system

Abstract

Provide a system. 【Solution means】 Means for receiving a proposal request from a user, Means for generating a list of necessary input items based on the proposal request, Means for sending a prompt to sequentially instruct the user to input based on the input item list, Means for receiving answers to each input item from the user, Means for checking whether all received input items are correctly input, Means for storing in a database when the input items are correctly input, Means for sending a notification of the completion of the storage to the user, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The present invention aims to solve the problems of oversight of mandatory input items and occurrence of confirmation processes due to input errors in the proposal decision-making and drafting process in corporate business, and the accompanying delay until approval. Thereby, it is intended to process proposal decisions quickly and accurately and improve work efficiency.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for receiving a proposal request from a user, means for generating a list of necessary input items, means for sending prompts to the user to sequentially input based on the input item list, means for receiving the user's input and verifying its accuracy, means for saving all inputs to a database if they are accurate, and means for notifying the user when saving is complete. This allows the user to input all necessary items without omission, enabling the rapid and accurate drafting of proposals for approval. Furthermore, by providing means for sending error messages and requesting re-entry if there are errors or omissions in the input items, the system realizes a system that allows the user to automatically correct their own mistakes.

[0006] A "proposal request" refers to a request that a user submits to begin creating a proposal for approval.

[0007] The "input item list" is a collection of items that indicate the information necessary for proposal approval, and specifically includes customer information, proposal details, estimated price, and approval deadline.

[0008] A "prompt" refers to instructions or messages displayed to the user to request specific input.

[0009] A "database" is a system for organizing and storing collected data, enabling the storage and retrieval of necessary data.

[0010] A "save completion notification" refers to a message sent to inform the user that the data they entered has been successfully saved to the database.

[0011] An "error message" refers to a message sent to inform a user when there is an error or missing information in their input.

[0012] "Re-entering" refers to the act of re-entering necessary information to correct errors or missing entries.

[0013] The "verification process" refers to the procedures and steps involved in checking whether all required fields for proposal approval have been entered correctly. [Brief explanation of the drawing]

[0014] [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] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when combined with an emotion engine.

Embodiments for Carrying Out the Invention

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered 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.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered 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, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] In order to implement the present invention, it is necessary to provide a system in which the user, terminal, and server cooperate to accurately execute the proposal approval process. A specific embodiment of this system is described below.

[0036] First, the user initiates the proposal approval process by giving instructions to the terminal via voice or text. For example, they might enter a request such as, "I want to draft a proposal for company XX to approve."

[0037] Next, the terminal that receives this request parses the request content and sends it to the server. The server confirms the request and generates a list of necessary input fields. This includes customer information, proposal details, estimated price, and approval deadline.

[0038] Based on this list of input items, the server generates prompts that instruct the user to enter the information sequentially and sends them to the terminal.

[0039] The terminal displays the received prompt to the user. For example, it might display "Please enter customer information." The user then enters "ABC Corporation." Similarly, prompts are displayed sequentially for all input fields sent from the server, and the user enters the information.

[0040] Once all input is complete, the terminal sends the user's input data to the server. The server verifies the received data to ensure that all required fields are entered correctly. If there are any missing entries or errors, the server generates an error message and sends a prompt to the terminal requesting re-entry.

[0041] If all fields are entered correctly, the server saves this data to the database. Once saving is complete, the server sends the result to the terminal, which notifies the user that "the proposal has been successfully submitted."

[0042] As a concrete example, a user might type "I want to draft a proposal for approval from company XX," and then be prompted to "Please enter customer information." The user would then type "ABC Corporation," and then be prompted to "Please enter the proposal details," to which the user would type "Implementation of a new system." This process is repeated for all required fields, and finally the data is sent to the server. The server checks the data, and if everything is entered correctly, it saves it to the database and notifies the terminal that saving is complete.

[0043] In this way, this system can help users draft accurate and complete proposals for approval, thereby improving work efficiency.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user instructs the terminal via voice or text, "I want to initiate a proposal for company XX to approve." This request is received by the terminal.

[0047] Step 2:

[0048] The terminal analyzes the user's request, confirms that it is a proposal approval request, and then sends the request details to the server.

[0049] Step 3:

[0050] The server analyzes the received proposal request and generates a list of necessary input fields. This list includes customer information, proposal details, estimated price, and approval deadline.

[0051] Step 4:

[0052] Based on the generated list of input items, the server sequentially generates prompts for each item, requesting input from the user, and sends them to the terminal.

[0053] Step 5:

[0054] The terminal displays the received prompt to the user. For example, it might display "Please enter customer information."

[0055] Step 6:

[0056] The user enters the required information according to the displayed prompts, and the terminal receives that input. For example, the user might enter "ABC Corporation".

[0057] Step 7:

[0058] The terminal collects input from the user and prompts for the next input field. This process is repeated for all required fields.

[0059] Step 8:

[0060] Once all required fields are entered, the device sends the collected data to the server in a single batch.

[0061] Step 9:

[0062] The server checks the received user input data and verifies that all fields have been entered completely. If there are any missing entries or errors, it generates an error message and sends a prompt to the terminal requesting re-entry.

[0063] Step 10:

[0064] If all fields are entered correctly, the server will save the data to the database.

[0065] Step 11:

[0066] Once saving to the database is complete, the server generates a save completion message and sends it to the terminal.

[0067] Step 12:

[0068] The terminal displays a message to the user indicating that the saved document has been successfully saved, and notifies them that "the proposal has been successfully submitted for approval."

[0069] (Example 1)

[0070] 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."

[0071] The current proposal approval system can be difficult for users to input all the necessary information completely and accurately, resulting in frequent errors and omissions. This leads to decreased work efficiency and increased re-entry time. Furthermore, manual data entry is time-consuming and prone to human error. Therefore, there is a need for a system that allows users to quickly and accurately submit proposals for approval.

[0072] 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.

[0073] In this invention, the server includes means for receiving a proposal request from a user, means for analyzing the proposal request, means for generating a list of necessary input items based on the proposal request, means for generating and sending prompts to the user to sequentially input based on the list of input items, means for receiving responses from the user for each input item, means for verifying whether all received input items have been entered correctly, means for generating an error message and requesting re-entry if there is an error in the input items, means for saving the input items to a database if they have been entered correctly, and means for sending a notification to the user that the saving is complete. This enables the user to quickly and accurately draft proposals for approval.

[0074] A "user" is a person who uses this system to initiate the proposal approval process and inputs the necessary information.

[0075] A "proposal request" is an instruction that a user enters via voice or text to initiate the proposal approval process.

[0076] A "terminal" is a device used by a user, specifically a device for entering requests and displaying prompts.

[0077] A "server" is a computer system that controls the entire system based on user input and requests, and processes and stores data.

[0078] "Natural language processing" is a technology that analyzes text and audio data and interprets the meaning and structure contained within them.

[0079] An "input item list" is a list that organizes the information necessary for proposal approval, and includes customer information, proposal details, estimated price, and approval deadline.

[0080] A "prompt" is a message or instruction that instructs the user to enter information based on a list of input fields.

[0081] An "error message" is a warning or instruction to re-enter information that is displayed when there is an error or deficiency in the user's input.

[0082] A "database" is an information aggregation system used to systematically manage and store data within a system.

[0083] A "save completion notification" is a confirmation message sent to the user after the server has successfully saved the data.

[0084] To implement the present invention, it is necessary to provide a system that enables users, terminals, and servers to work together to accurately execute the proposal approval process. This system aims to collect necessary data from user requests and quickly create error-free approval documents. A specific embodiment of this system is shown below.

[0085] First, the user gives instructions to the device via voice or text to begin drafting a proposal for approval. For example, the user inputs a request such as "I want to draft a proposal for approval for company XX" into a device such as a smartphone or computer. This device uses a natural language processing library (e.g., NLTK, spaCy) to analyze the content of the request. After analysis, the device sends the analysis results to the server.

[0086] Next, the server generates a list of input items necessary for proposal approval based on the received request. This list includes customer information, proposal details, estimated price, and approval deadline. Programming languages ​​such as Python and Java (registered trademarks) can be used for this, and database management systems (e.g., MySQL (registered trademark), PostgreSQL) can be utilized. The server then sends this input item list to the terminal in JSON format or another appropriate format.

[0087] The terminal displays prompts to the user sequentially based on a list of input fields received from the server. For example, a prompt saying "Please enter customer information" is displayed on a web browser. The user enters "ABC Corporation," then a prompt saying "Please enter proposal details" is displayed, and the user enters "Implementation of a new system." Specifically, these prompts are displayed as "Please enter customer information," "Please enter proposal details," "Please enter estimated price," and "Please enter approval deadline."

[0088] Once the user has completed all the inputs, the terminal sends the input data to the server. The server verifies the received data and checks that all required fields have been entered correctly. If there are any errors or missing entries in the data, the server generates an error message and sends it to the terminal along with a prompt to re-enter the information. For example, it might generate a message such as, "The estimated amount is not entered. Please re-enter it."

[0089] If all fields are entered correctly, the server saves the data to the database. After inserting the data using an SQL statement and saving is complete, the server notifies the terminal. The terminal then notifies the user that "the proposal has been successfully submitted," and this message is displayed as a pop-up in the web browser.

[0090] In this way, this system can help users accurately draft proposals for approval, thereby improving work efficiency. Furthermore, by utilizing a generative AI model, the system can further refine user input and achieve highly accurate data processing.

[0091] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0092] Step 1:

[0093] The user enters a request into their device via voice or text to begin drafting a proposal for approval. For example, they might type "I want to draft a proposal for company XX" into their smartphone or computer.

[0094] Input: User request via voice or text input.

[0095] Output: The terminal retrieves the request data.

[0096] Step 2:

[0097] The terminal receives a request from the user and parses the request using a natural language processing library (e.g., NLTK, spaCy). The parsing results include key information such as the name of the company subject to proposal approval and the content of the proposal. After parsing, the terminal sends these results to the server.

[0098] Input: User's request data

[0099] Data processing / calculations: Text analysis using natural language processing

[0100] Output: Send analysis results to the server

[0101] Step 3:

[0102] The server generates a list of input items necessary for proposal approval based on the received analysis results. This list includes customer information, proposal details, estimated price, and approval deadline. Programming languages ​​such as Python or Java are used to generate the list, and it is converted into a format compatible with the structure of the database management system (e.g., MySQL, PostgreSQL). The server sends this input item list to the terminal in JSON format or similar.

[0103] Input: Analysis results

[0104] Data processing / calculations: Generating a list of required input items.

[0105] Output: Send the list of input items to the terminal.

