing the actions of a work procedure from video data and obtaining an analysis result that infers the emotional state.

[0941] (Claim 3)

[0942] The system according to claim 1, comprising the steps of converting audio data into text, extracting work instructions using natural language processing technology, and generating prompt sentences. [Explanation of Symbols]

[0943] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of filming work procedures using a video acquisition device, Means for collecting audio data and text data, An analysis device for analyzing collected data and generating business procedure models, A program generation device that generates automation programs based on business procedure models, A means of distributing the generated automation program to the terminal, A system that includes this.

2. The system according to claim 1, which includes the step of recognizing the actions of a work procedure from video data and obtaining analysis results based on that.

3. The system according to claim 1, further comprising the step of converting audio data into text and extracting the content of work instructions using natural language processing technology.

Images