[0106] Step 4:

[0107] The terminal displays prompts to the user sequentially based on the list of input fields received from the server. For example, a prompt saying "Please enter customer information" is displayed on the web browser. The user enters "ABC Corporation," and then a prompt saying "Please enter your proposal" is displayed, to which the user enters "Implementation of a new system."

[0108] Input: Input item list

[0109] Output: Prompt displayed to the user

[0110] Step 5:

[0111] The user enters the required information sequentially according to the prompts displayed on the terminal.

[0112] Input: User input data in response to prompts (e.g., customer information, proposal details, estimated price, approval deadline)

[0113] Output: The terminal collects user input data.

[0114] Step 6:

[0115] The terminal collects all input data from the user and then sends that data to the server.

[0116] Input: User input data

[0117] Output: Input data sent to the server

[0118] Step 7:

[0119] The server validates the received input data. It checks if all required fields are entered correctly and generates an error message if any are missing or incorrect. Along with this error message, it sends a prompt to the terminal to re-enter the information. For example, it might generate a message such as, "The estimated amount is not entered. Please re-enter it."

[0120] Input: User input data

[0121] Data processing / calculations: Data validation and error message generation.

[0122] Output: Error messages and re-entry prompts sent to the terminal

[0123] Step 8:

[0124] The server verifies that all fields are entered correctly and then saves the input data to the database. It inserts the data using SQL statements, and once saving is complete, it generates a save completion notification and sends it to the terminal.

[0125] Input: Validated input data

[0126] Data processing / calculations: Saving data to a database.

[0127] Output: Sends a save completion notification to the device.

[0128] Step 9:

[0129] The terminal receives a notification from the server confirming that the save is complete and notifies the user that "the proposal has been successfully submitted." For example, this may appear as a pop-up message in the web browser.

[0130] Input: Save complete notification

[0131] Output: Completion notification to the user

[0132] (Application Example 1)

[0133] 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."

[0134] Conventional proposal approval systems faced challenges such as the significant time and effort required for users to accurately input the necessary information. Furthermore, frequent input errors and missing fields, along with the time-consuming corrections, often hindered the overall business process. Additionally, using voice input presented difficulties in accurately converting speech to text and generating appropriate prompts.

[0135] 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.

[0136] In this invention, the server includes means for receiving a proposal request from a user, means for generating a list of necessary input items based on the proposal request, means for sending prompts to the user to sequentially input based on the input item list, means for receiving the user's response to each input item, means for verifying whether all received input items have been entered correctly, means for saving the input items to a database if they have been entered correctly, means for sending a notification to the user that the saving is complete, means for analyzing voice input, and means for generating prompt sentences using a generation AI model. As a result, users can efficiently draft proposals for approval using voice input or text input, reducing input errors and missing items, and improving the overall efficiency of the business process.

[0137] A "user" refers to the person who enters a proposal approval request and then provides answers to the subsequent input fields.

[0138] A "proposal request" refers to the initial request a user enters to initiate the proposal approval process.

[0139] The "input item list" refers to a list that enumerates the data items necessary for drafting a proposal for approval.

[0140] A "prompt" refers to a series of input instructions displayed to the user based on a list of input fields.

[0141] "Answer" refers to the content that the user enters in response to a prompt.

[0142] A "database" refers to an information management system used to store accurate data received from users.

[0143] A "save completion notification" refers to a message that informs the user that the data has been accurately saved to the database.

[0144] "Voice input" refers to the sound a user makes through a microphone, and includes the process of recognizing, analyzing, and converting that sound into text.

[0145] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate appropriate prompt sentences in response to user requests.

[0146] In order to implement the present invention, a system is needed in which a server, terminal, and user cooperate to smoothly advance the proposal approval process.

[0147] First, to initiate the proposal approval process, the user sends a request to the terminal via voice input or text input. The voice input used here utilizes the speech_recognition library to convert the user's voice into text data. This voice data is collected and analyzed by the terminal's built-in microphone and speech recognition software.

[0148] Next, the terminal analyzes the received request and sends the data to the server. The server generates an input field list and sends it to the terminal. This input field list includes essential data such as customer information, proposal details, estimated price, and approval deadline.

[0149] The server then uses a generative AI model to generate prompt messages corresponding to each input item. This generative AI model employs algorithms based on natural language processing to construct prompt messages in a way that is easy for the user to understand. The generated prompt messages are sent to the terminal, which then displays them to the user.

[0150] The terminal displays prompts to the user sequentially, and the user enters the necessary data into each input field based on those prompts. For example, if the prompt is "Please enter customer information," the user would enter "ABC Corporation." Similarly, if the prompt is "Please enter proposal details," the user would enter "Implementation of a new system."

[0151] Once all inputs are complete, the terminal sends this data to the server. The server validates the received data to ensure that all input fields are filled in correctly. If there are any errors, it generates an error message and sends a prompt to the terminal requesting re-entry. If there are no errors, it saves the data to the database and sends a notification to the user that the data has been saved.

[0152] As a concrete example, the following prompt message may be displayed:

[0153] 1. "Please enter customer information."

[0154] 2. "Please enter your proposal."

[0155] 3. "Please enter the estimated price."

[0156] 4. "Please enter the approval deadline."

[0157] For example, if a user voice-inputs "I would like to submit a proposal for approval," the terminal will display "Please enter customer information," and the user will input "ABC Corporation." Similarly, when prompted to "Please enter proposal details," the user will input "Introduction of a new system," and the necessary information will be seamlessly collected on the server.

[0158] In this way, prompt generation using voice input analysis and generative AI models reduces the workload on users and enables the efficient and accurate drafting of proposals for approval.

[0159] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0160] Step 1:

[0161] The user inputs a request to initiate a proposal for approval. Specifically, in the case of voice input, the request is sent via the microphone using the speech_recognition library. This voice data is converted to text on the device. The input is the user's voice request, "I want to initiate a proposal for approval." The output is a text version of the request, "I want to initiate a proposal for approval."

[0162] Step 2:

[0163] The terminal analyzes the received request. The analyzed data is sent to the server as an HTTP request. The input is a text-based request: "I want to submit a proposal for approval." The output is a request that has been converted into a data format for transmission to the server.

[0164] Step 3:

[0165] The server analyzes the received request and generates a list of input fields for proposal approval. This list includes customer information, proposal details, estimated price, approval deadline, etc. The input is the submitted request data. The output is the generated list of input fields.

[0166] Step 4:

[0167] The server uses a generative AI model to generate prompt messages based on the input item list. The generated prompt messages are sent to the terminal. The input is the input item list. The output is the prompt messages generated by the generative AI model and sent to the terminal.

[0168] Step 5:

[0169] The terminal displays prompt messages to the user. For example, it might display the message, "Please enter customer information." The input is the prompt message received from the server. The output is the generation of the prompt message displayed to the user.

[0170] Step 6:

[0171] The user enters information into each input field according to the prompts. For example, they might enter "ABC Corporation". The input is the data entered by the user in response to the prompt displayed on the terminal. The output is the user's input data.

[0172] Step 7:

[0173] The terminal sends user input data to the server. The input is the data entered by the user. The output is data generated that is formatted for transmission to the server.

[0174] Step 8:

[0175] The server validates the received data and verifies that all required fields have been entered correctly. For example, it performs error checking to ensure there are no missing fields or input errors. The input is user input data, and the output is the validation results.

[0176] Step 9:

[0177] The server saves the data to the database if it is correct. It accepts verified data as input and generates saved verification information as output.

[0178] Step 10:

[0179] The server generates a message notifying the terminal that saving is complete and sends it. The input is confirmation that saving is complete. The output is a generated save completion notification message sent to the terminal.

[0180] Step 11:

[0181] The terminal displays a save completion notification to the user. The input is the save completion notification message received from the server. The output is the generation of the save completion notification message that will be displayed to the user.

[0182] Example of a prompt:

[0183] "Please enter customer information."

[0184] Please enter your proposal details.

[0185] "Please enter the estimated price."

[0186] "Please enter the approval deadline."

[0187] 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.

[0188] This document specifically describes an embodiment of the present invention: a proposal approval system in which an emotion engine is combined with the user, terminal, and server.

[0189] The user instructs the terminal via voice or text, "I want to draft a proposal for company XX," in order to initiate a proposal approval process. The terminal receives this request, analyzes the request, and sends it to the server. The server confirms the request and generates a list of necessary input fields. This list of input fields includes customer information, proposal details, estimated price, and approval deadline.

[0190] Next, the server generates prompts for each input field based on the generated input field list, instructing the user to enter the information sequentially, and sends these prompts to the terminal. The terminal displays these prompts to the user, who then enters the specific information. For example, it might display "Please enter customer information," and the user would enter "ABC Corporation." Similarly, prompts are displayed sequentially for each input field, and the user enters the information accordingly.

[0191] The terminal collects the data entered by the user, and once all required fields are filled in, it sends the data to the server. The server verifies the received data to confirm that all fields have been entered correctly. If there are any missing entries or errors, it generates an error message and requests re-entry.

[0192] If all fields are entered correctly, the server saves the data to the database. Once saving is complete, the server sends a save completion message to the terminal, and the terminal notifies the user that "the proposal has been successfully submitted."

[0193] Furthermore, this system incorporates an emotion engine. The emotion engine analyzes the user's facial expressions, voice tone, and input speed to recognize the user's emotions. For example, if the user's voice suddenly becomes louder or their input slows down, the emotion engine will determine that the user is experiencing stress or confusion. In such cases, the server supports the user by generating prompts that provide supplementary explanations and guidance and sending them to the terminal.

[0194] For example, if the emotion engine detects that a user is slow to enter customer information, the server will send detailed guidance such as, "Please enter the company name and contact information for customer information." This allows users to submit proposals smoothly without feeling stressed.

[0195] In this way, this system, which incorporates an emotion engine, can respond flexibly to the user's emotional state, making the proposal approval process more efficient and accurate.

[0196] The following describes the processing flow.

[0197] Step 1:

[0198] The user instructs the terminal via voice or text, "I want to draft a proposal for company XX to approve." The terminal receives this request.

[0199] Step 2:

[0200] The terminal analyzes the user's request, confirms that it is a proposal approval request, and then sends the request details to the server.

[0201] Step 3:

[0202] The server analyzes the received proposal request and generates a list of input fields necessary for proposal approval. This list includes customer information, proposal details, estimated price, and approval deadline.

[0203] Step 4:

[0204] Based on the generated list of input items, the server generates prompts for each item to sequentially instruct the user to enter the information, and sends these prompts to the terminal.

[0205] Step 5:

[0206] The terminal displays the received prompt to the user. For example, a prompt such as "Please enter customer information" might be displayed.

[0207] Step 6:

[0208] The user enters the required information according to the displayed prompts. For example, they might enter "ABC Corporation".

[0209] Step 7:

[0210] The terminal collects input from the user and prompts for the next input field. This process is repeated for all required fields.

[0211] Step 8:

[0212] Once the terminal confirms that all fields have been entered, it sends the collected data to the server in a single batch.

[0213] Step 9:

[0214] The server checks the received user input data and verifies that all items have been entered completely and accurately.

[0215] Step 10:

[0216] If there are any missing or incorrect entries, the server generates an error message and sends it to the terminal along with a prompt for re-entry. The terminal then displays this again to the user.

[0217] Step 11:

[0218] If all fields are entered correctly, the server will save the data to the database.

[0219] Step 12:

[0220] Once saving to the database is complete, the server generates a save completion message and sends it to the terminal.

[0221] Step 13:

[0222] The terminal displays a message to the user indicating that the saved document has been successfully saved. For example, it might notify the user that "The proposal has been successfully drafted."

[0223] Step 14:

[0224] The device activates an emotion engine when the user inputs data, analyzing the user's facial expressions, voice tone, and input speed in real time. This analysis is then sent to a server.

[0225] Step 15:

[0226] The server receives analysis results sent from the emotion engine and determines the user's emotional state. If stress or confusion is detected, the server generates a corresponding guidance prompt and sends it to the terminal.

[0227] Step 16:

[0228] Based on the analysis results of the emotion engine, the device will display prompts that provide supplementary explanations and guidance if the user is experiencing stress or confusion. For example, it might display, "You seem to be having trouble entering information, please enter the company name and contact information."

[0229] This series of steps allows users to accurately draft proposals for approval without experiencing stress. By combining this with an emotion engine, a system is created that can respond flexibly according to the user's emotional state.

[0230] (Example 2)

[0231] 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".

[0232] Conventional proposal approval systems often caused stress and frustration for users when performing cumbersome data entry tasks. Furthermore, the need to repeatedly re-enter data to correct errors and omissions reduced efficiency. Additionally, the lack of appropriate support tailored to users' emotional states exacerbated the burden of data entry.

[0233] 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.

[0234] In this invention, the server includes an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize emotions, means for generating prompts that provide supplementary explanations and guidance based on the user's emotional state, means for receiving a proposal request from the user, means for generating a list of necessary input items based on the proposal request, means for sending prompts to the user to sequentially input based on the input item list, means for receiving the user's response to each input item, means for confirming that all received input items have been entered correctly, means for saving the input items to a database if they have been entered correctly, and means for sending a notification to the user that the saving is complete. This makes it possible to respond flexibly according to the user's emotional state and to carry out the proposal approval process more efficiently and accurately.

[0235] A "proposal request" is an instruction or request that a user sends to the system to initiate the proposal approval process.

[0236] An "input item list" is a list that enumerates the items of information that the system requests from the user.

[0237] A "prompt" is a message or screen display that a system uses to instruct a user to enter information.

[0238] "Answer" refers to the information that the user enters in response to system prompts.

[0239] A "database" is a structured collection of data used by a system to store and manage information.

[0240] A "save completion notification" is a message sent to the user informing them that the system has successfully finished saving information to the database.

[0241] The "emotion engine" is a system module that analyzes the user's facial expressions, voice tone, and input speed to recognize their emotions.

[0242] "Supplementary explanations and guidance" refer to additional instructions or explanations provided when a user experiences confusion or stress during input.

[0243] An "error message" is a message that the system sends to the user prompting them to re-enter data when there are errors or deficiencies in the input data.

[0244] Regarding embodiments for carrying out the present invention, a proposal approval and drafting system in which an emotion engine is combined with the user, terminal, and server will be specifically described.

[0245] The user instructs the terminal via voice or text, "I want to draft a proposal for approval from company XX," with the intention of drafting a proposal for approval. The terminal, upon receiving this request, analyzes the request and sends it to the server. For example, Google's Speech-to-Text API is used for speech recognition, and a general natural language processing library is used for text analysis.

[0246] The server confirms the request and generates a list of necessary input fields. This list includes customer information, proposal details, estimated price, and approval deadline. Based on the input field list, the server generates prompts for each field, instructing the user to enter the information sequentially, and sends these prompts to the terminal. Generative AI models such as OpenAI® GPT-4® are used to generate the prompts.

[0247] The terminal displays prompts to the user, who then enters specific information. For example, it might display "Please enter customer information," and the user would enter "ABC Corporation." Similarly, prompts are displayed sequentially for each input field, and the user enters the information accordingly. The data entered by the user is collected by the terminal, and once all required fields have been completed, the data is sent to the server.

[0248] The server validates the received data to ensure all fields are entered correctly. If there are any missing entries or errors, it generates an error message prompting the user to re-enter the information. The error message includes concise instructions for the user to re-enter the incorrect fields. For example, a message such as "The estimated amount is not entered; please enter it again."

[0249] If all fields are entered correctly, the server saves the data to the database. Once saving is complete, the server sends a save completion message to the terminal, which then notifies the user. For example, it might notify the user that "the proposal has been successfully drafted."

[0250] This system incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize their emotions. The emotion engine utilizes IBM Watson® Tone Analyzer or Microsoft® Azure® Emotion API. For example, if a user's voice suddenly becomes louder or their input slows down, the emotion engine determines that the user is experiencing stress or confusion. In such cases, the server generates and sends prompts providing supplementary explanations and guidance to the terminal.

[0251] For example, if the emotion engine detects that a user is slow to enter customer information in response to the prompt "Please enter customer information," the server will send detailed guidance such as "Please enter company name and contact information." This allows users to submit proposals smoothly without feeling stressed.

[0252] In this way, this system, which incorporates an emotion engine, can respond flexibly to the user's emotional state, making the proposal approval process more efficient and accurate.

[0253] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0254] Step 1:

[0255] To initiate a proposal approval process, the user instructs the terminal via voice or text, saying, "I would like to initiate a proposal approval process for Company XX." Based on this input, the terminal uses speech recognition software (e.g., Google Speech-to-Text API) or text analysis software to analyze the request. The analyzed data becomes the request statement, "I would like to initiate a proposal approval process for Company XX."

[0256] Step 2:

[0257] The terminal sends the parsed request statement to the server. This request statement is the input necessary to convey the user's intent to the server. The server parses the received request statement and determines the list of input items to be generated. As output, the server generates an input item list that includes customer information, proposal details, estimated amount, and approval deadline.

[0258] Step 3:

[0259] The server generates prompts that sequentially instruct the user to enter information based on a list of input fields. Generative AI models such as OpenAI GPT-4 are used for this prompt generation. An example prompt generated is "Please enter customer information." This prompt is sent to the terminal and displayed to the user.

[0260] Step 4:

[0261] The terminal displays prompts to the user, who then enters specific information for each input field. For example, the user might enter "ABC Corporation". This input data is received by the terminal. The data entered by the user is temporarily stored on the terminal.

[0262] Step 5:

[0263] The terminal sends all collected input data to the server. This data includes customer information, proposal details, estimated price, and approval deadline. The server analyzes the received data and verifies that each item has been entered correctly. As output, the server obtains the verification results.

[0264] Step 6:

[0265] The server performs error checking based on the validation results of the input data. If there are errors or missing entries, the server generates an error message and sends a command to the terminal requesting re-entry. The user corrects the data by re-entering it.

[0266] Step 7:

[0267] If all fields are confirmed to be entered correctly, the server saves the data to the database. Databases such as MySQL and PostgreSQL can be used. Once saving to the database is complete, the server generates a completion notification and sends it to the terminal. The terminal then notifies the user that "the proposal has been successfully submitted."

[0268] Step 8:

[0269] The server incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize emotions. Examples of emotion engines used include IBM Watson Tone Analyzer and Microsoft Azure Emotion API. If the emotion engine detects user stress or confusion, the server generates and sends prompts providing supplementary explanations and guidance to the terminal. For example, if a user is slow to input information in response to "Please enter customer information," the server sends detailed guidance such as "Please enter company name and contact information for customer information." This allows users to smoothly draft proposals for approval without feeling stressed.

[0270] (Application Example 2)

[0271] 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 device 14 will be referred to as the "terminal."

[0272] The work in logistics centers is complex and requires many steps to be performed instantly, placing a heavy burden on employees. Furthermore, the stress and confusion employees experience during work significantly reduce work efficiency. Additionally, errors or mistakes in data entry necessitate re-entry, resulting in additional time and effort.

[0273] 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. In this invention, the server includes means for receiving a proposal request from a user, means for generating a list of necessary input items based on the proposal request, means for sending prompts to the user to sequentially input based on the input item list, means for receiving responses from the user to each input item, means for confirming whether all received input items have been entered correctly, means for saving the input items to a database if they have been entered correctly, means for sending a notification to the user that the saving is complete, means including an emotion engine for analyzing emotional states, and means for providing supplementary explanations and guidance based on the emotion analysis results. This reduces the stress and confusion that employees feel while working in a logistics center, enabling efficient and accurate work execution.

[0274] A "user" is an entity that uses a system to input information and perform tasks.

[0275] A "proposal request" is a request from a user to initiate a task or perform a specific process within the system.

[0276] An "input item list" is a list of necessary information that the user must enter into the system.

[0277] A "prompt" is a message from the system that instructs the user to input information sequentially.

[0278] "Answer" refers to the information that a user provides to the system based on the input fields.

[0279] A "database" is a system for storing and managing collected data.

[0280] An "emotion engine" is a device or program that analyzes a user's emotional state and evaluates stress and confusion.

[0281] "Supplementary Explanation and Guidance" refers to additional explanations and instructions provided when a user utilizes the system.

[0282] Mode for Carrying Out the Invention

[0283] The present invention is a proposal decision-making and planning system for a logistics center using an emotion engine. The main components used to implement this invention will be described below.

[0284] System Overview

[0285] In this system, the user makes a request through voice or text input, the server analyzes this and generates the necessary input items, and then presents a prompt to the user based on that. Furthermore, it analyzes the user's emotional state using an emotion engine and provides supplementary explanations and guidance as necessary.

[0286] Hardware

[0287] 1. Smartphone: <00OO910> It is used for the user to perform voice input or text input.

[0289] It plays the role of displaying a prompt to the user and sending the input data to the server.

[0290] 2. Server:

[0291] <00OO920>Receives and analyzes requests from the user.

[0292] Generates a list of necessary input items and prepares a prompt.

[0293] Analyzes the emotional state using an emotion engine and generates appropriate guidance.

[0294] Saves the received data in the database.

[0295] Software

[0296] 1. Flask:

[0297] It is used as a server - side web application framework.

[0298] 2. EmotionEngine:

[0299] A proprietary module for analyzing the user's emotional state.

[0300] It performs emotion analysis based on voice and text input.

[0301] 3. SpeechRecognition:

[0302] A library that converts voice input to text.

[0303] Processing flow

[0304] 1. User's voice input:

[0305] The user uses a smartphone to give voice input such as "I want to ship the goods."

[0306] 2. Conversion from voice to text:

[0307] The smartphone converts the voice input to text and sends it to the server.

[0308] 3. Generation of input item list:

[0309] The server analyzes the text of the voice input and generates a list of necessary input items (product name, quantity, shipping address, shipping deadline, etc.).

[0310] 4. Prompt presentation:

[0311] Based on the generated list of input fields, the server generates prompts that sequentially present the user with input fields and sends them to the smartphone.

[0312] Example: "Please enter the following information: Product name details" "Please enter the shipping address"

[0313] 5. Analysis of emotional state:

[0314] An emotion engine within the server analyzes the user's voice and input speed to determine if the user is experiencing stress or confusion.

[0315] 6. Supplementary explanations and guidance:

[0316] If the emotion engine detects a user's stress level, the server generates supplementary explanations and guidance and sends them to the smartphone.

[0317] Example: "Additional guidance: Please enter the product name, quantity, and shipping address."

[0318] 7. Saving input data:

[0319] If all user input fields are entered correctly, the server saves this information to the database.

[0320] 8. Completion notification:

[0321] Once data saving is complete, the server sends a saving completion notification to the user, which is then displayed to the user.

[0322] Specific example

[0323] When a user requests, "What should I do next?", the server provides detailed guidance such as, "Please enter the product name, quantity, and shipping address." This prompt might appear in a real-world scenario as follows:

[0324] "I want to ship the product. What should I do next?"

[0325] "I'm having trouble entering customer information. Please help me."

[0326] In this way, systems using emotion engines and prompts enable users to work efficiently in logistics centers without experiencing stress.

[0327] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0328] Step 1:

[0329] User voice input

[0330] The user uses their smartphone to make a voice input, such as "I want to ship the product." This voice data is then sent to the smartphone as input.

[0331] Step 2:

[0332] Speech-to-text conversion

[0333] The device (smartphone) uses the SpeechRecognition library to convert voice input into text data. Specifically, it inputs voice data into the speech recognition engine and outputs the resulting text data.

[0334] Step 3:

[0335] Send a request

[0336] The terminal sends the converted text data to the server. The text, as input data, is sent to the server in the form of an HTTP request. The server's endpoint receives this and prepares the data for analysis.

[0337] Step 4:

[0338] Generating an input item list

[0339] The server parses the received text data and generates a list of necessary input fields. For example, in response to a request such as "I want to ship the product," the server creates a list of input fields including product name, quantity, shipping address, and shipping deadline, and generates this as output data.

[0340] Step 5:

[0341] Prompt presentation

[0342] The server generates prompts that instruct the user to enter information sequentially based on the generated list of input fields. These prompts include text such as "Please enter the product name" or "Please enter the shipping address." These prompts are sent to the terminal and displayed to the user.

[0343] Step 6:

[0344] Receiving user input

[0345] The terminal receives text data entered by the user based on prompts and sends it to the server. The input data includes specific answers to each item provided by the user.

[0346] Step 7:

[0347] Analysis of emotional states

[0348] The server uses an emotion engine to analyze the user's input data, voice tone, and input speed. Based on the emotion engine's analysis, it determines whether the user is experiencing stress or confusion and outputs the result.

[0349] Step 8:

[0350] Providing supplementary explanations and guidance

[0351] Based on the analysis results of the emotion engine, the server generates prompts that provide supplementary explanations and guidance as needed. For example, if user stress is detected, it generates additional guidance such as "Please enter the product name, quantity, and shipping address" and sends it to the terminal.

[0352] Step 9:

[0353] Input data verification

[0354] The server verifies that all received user input data is entered correctly. If there are errors or missing data, it generates an error message and sends a prompt to the terminal requesting re-entry.

[0355] Step 10:

[0356] Data saving and completion notification

[0357] After all input data has been entered correctly and verified by the server, the data is saved to the database. Once saving is complete, the server generates a completion notification and sends it to the terminal. The user receives a completion notification on their terminal, such as "Proposal approval has been successfully submitted."

[0358] 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.

[0359] Data generation model 58 is a type of 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.

[0360] 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.

[0361] [Second Embodiment]

[0362] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0363] 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.

[0364] 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).

[0365] 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.

[0366] 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.

[0367] 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).

[0368] 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.

[0369] 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.

[0370] 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.

[0371] 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.

[0372] 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.

[0373] 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".

[0374] In order to implement the present invention, it is necessary to provide a system in which the user, terminal, and server cooperate to accurately execute the proposal approval process. A specific embodiment of this system is described below.

[0375] First, the user initiates the proposal approval process by giving instructions to the terminal via voice or text. For example, they might enter a request such as, "I want to draft a proposal for company XX to approve."

[0376] Next, the terminal that receives this request parses the request content and sends it to the server. The server confirms the request and generates a list of necessary input fields. This includes customer information, proposal details, estimated price, and approval deadline.

[0377] Based on this list of input items, the server generates prompts that instruct the user to enter the information sequentially and sends them to the terminal.

[0378] The terminal displays the received prompt to the user. For example, it might display "Please enter customer information." The user then enters "ABC Corporation." Similarly, prompts are displayed sequentially for all input fields sent from the server, and the user enters the information.

[0379] Once all input is complete, the terminal sends the user's input data to the server. The server verifies the received data to ensure that all required fields are entered correctly. If there are any missing entries or errors, the server generates an error message and sends a prompt to the terminal requesting re-entry.

[0380] If all fields are entered correctly, the server saves this data to the database. Once saving is complete, the server sends the result to the terminal, which notifies the user that "the proposal has been successfully submitted."

[0381] As a concrete example, a user might type "I want to draft a proposal for approval from company XX," and then be prompted to "Please enter customer information." The user would then type "ABC Corporation," and then be prompted to "Please enter the proposal details," to which the user would type "Implementation of a new system." This process is repeated for all required fields, and finally the data is sent to the server. The server checks the data, and if everything is entered correctly, it saves it to the database and notifies the terminal that saving is complete.

[0382] In this way, this system can help users draft accurate and complete proposals for approval, thereby improving work efficiency.

[0383] The following describes the processing flow.

[0384] Step 1:

[0385] The user instructs the terminal via voice or text, "I want to initiate a proposal for company XX to approve." This request is received by the terminal.

[0386] Step 2:

[0387] The terminal analyzes the user's request, confirms that it is a proposal approval request, and then sends the request details to the server.

[0388] Step 3:

[0389] The server analyzes the received proposal request and generates a list of necessary input fields. This list includes customer information, proposal details, estimated price, and approval deadline.

[0390] Step 4:

[0391] Based on the generated list of input items, the server sequentially generates prompts for each item, requesting input from the user, and sends them to the terminal.

[0392] Step 5:

[0393] The terminal displays the received prompt to the user. For example, it might display "Please enter customer information."

[0394] Step 6:

[0395] The user enters the required information according to the displayed prompts, and the terminal receives that input. For example, the user might enter "ABC Corporation".

[0396] Step 7:

[0397] The terminal collects input from the user and prompts for the next input field. This process is repeated for all required fields.

[0398] Step 8:

[0399] Once all required fields are entered, the device sends the collected data to the server in a single batch.

[0400] Step 9:

[0401] The server checks the received user input data and verifies that all fields have been entered completely. If there are any missing entries or errors, it generates an error message and sends a prompt to the terminal requesting re-entry.

[0402] Step 10:

[0403] If all fields are entered correctly, the server will save the data to the database.

[0404] Step 11:

[0405] Once saving to the database is complete, the server generates a save completion message and sends it to the terminal.

[0406] Step 12:

[0407] The terminal displays a message to the user indicating that the saved document has been successfully saved, and notifies them that "the proposal has been successfully submitted for approval."

[0408] (Example 1)

[0409] 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."

[0410] The current proposal approval system can be difficult for users to input all the necessary information completely and accurately, resulting in frequent errors and omissions. This leads to decreased work efficiency and increased re-entry time. Furthermore, manual data entry is time-consuming and prone to human error. Therefore, there is a need for a system that allows users to quickly and accurately submit proposals for approval.

[0411] 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.

[0412] In this invention, the server includes means for receiving a proposal request from a user, means for analyzing the proposal request, means for generating a list of necessary input items based on the proposal request, means for generating and sending prompts to the user to sequentially input based on the list of input items, means for receiving responses from the user for each input item, means for verifying whether all received input items have been entered correctly, means for generating an error message and requesting re-entry if there is an error in the input items, means for saving the input items to a database if they have been entered correctly, and means for sending a notification to the user that the saving is complete. This enables the user to quickly and accurately draft proposals for approval.

[0413] A "user" is a person who uses this system to initiate the proposal approval process and inputs the necessary information.

[0414] A "proposal request" is an instruction that a user enters via voice or text to initiate the proposal approval process.

[0415] A "terminal" is a device used by a user, specifically a device for entering requests and displaying prompts.

[0416] A "server" is a computer system that controls the entire system based on user input and requests, and processes and stores data.

[0417] "Natural language processing" is a technology that analyzes text and audio data and interprets the meaning and structure contained within them.

[0418] An "input item list" is a list that organizes the information necessary for proposal approval, and includes customer information, proposal details, estimated price, and approval deadline.

[0419] A "prompt" is a message or instruction that instructs the user to enter information based on a list of input fields.

[0420] An "error message" is a warning or instruction to re-enter information that is displayed when there is an error or deficiency in the user's input.

[0421] A "database" is an information aggregation system used to systematically manage and store data within a system.

[0422] A "save completion notification" is a confirmation message sent to the user after the server has successfully saved the data.

[0423] To implement the present invention, it is necessary to provide a system that enables users, terminals, and servers to work together to accurately execute the proposal approval process. This system aims to collect necessary data from user requests and quickly create error-free approval documents. A specific embodiment of this system is shown below.

[0424] First, the user gives instructions to the device via voice or text to begin drafting a proposal for approval. For example, the user inputs a request such as "I want to draft a proposal for approval for company XX" into a device such as a smartphone or computer. This device uses a natural language processing library (e.g., NLTK, spaCy) to analyze the content of the request. After analysis, the device sends the analysis results to the server.

[0425] Next, the server generates a list of input items necessary for proposal approval based on the received request. This list includes customer information, proposal details, estimated price, and approval deadline. Programming languages ​​such as Python or Java can be used for this, and database management systems (e.g., MySQL, PostgreSQL) can be utilized. The server then sends this input item list to the terminal in JSON format or another appropriate format.

[0426] The terminal displays prompts to the user sequentially based on a list of input fields received from the server. For example, a prompt saying "Please enter customer information" is displayed on a web browser. The user enters "ABC Corporation," then a prompt saying "Please enter proposal details" is displayed, and the user enters "Implementation of a new system." Specifically, these prompts are displayed as "Please enter customer information," "Please enter proposal details," "Please enter estimated price," and "Please enter approval deadline."

[0427] Once the user has completed all the inputs, the terminal sends the input data to the server. The server verifies the received data and checks that all required fields have been entered correctly. If there are any errors or missing entries in the data, the server generates an error message and sends it to the terminal along with a prompt to re-enter the information. For example, it might generate a message such as, "The estimated amount is not entered. Please re-enter it."

[0428] If all fields are entered correctly, the server saves the data to the database. After inserting the data using an SQL statement and saving is complete, the server notifies the terminal. The terminal then notifies the user that "the proposal has been successfully submitted," and this message is displayed as a pop-up in the web browser.

[0429] In this way, this system can help users accurately draft proposals for approval, thereby improving work efficiency. Furthermore, by utilizing a generative AI model, the system can further refine user input and achieve highly accurate data processing.

[0430] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0431] Step 1:

[0432] The user enters a request into their device via voice or text to begin drafting a proposal for approval. For example, they might type "I want to draft a proposal for company XX" into their smartphone or computer.

[0433] Input: User request via voice or text input.

[0434] Output: The terminal retrieves the request data.

[0435] Step 2:

[0436] The terminal receives a request from the user and parses the request using a natural language processing library (e.g., NLTK, spaCy). The parsing results include key information such as the name of the company subject to proposal approval and the content of the proposal. After parsing, the terminal sends these results to the server.

[0437] Input: User's request data

[0438] Data processing / calculations: Text analysis using natural language processing

[0439] Output: Send analysis results to the server

[0440] Step 3:

[0441] The server generates a list of input items necessary for proposal approval based on the received analysis results. This list includes customer information, proposal details, estimated price, and approval deadline. Programming languages ​​such as Python or Java are used to generate the list, and it is converted into a format compatible with the structure of the database management system (e.g., MySQL, PostgreSQL). The server sends this input item list to the terminal in JSON format or similar.

[0442] Input: Analysis results

[0443] Data processing / calculations: Generating a list of required input items.

[0444] Output: Send the list of input items to the terminal.

[0445] Step 4:

[0446] The terminal displays prompts to the user sequentially based on the list of input fields received from the server. For example, a prompt saying "Please enter customer information" is displayed on the web browser. The user enters "ABC Corporation," and then a prompt saying "Please enter your proposal" is displayed, to which the user enters "Implementation of a new system."

[0447] Input: Input item list

[0448] Output: Prompt displayed to the user

[0449] Step 5:

[0450] The user enters the required information sequentially according to the prompts displayed on the terminal.

[0451] Input: User input data in response to prompts (e.g., customer information, proposal details, estimated price, approval deadline)

[0452] Output: The terminal collects user input data.

[0453] Step 6:

[0454] The terminal collects all input data from the user and then sends that data to the server.

[0455] Input: User input data

[0456] Output: Input data sent to the server

[0457] Step 7:

[0458] The server validates the received input data. It checks if all required fields are entered correctly and generates an error message if any are missing or incorrect. Along with this error message, it sends a prompt to the terminal to re-enter the information. For example, it might generate a message such as, "The estimated amount is not entered. Please re-enter it."

[0459] Input: User input data

[0460] Data processing / calculations: Data validation and error message generation.

[0461] Output: Error messages and re-entry prompts sent to the terminal

[0462] Step 8:

[0463] The server verifies that all fields are entered correctly and then saves the input data to the database. It inserts the data using SQL statements, and once saving is complete, it generates a save completion notification and sends it to the terminal.

[0464] Input: Validated input data

[0465] Data processing / calculations: Saving data to a database.

[0466] Output: Sends a save completion notification to the device.

[0467] Step 9:

[0468] The terminal receives a notification from the server confirming that the save is complete and notifies the user that "the proposal has been successfully submitted." For example, this may appear as a pop-up message in the web browser.

[0469] Input: Save complete notification

[0470] Output: Completion notification to the user

[0471] (Application Example 1)

[0472] 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."

[0473] Conventional proposal approval systems faced challenges such as the significant time and effort required for users to accurately input the necessary information. Furthermore, frequent input errors and missing fields, along with the time-consuming corrections, often hindered the overall business process. Additionally, using voice input presented difficulties in accurately converting speech to text and generating appropriate prompts.

[0474] 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.

[0475] In this invention, the server includes means for receiving a proposal request from a user, means for generating a list of necessary input items based on the proposal request, means for sending prompts to the user to sequentially input based on the input item list, means for receiving the user's response to each input item, means for verifying whether all received input items have been entered correctly, means for saving the input items to a database if they have been entered correctly, means for sending a notification to the user that the saving is complete, means for analyzing voice input, and means for generating prompt sentences using a generation AI model. As a result, users can efficiently draft proposals for approval using voice input or text input, reducing input errors and missing items, and improving the overall efficiency of the business process.

[0476] A "user" refers to the person who enters a proposal approval request and then provides answers to the subsequent input fields.

[0477] A "proposal request" refers to the initial request a user enters to initiate the proposal approval process.

[0478] The "input item list" refers to a list that enumerates the data items necessary for drafting a proposal for approval.

[0479] A "prompt" refers to a series of input instructions displayed to the user based on a list of input fields.

[0480] "Answer" refers to the content that the user enters in response to a prompt.

[0481] A "database" refers to an information management system used to store accurate data received from users.

[0482] A "save completion notification" refers to a message that informs the user that the data has been accurately saved to the database.

[0483] "Voice input" refers to the sound a user makes through a microphone, and includes the process of recognizing, analyzing, and converting that sound into text.

[0484] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate appropriate prompt sentences in response to user requests.

[0485] In order to implement the present invention, a system is needed in which a server, terminal, and user cooperate to smoothly advance the proposal approval process.

[0486] First, to initiate the proposal approval process, the user sends a request to the terminal via voice input or text input. The voice input used here utilizes the speech_recognition library to convert the user's voice into text data. This voice data is collected and analyzed by the terminal's built-in microphone and speech recognition software.

[0487] Next, the terminal analyzes the received request and sends the data to the server. The server generates an input field list and sends it to the terminal. This input field list includes essential data such as customer information, proposal details, estimated price, and approval deadline.

[0488] The server then uses a generative AI model to generate prompt messages corresponding to each input item. This generative AI model employs algorithms based on natural language processing to construct prompt messages in a way that is easy for the user to understand. The generated prompt messages are sent to the terminal, which then displays them to the user.

[0489] The terminal displays prompts to the user sequentially, and the user enters the necessary data into each input field based on those prompts. For example, if the prompt is "Please enter customer information," the user would enter "ABC Corporation." Similarly, if the prompt is "Please enter proposal details," the user would enter "Implementation of a new system."

[0490] Once all inputs are complete, the terminal sends this data to the server. The server validates the received data to ensure that all input fields are filled in correctly. If there are any errors, it generates an error message and sends a prompt to the terminal requesting re-entry. If there are no errors, it saves the data to the database and sends a notification to the user that the data has been saved.

[0491] As a concrete example, the following prompt message may be displayed:

[0492] 1. "Please enter customer information."

[0493] 2. "Please enter your proposal."

[0494] 3. "Please enter the estimated price."

[0495] 4. "Please enter the approval deadline."

[0496] For example, if a user voice-inputs "I would like to submit a proposal for approval," the terminal will display "Please enter customer information," and the user will input "ABC Corporation." Similarly, when prompted to "Please enter proposal details," the user will input "Introduction of a new system," and the necessary information will be seamlessly collected on the server.

[0497] In this way, prompt generation using voice input analysis and generative AI models reduces the user's workload and enables the efficient and accurate drafting of proposals for approval.

[0498] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0499] Step 1:

[0500] The user inputs a request to initiate a proposal for approval. Specifically, in the case of voice input, the request is sent via the microphone using the speech_recognition library. This voice data is converted to text on the device. The input is the user's voice request, "I want to initiate a proposal for approval." The output is a text version of the request, "I want to initiate a proposal for approval."

[0501] Step 2:

[0502] The terminal analyzes the received request. The analyzed data is sent to the server as an HTTP request. The input is a text-based request: "I want to submit a proposal for approval." The output is a request that has been converted into a data format for transmission to the server.

[0503] Step 3:

[0504] The server analyzes the received request and generates a list of input fields for proposal approval. This list includes customer information, proposal details, estimated price, approval deadline, etc. The input is the submitted request data. The output is the generated list of input fields.

[0505] Step 4:

[0506] The server uses a generative AI model to generate prompt messages based on the input item list. The generated prompt messages are sent to the terminal. The input is the input item list. The output is the prompt messages generated by the generative AI model and sent to the terminal.

[0507] Step 5:

[0508] The terminal displays prompt messages to the user. For example, it might display the message, "Please enter customer information." The input is the prompt message received from the server. The output is the generation of the prompt message displayed to the user.

[0509] Step 6:

[0510] The user enters information into each input field according to the prompts. For example, they might enter "ABC Corporation". The input is the data entered by the user in response to the prompt displayed on the terminal. The output is the user's input data.

[0511] Step 7:

[0512] The terminal sends user input data to the server. The input is the data entered by the user. The output is data generated that is formatted for transmission to the server.

[0513] Step 8:

[0514] The server validates the received data and verifies that all required fields have been entered correctly. For example, it performs error checking to ensure there are no missing fields or input errors. The input is user input data, and the output is the validation results.

[0515] Step 9:

[0516] The server saves the data to the database if it is correct. It accepts verified data as input and generates saved verification information as output.

[0517] Step 10:

[0518] The server generates a message notifying the terminal that saving is complete and sends it. The input is confirmation that saving is complete. The output is a generated save completion notification message sent to the terminal.

[0519] Step 11:

[0520] The terminal displays a save completion notification to the user. The input is the save completion notification message received from the server. The output is the generation of the save completion notification message that will be displayed to the user.

[0521] Example of a prompt:

[0522] "Please enter customer information."

[0523] Please enter your proposal details.

[0524] "Please enter the estimated price."

[0525] "Please enter the approval deadline."

[0526] 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.

[0527] Regarding embodiments for carrying out the present invention, a proposal approval and drafting system in which an emotion engine is combined with the user, terminal, and server will be specifically described.

[0528] The user instructs the terminal via voice or text, "I want to draft a proposal for company XX," in order to initiate a proposal approval process. The terminal receives this request, analyzes the request, and sends it to the server. The server confirms the request and generates a list of necessary input fields. This list of input fields includes customer information, proposal details, estimated price, and approval deadline.

[0529] Next, the server generates prompts for each input field based on the generated input field list, instructing the user to enter the information sequentially, and sends these prompts to the terminal. The terminal displays these prompts to the user, who then enters the specific information. For example, it might display "Please enter customer information," and the user would enter "ABC Corporation." Similarly, prompts are displayed sequentially for each input field, and the user enters the information accordingly.

[0530] The terminal collects the data entered by the user, and once all required fields are filled in, it sends the data to the server. The server verifies the received data to confirm that all fields have been entered correctly. If there are any missing entries or errors, it generates an error message and requests re-entry.

[0531] If all fields are entered correctly, the server saves the data to the database. Once saving is complete, the server sends a save completion message to the terminal, and the terminal notifies the user that "the proposal has been successfully submitted."

[0532] Furthermore, this system incorporates an emotion engine. The emotion engine analyzes the user's facial expressions, voice tone, and input speed to recognize the user's emotions. For example, if the user's voice suddenly becomes louder or their input slows down, the emotion engine will determine that the user is experiencing stress or confusion. In such cases, the server supports the user by generating prompts that provide supplementary explanations and guidance and sending them to the terminal.

[0533] For example, if the emotion engine detects that a user is slow to enter customer information, the server will send detailed guidance such as, "Please enter the company name and contact information for customer information." This allows users to submit proposals smoothly without feeling stressed.

[0534] In this way, this system, which incorporates an emotion engine, can respond flexibly to the user's emotional state, making the proposal approval process more efficient and accurate.

[0535] The following describes the processing flow.

[0536] Step 1:

[0537] The user instructs the terminal via voice or text, "I want to draft a proposal for company XX to approve." The terminal receives this request.

[0538] Step 2:

[0539] The terminal analyzes the user's request, confirms that it is a proposal approval request, and then sends the request details to the server.

[0540] Step 3:

[0541] The server analyzes the received proposal request and generates a list of input fields necessary for proposal approval. This list includes customer information, proposal details, estimated price, and approval deadline.

[0542] Step 4:

[0543] Based on the generated list of input items, the server generates prompts for each item to sequentially instruct the user to enter the information, and sends these prompts to the terminal.

[0544] Step 5:

[0545] The terminal displays the received prompt to the user. For example, a prompt such as "Please enter customer information" might be displayed.

[0546] Step 6:

[0547] The user enters the required information according to the displayed prompts. For example, they might enter "ABC Corporation".

[0548] Step 7:

[0549] The terminal collects input from the user and prompts for the next input field. This process is repeated for all required fields.

[0550] Step 8:

[0551] Once the terminal confirms that all fields have been entered, it sends the collected data to the server in a single batch.

[0552] Step 9:

[0553] The server checks the received user input data and verifies that all items have been entered completely and accurately.

[0554] Step 10:

[0555] If there are any missing or incorrect entries, the server generates an error message and sends it to the terminal along with a prompt for re-entry. The terminal then displays this again to the user.

[0556] Step 11:

[0557] If all fields are entered correctly, the server will save the data to the database.

[0558] Step 12:

[0559] Once saving to the database is complete, the server generates a save completion message and sends it to the terminal.

[0560] Step 13:

[0561] The terminal displays a message to the user indicating that the saved document has been successfully saved. For example, it might notify the user that "The proposal has been successfully drafted."

[0562] Step 14:

[0563] The device activates an emotion engine when the user inputs data, analyzing the user's facial expressions, voice tone, and input speed in real time. This analysis is then sent to a server.

[0564] Step 15:

[0565] The server receives analysis results sent from the emotion engine and determines the user's emotional state. If stress or confusion is detected, the server generates a corresponding guidance prompt and sends it to the terminal.

[0566] Step 16:

[0567] Based on the analysis results of the emotion engine, the device will display prompts that provide supplementary explanations and guidance if the user is experiencing stress or confusion. For example, it might display, "You seem to be having trouble entering information, please enter the company name and contact information."

[0568] This series of steps allows users to accurately draft proposals for approval without experiencing stress. By combining this with an emotion engine, a system is created that can respond flexibly according to the user's emotional state.

[0569] (Example 2)

[0570] 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".

[0571] Conventional proposal approval systems often caused stress and frustration for users when performing cumbersome data entry tasks. Furthermore, the need to repeatedly re-enter data to correct errors and omissions reduced efficiency. Additionally, the lack of appropriate support tailored to users' emotional states exacerbated the burden of data entry.

[0572] 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.

[0573] In this invention, the server includes an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize emotions, means for generating prompts that provide supplementary explanations and guidance based on the user's emotional state, means for receiving a proposal request from the user, means for generating a list of necessary input items based on the proposal request, means for sending prompts to the user to sequentially input based on the input item list, means for receiving the user's response to each input item, means for confirming that all received input items have been entered correctly, means for saving the input items to a database if they have been entered correctly, and means for sending a notification to the user that the saving is complete. This makes it possible to respond flexibly according to the user's emotional state and to carry out the proposal approval process more efficiently and accurately.

[0574] A "proposal request" is an instruction or request that a user sends to the system to initiate the proposal approval process.

[0575] An "input item list" is a list that enumerates the items of information that the system requests from the user.

[0576] A "prompt" is a message or screen display that a system uses to instruct a user to enter information.

[0577] "Answer" refers to the information that the user enters in response to system prompts.

[0578] A "database" is a structured collection of data used by a system to store and manage information.

[0579] A "save completion notification" is a message sent to the user informing them that the system has successfully finished saving information to the database.

[0580] The "emotion engine" is a system module that analyzes the user's facial expressions, voice tone, and input speed to recognize their emotions.

[0581] "Supplementary explanations and guidance" refer to additional instructions or explanations provided when a user experiences confusion or stress during input.

[0582] An "error message" is a message that the system sends to the user prompting them to re-enter data when there are errors or deficiencies in the input data.

[0583] Regarding embodiments for carrying out the present invention, a proposal approval and drafting system in which an emotion engine is combined with the user, terminal, and server will be specifically described.

[0584] The user instructs the terminal via voice or text, saying, "I want to draft a proposal for approval from company XX," with the intention of drafting a proposal for approval. The terminal, upon receiving this request, analyzes the request and sends it to the server. For example, the Google Speech-to-Text API is used for speech recognition, and a general natural language processing library is used for text analysis.

[0585] The server confirms the request and generates a list of required input fields. This list includes customer information, proposal details, estimated price, and approval deadline. Based on the input field list, the server generates prompts for each field, instructing the user to enter the information sequentially, and sends these prompts to the terminal. Generative AI models such as OpenAI GPT-4 are used to generate the prompts.

[0586] The terminal displays prompts to the user, who then enters specific information. For example, it might display "Please enter customer information," and the user would enter "ABC Corporation." Similarly, prompts are displayed sequentially for each input field, and the user enters the information accordingly. The data entered by the user is collected by the terminal, and once all required fields have been completed, the data is sent to the server.

[0587] The server validates the received data to ensure all fields are entered correctly. If there are any missing entries or errors, it generates an error message prompting the user to re-enter the information. The error message includes concise instructions for the user to re-enter the incorrect fields. For example, a message such as "The estimated amount is not entered; please enter it again."

[0588] If all fields are entered correctly, the server saves the data to the database. Once saving is complete, the server sends a save completion message to the terminal, which then notifies the user. For example, it might notify the user that "the proposal has been successfully drafted."

[0589] This system incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize their emotions. The emotion engine utilizes tools such as IBM Watson Tone Analyzer and Microsoft Azure Emotion API. For example, if a user's voice suddenly becomes louder or their input slows down, the emotion engine might determine that the user is experiencing stress or confusion. In such cases, the server generates and sends prompts providing supplementary explanations and guidance to the terminal.

[0590] For example, if the emotion engine detects that a user is slow to enter customer information in response to the prompt "Please enter customer information," the server will send detailed guidance such as "Please enter company name and contact information." This allows users to submit proposals smoothly without feeling stressed.

[0591] In this way, this system, which incorporates an emotion engine, can respond flexibly to the user's emotional state, making the proposal approval process more efficient and accurate.

[0592] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0593] Step 1:

[0594] To initiate a proposal approval process, the user instructs the terminal via voice or text, saying, "I would like to initiate a proposal approval process for Company XX." Based on this input, the terminal uses speech recognition software (e.g., Google Speech-to-Text API) or text analysis software to analyze the request. The analyzed data becomes the request statement, "I would like to initiate a proposal approval process for Company XX."

[0595] Step 2:

[0596] The terminal sends the parsed request statement to the server. This request statement is the input necessary to convey the user's intent to the server. The server parses the received request statement and determines the list of input items to be generated. As output, the server generates an input item list that includes customer information, proposal details, estimated amount, and approval deadline.

[0597] Step 3:

[0598] The server generates prompts that sequentially instruct the user to enter information based on a list of input fields. Generative AI models such as OpenAI GPT-4 are used for this prompt generation. An example prompt generated is "Please enter customer information." This prompt is sent to the terminal and displayed to the user.

[0599] Step 4:

[0600] The terminal displays prompts to the user, who then enters specific information for each input field. For example, the user might enter "ABC Corporation". This input data is received by the terminal. The data entered by the user is temporarily stored on the terminal.

[0601] Step 5:

[0602] The terminal sends all collected input data to the server. This data includes customer information, proposal details, estimated price, and approval deadline. The server analyzes the received data and verifies that each item has been entered correctly. As output, the server obtains the verification results.

[0603] Step 6:

[0604] The server performs error checking based on the validation results of the input data. If there are errors or missing entries, the server generates an error message and sends a command to the terminal requesting re-entry. The user corrects the data by re-entering it.

[0605] Step 7:

[0606] If all fields are confirmed to be entered correctly, the server saves the data to the database. Databases such as MySQL and PostgreSQL can be used. Once saving to the database is complete, the server generates a completion notification and sends it to the terminal. The terminal then notifies the user that "the proposal has been successfully submitted."

[0607] Step 8:

[0608] The server incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize emotions. Examples of emotion engines used include IBM Watson Tone Analyzer and Microsoft Azure Emotion API. If the emotion engine detects user stress or confusion, the server generates and sends prompts providing supplementary explanations and guidance to the terminal. For example, if a user is slow to input information in response to "Please enter customer information," the server sends detailed guidance such as "Please enter company name and contact information for customer information." This allows users to smoothly draft proposals for approval without feeling stressed.

[0609] (Application Example 2)

[0610] 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."

[0611] The work in logistics centers is complex and requires many steps to be performed instantly, placing a heavy burden on employees. Furthermore, the stress and confusion employees experience during work significantly reduce work efficiency. Additionally, errors or mistakes in data entry necessitate re-entry, resulting in additional time and effort.

[0612] 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. In this invention, the server includes means for receiving a proposal request from a user, means for generating a list of necessary input items based on the proposal request, means for sending prompts to the user to sequentially input based on the input item list, means for receiving responses from the user to each input item, means for confirming whether all received input items have been entered correctly, means for saving the input items to a database if they have been entered correctly, means for sending a notification to the user that the saving is complete, means including an emotion engine for analyzing emotional states, and means for providing supplementary explanations and guidance based on the emotion analysis results. This reduces the stress and confusion that employees feel while working in a logistics center, enabling efficient and accurate work execution.

[0613] A "user" is an entity that uses a system to input information and perform tasks.

[0614] A "proposal request" is a request from a user to initiate a task or perform a specific process within the system.

[0615] An "input item list" is a list of necessary information that the user must enter into the system.

[0616] A "prompt" is a message from the system that instructs the user to input information sequentially.

[0617] "Answer" refers to the information that a user provides to the system based on the input fields.

[0618] A "database" is a system for storing and managing collected data.

[0619] An "emotion engine" is a device or program that analyzes a user's emotional state and evaluates stress and confusion.

[0620] "Supplementary explanations and guidance" refer to additional explanations or instructions provided to users when using the system.

[0621] Modes for carrying out the invention

[0622] This invention is a proposal approval system for logistics centers that utilizes an emotion engine. The main components used to carry out this invention are described below.

[0623] System Overview

[0624] This system allows users to make requests via voice or text input, which the server then analyzes to generate the necessary input fields and presents prompts to the user based on those fields. Furthermore, it uses an emotion engine to analyze the user's emotional state and provides supplementary explanations and guidance as needed.

[0625] hardware

[0626] 1. Smartphone:

[0627] It is used by users for voice input and text input.

[0628] It is responsible for displaying prompts to the user and sending input data to the server.

[0629] 2. Server:

[0630] Receive and analyze requests from users.

[0631] Generate a list of required input fields and prepare prompts.

[0632] The system uses an emotion engine to analyze emotional states and generate appropriate guidance.

[0633] The received data is saved to the database.

[0634] software

[0635] 1. Flask:

[0636] It is used as a server-side web application framework.

[0637] 2. EmotionEngine:

[0638] A proprietary module for analyzing the emotional state of users.

[0639] It performs sentiment analysis based on voice and text input.

[0640] 3. Speech Recognition:

[0641] A library that converts voice input to text.

[0642] Processing flow

[0643] 1. User voice input:

[0644] The user uses their smartphone to input voice commands such as, "I want to ship the product."

[0645] 2. Converting speech to text:

[0646] The smartphone converts voice input into text and sends it to the server.

[0647] 3. Generating the input item list:

[0648] The server analyzes the text input via voice and generates a list of necessary input fields (such as product name, quantity, shipping address, and shipping deadline).

[0649] 4. Prompt presentation:

[0650] Based on the generated list of input fields, the server generates prompts that sequentially present the user with input fields and sends them to the smartphone.

[0651] Example: "Please enter the following information: Product name details" "Please enter the shipping address"

[0652] 5. Analysis of emotional state:

[0653] An emotion engine within the server analyzes the user's voice and input speed to determine if the user is experiencing stress or confusion.

[0654] 6. Supplementary explanations and guidance:

[0655] If the emotion engine detects a user's stress level, the server generates supplementary explanations and guidance and sends them to the smartphone.

[0656] Example: "Additional guidance: Please enter the product name, quantity, and shipping address."

[0657] 7. Saving input data:

[0658] If all user input fields are entered correctly, the server saves this information to the database.

[0659] 8. Completion notification:

[0660] Once data saving is complete, the server sends a saving completion notification to the user, which is then displayed to the user.

[0661] Specific example

[0662] When a user requests, "What should I do next?", the server provides detailed guidance such as, "Please enter the product name, quantity, and shipping address." This prompt might appear in a real-world scenario as follows:

[0663] "I want to ship the product. What should I do next?"

[0664] "I'm having trouble entering customer information. Please help me."

[0665] In this way, systems using emotion engines and prompts enable users to work efficiently in logistics centers without experiencing stress.

[0666] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0667] Step 1:

[0668] User voice input

[0669] The user uses their smartphone to make a voice input, such as "I want to ship the product." This voice data is then sent to the smartphone as input.

[0670] Step 2:

[0671] Speech-to-text conversion

[0672] The device (smartphone) uses the SpeechRecognition library to convert voice input into text data. Specifically, it inputs voice data into the speech recognition engine and outputs the resulting text data.

[0673] Step 3:

[0674] Send a request

[0675] The terminal sends the converted text data to the server. The text, as input data, is sent to the server in the form of an HTTP request. The server's endpoint receives this and prepares the data for analysis.

[0676] Step 4:

[0677] Generating an input item list

[0678] The server parses the received text data and generates a list of necessary input fields. For example, in response to a request such as "I want to ship the product," the server creates a list of input fields including product name, quantity, shipping address, and shipping deadline, and generates this as output data.

[0679] Step 5:

[0680] Prompt presentation

[0681] The server generates prompts that instruct the user to enter information sequentially based on the generated list of input fields. These prompts include text such as "Please enter the product name" or "Please enter the shipping address." These prompts are sent to the terminal and displayed to the user.

[0682] Step 6:

[0683] Receiving user input

[0684] The terminal receives text data entered by the user based on prompts and sends it to the server. The input data includes specific answers to each item provided by the user.

[0685] Step 7:

[0686] Analysis of emotional states

[0687] The server uses an emotion engine to analyze the user's input data, voice tone, and input speed. Based on the emotion engine's analysis, it determines whether the user is experiencing stress or confusion and outputs the result.

[0688] Step 8:

[0689] Providing supplementary explanations and guidance

[0690] Based on the analysis results of the emotion engine, the server generates prompts that provide supplementary explanations and guidance as needed. For example, if user stress is detected, it generates additional guidance such as "Please enter the product name, quantity, and shipping address" and sends it to the terminal.

[0691] Step 9:

[0692] Input data verification

[0693] The server verifies that all received user input data is entered correctly. If there are errors or missing data, it generates an error message and sends a prompt to the terminal requesting re-entry.

[0694] Step 10:

[0695] Data saving and completion notification

[0696] After all input data has been entered correctly and verified by the server, the data is saved to the database. Once saving is complete, the server generates a completion notification and sends it to the terminal. The user receives a completion notification on their terminal, such as "Proposal approval has been successfully submitted."

[0697] 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.

[0698] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0699] 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.

[0700] [Third Embodiment]

[0701] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0702] 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.

[0703] 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).

[0704] 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.

[0705] 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.

[0706] 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).

[0707] 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.

[0708] 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.

[0709] 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.

[0710] 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.

[0711] 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.

[0712] 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".

[0713] In order to implement the present invention, it is necessary to provide a system in which the user, terminal, and server cooperate to accurately execute the proposal approval process. A specific embodiment of this system is described below.

[0714] First, the user initiates the proposal approval process by giving instructions to the terminal via voice or text. For example, they might enter a request such as, "I want to draft a proposal for company XX to approve."

[0715] Next, the terminal that receives this request parses the request content and sends it to the server. The server confirms the request and generates a list of necessary input fields. This includes customer information, proposal details, estimated price, and approval deadline.

[0716] Based on this list of input items, the server generates prompts that instruct the user to enter the information sequentially and sends them to the terminal.

[0717] The terminal displays the received prompt to the user. For example, it might display "Please enter customer information." The user then enters "ABC Corporation." Similarly, prompts are displayed sequentially for all input fields sent from the server, and the user enters the information.

[0718] Once all input is complete, the terminal sends the user's input data to the server. The server verifies the received data to ensure that all required fields are entered correctly. If there are any missing entries or errors, the server generates an error message and sends a prompt to the terminal requesting re-entry.

[0719] If all fields are entered correctly, the server saves this data to the database. Once saving is complete, the server sends the result to the terminal, which notifies the user that "the proposal has been successfully submitted."

[0720] As a concrete example, a user might type "I want to draft a proposal for approval from company XX," and then be prompted to "Please enter customer information." The user would then type "ABC Corporation," and then be prompted to "Please enter the proposal details," to which the user would type "Implementation of a new system." This process is repeated for all required fields, and finally the data is sent to the server. The server checks the data, and if everything is entered correctly, it saves it to the database and notifies the terminal that saving is complete.

[0721] In this way, this system can help users draft accurate and complete proposals for approval, thereby improving work efficiency.

[0722] The following describes the processing flow.

[0723] Step 1:

[0724] The user instructs the terminal via voice or text, "I want to initiate a proposal for company XX to approve." This request is received by the terminal.

[0725] Step 2:

[0726] The terminal analyzes the user's request, confirms that it is a proposal approval request, and then sends the request details to the server.

[0727] Step 3:

[0728] The server analyzes the received proposal request and generates a list of necessary input fields. This list includes customer information, proposal details, estimated price, and approval deadline.

[0729] Step 4:

[0730] Based on the generated list of input items, the server sequentially generates prompts for each item, requesting input from the user, and sends them to the terminal.

[0731] Step 5:

[0732] The terminal displays the received prompt to the user. For example, it might display "Please enter customer information."

[0733] Step 6:

[0734] The user enters the required information according to the displayed prompts, and the terminal receives that input. For example, the user might enter "ABC Corporation".

[0735] Step 7:

[0736] The terminal collects input from the user and prompts for the next input field. This process is repeated for all required fields.

[0737] Step 8:

[0738] Once all required fields are entered, the device sends the collected data to the server in a single batch.

[0739] Step 9:

[0740] The server checks the received user input data and verifies that all fields have been entered completely. If there are any missing entries or errors, it generates an error message and sends a prompt to the terminal requesting re-entry.

[0741] Step 10:

[0742] If all fields are entered correctly, the server will save the data to the database.

[0743] Step 11:

[0744] Once saving to the database is complete, the server generates a save completion message and sends it to the terminal.

[0745] Step 12:

[0746] The terminal displays a message to the user indicating that the saved document has been successfully saved, and notifies them that "the proposal has been successfully submitted for approval."

[0747] (Example 1)

[0748] 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."

[0749] The current proposal approval system can be difficult for users to input all the necessary information completely and accurately, resulting in frequent errors and omissions. This leads to decreased work efficiency and increased re-entry time. Furthermore, manual data entry is time-consuming and prone to human error. Therefore, there is a need for a system that allows users to quickly and accurately submit proposals for approval.

[0750] 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.

[0751] In this invention, the server includes means for receiving a proposal request from a user, means for analyzing the proposal request, means for generating a list of necessary input items based on the proposal request, means for generating and sending prompts to the user to sequentially input based on the list of input items, means for receiving responses from the user for each input item, means for verifying whether all received input items have been entered correctly, means for generating an error message and requesting re-entry if there is an error in the input items, means for saving the input items to a database if they have been entered correctly, and means for sending a notification to the user that the saving is complete. This enables the user to quickly and accurately draft proposals for approval.

[0752] A "user" is a person who uses this system to initiate the proposal approval process and inputs the necessary information.

[0753] A "proposal request" is an instruction that a user enters via voice or text to initiate the proposal approval process.

[0754] A "terminal" is a device used by a user, specifically a device for entering requests and displaying prompts.

[0755] A "server" is a computer system that controls the entire system based on user input and requests, and processes and stores data.

[0756] "Natural language processing" is a technology that analyzes text and audio data and interprets the meaning and structure contained within them.

[0757] An "input item list" is a list that organizes the information necessary for proposal approval, and includes customer information, proposal details, estimated price, and approval deadline.

[0758] A "prompt" is a message or instruction that instructs the user to enter information based on a list of input fields.

[0759] An "error message" is a warning or instruction to re-enter information that is displayed when there is an error or deficiency in the user's input.

[0760] A "database" is an information aggregation system used to systematically manage and store data within a system.

[0761] A "save completion notification" is a confirmation message sent to the user after the server has successfully saved the data.

[0762] To implement the present invention, it is necessary to provide a system that enables users, terminals, and servers to work together to accurately execute the proposal approval process. This system aims to collect necessary data from user requests and quickly create error-free approval documents. A specific embodiment of this system is shown below.

[0763] First, the user gives instructions to the device via voice or text to begin drafting a proposal for approval. For example, the user inputs a request such as "I want to draft a proposal for approval for company XX" into a device such as a smartphone or computer. This device uses a natural language processing library (e.g., NLTK, spaCy) to analyze the content of the request. After analysis, the device sends the analysis results to the server.

[0764] Next, the server generates a list of input items necessary for proposal approval based on the received request. This list includes customer information, proposal details, estimated price, and approval deadline. Programming languages ​​such as Python or Java can be used for this, and database management systems (e.g., MySQL, PostgreSQL) can be utilized. The server then sends this input item list to the terminal in JSON format or another appropriate format.

[0765] The terminal displays prompts to the user sequentially based on a list of input fields received from the server. For example, a prompt saying "Please enter customer information" is displayed on a web browser. The user enters "ABC Corporation," then a prompt saying "Please enter proposal details" is displayed, and the user enters "Implementation of a new system." Specifically, these prompts are displayed as "Please enter customer information," "Please enter proposal details," "Please enter estimated price," and "Please enter approval deadline."

[0766] Once the user has completed all the inputs, the terminal sends the input data to the server. The server verifies the received data and checks that all required fields have been entered correctly. If there are any errors or missing entries in the data, the server generates an error message and sends it to the terminal along with a prompt to re-enter the information. For example, it might generate a message such as, "The estimated amount is not entered. Please re-enter it."

[0767] If all fields are entered correctly, the server saves the data to the database. After inserting the data using an SQL statement and saving is complete, the server notifies the terminal. The terminal then notifies the user that "the proposal has been successfully submitted," and this message is displayed as a pop-up in the web browser.

[0768] In this way, this system can help users accurately draft proposals for approval, thereby improving work efficiency. Furthermore, by utilizing a generative AI model, the system can further refine user input and achieve highly accurate data processing.

[0769] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0770] Step 1:

[0771] The user enters a request into their device via voice or text to begin drafting a proposal for approval. For example, they might type "I want to draft a proposal for company XX" into their smartphone or computer.

[0772] Input: User request via voice or text input.

[0773] Output: The terminal retrieves the request data.

[0774] Step 2:

[0775] The terminal receives a request from the user and parses the request using a natural language processing library (e.g., NLTK, spaCy). The parsing results include key information such as the name of the company subject to proposal approval and the content of the proposal. After parsing, the terminal sends these results to the server.

[0776] Input: User's request data

[0777] Data processing / calculations: Text analysis using natural language processing

[0778] Output: Send analysis results to the server

[0779] Step 3:

[0780] The server generates a list of input items necessary for proposal approval based on the received analysis results. This list includes customer information, proposal details, estimated price, and approval deadline. Programming languages ​​such as Python or Java are used to generate the list, and it is converted into a format compatible with the structure of the database management system (e.g., MySQL, PostgreSQL). The server sends this input item list to the terminal in JSON format or similar.

[0781] Input: Analysis results

[0782] Data processing / calculations: Generating a list of required input items.

[0783] Output: Send the list of input items to the terminal.

[0784] Step 4:

[0785] The terminal displays prompts to the user sequentially based on the list of input fields received from the server. For example, a prompt saying "Please enter customer information" is displayed on the web browser. The user enters "ABC Corporation," and then a prompt saying "Please enter your proposal" is displayed, to which the user enters "Implementation of a new system."

[0786] Input: Input item list

[0787] Output: Prompt displayed to the user

[0788] Step 5:

[0789] The user enters the required information sequentially according to the prompts displayed on the terminal.

[0790] Input: User input data in response to prompts (e.g., customer information, proposal details, estimated price, approval deadline)

[0791] Output: The terminal collects user input data.

[0792] Step 6:

[0793] The terminal collects all input data from the user and then sends that data to the server.

[0794] Input: User input data

[0795] Output: Input data sent to the server

[0796] Step 7:

[0797] The server validates the received input data. It checks if all required fields are entered correctly and generates an error message if any are missing or incorrect. Along with this error message, it sends a prompt to the terminal to re-enter the information. For example, it might generate a message such as, "The estimated amount is not entered. Please re-enter it."

[0798] Input: User input data

[0799] Data processing / calculations: Data validation and error message generation.

[0800] Output: Error messages and re-entry prompts sent to the terminal

[0801] Step 8:

[0802] The server verifies that all fields are entered correctly and then saves the input data to the database. It inserts the data using SQL statements, and once saving is complete, it generates a save completion notification and sends it to the terminal.

[0803] Input: Validated input data

[0804] Data processing / calculations: Saving data to a database.

[0805] Output: Sends a save completion notification to the device.

[0806] Step 9:

[0807] The terminal receives a notification from the server confirming that the save is complete and notifies the user that "the proposal has been successfully submitted." For example, this may appear as a pop-up message in the web browser.

[0808] Input: Save complete notification

[0809] Output: Completion notification to the user

[0810] (Application Example 1)

[0811] 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."

[0812] Conventional proposal approval systems faced challenges such as the significant time and effort required for users to accurately input the necessary information. Furthermore, frequent input errors and missing fields, along with the time-consuming corrections, often hindered the overall business process. Additionally, using voice input presented difficulties in accurately converting speech to text and generating appropriate prompts.

[0813] 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.

[0814] In this invention, the server includes means for receiving a proposal request from a user, means for generating a list of necessary input items based on the proposal request, means for sending prompts to the user to sequentially input based on the input item list, means for receiving the user's response to each input item, means for verifying whether all received input items have been entered correctly, means for saving the input items to a database if they have been entered correctly, means for sending a notification to the user that the saving is complete, means for analyzing voice input, and means for generating prompt sentences using a generation AI model. As a result, users can efficiently draft proposals for approval using voice input or text input, reducing input errors and missing items, and improving the overall efficiency of the business process.

[0815] A "user" refers to the person who enters a proposal approval request and then provides answers to the subsequent input fields.

[0816] A "proposal request" refers to the initial request a user enters to initiate the proposal approval process.

[0817] The "input item list" refers to a list that enumerates the data items necessary for drafting a proposal for approval.

[0818] A "prompt" refers to a series of input instructions displayed to the user based on a list of input fields.

[0819] "Answer" refers to the content that the user enters in response to a prompt.

[0820] A "database" refers to an information management system used to store accurate data received from users.

[0821] A "save completion notification" refers to a message that informs the user that the data has been accurately saved to the database.

[0822] "Voice input" refers to the sound a user makes through a microphone, and includes the process of recognizing, analyzing, and converting that sound into text.

[0823] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate appropriate prompt sentences in response to user requests.

[0824] In order to implement the present invention, a system is needed in which a server, terminal, and user cooperate to smoothly advance the proposal approval process.

[0825] First, to initiate the proposal approval process, the user sends a request to the terminal via voice input or text input. The voice input used here utilizes the speech_recognition library to convert the user's voice into text data. This voice data is collected and analyzed by the terminal's built-in microphone and speech recognition software.

[0826] Next, the terminal analyzes the received request and sends the data to the server. The server generates an input field list and sends it to the terminal. This input field list includes essential data such as customer information, proposal details, estimated price, and approval deadline.

[0827] The server then uses a generative AI model to generate prompt messages corresponding to each input item. This generative AI model employs algorithms based on natural language processing to construct prompt messages in a way that is easy for the user to understand. The generated prompt messages are sent to the terminal, which then displays them to the user.

[0828] The terminal displays prompts to the user sequentially, and the user enters the necessary data into each input field based on those prompts. For example, if the prompt is "Please enter customer information," the user would enter "ABC Corporation." Similarly, if the prompt is "Please enter proposal details," the user would enter "Implementation of a new system."

[0829] Once all inputs are complete, the terminal sends this data to the server. The server validates the received data to ensure that all input fields are filled in correctly. If there are any errors, it generates an error message and sends a prompt to the terminal requesting re-entry. If there are no errors, it saves the data to the database and sends a notification to the user that the data has been saved.

[0830] As a concrete example, the following prompt message may be displayed:

[0831] 1. "Please enter customer information."

[0832] 2. "Please enter your proposal."

[0833] 3. "Please enter the estimated price."

[0834] 4. "Please enter the approval deadline."

[0835] For example, if a user voice-inputs "I would like to submit a proposal for approval," the terminal will display "Please enter customer information," and the user will input "ABC Corporation." Similarly, when prompted to "Please enter proposal details," the user will input "Introduction of a new system," and the necessary information will be seamlessly collected on the server.

[0836] In this way, prompt generation using voice input analysis and generative AI models reduces the workload on users and enables the efficient and accurate drafting of proposals for approval.

[0837] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0838] Step 1:

[0839] The user inputs a request to initiate a proposal for approval. Specifically, in the case of voice input, the request is sent via the microphone using the speech_recognition library. This voice data is converted to text on the device. The input is the user's voice request, "I want to initiate a proposal for approval." The output is a text version of the request, "I want to initiate a proposal for approval."

[0840] Step 2:

[0841] The terminal analyzes the received request. The analyzed data is sent to the server as an HTTP request. The input is a text-based request: "I want to submit a proposal for approval." The output is a request that has been converted into a data format for transmission to the server.

[0842] Step 3:

[0843] The server analyzes the received request and generates a list of input fields for proposal approval. This list includes customer information, proposal details, estimated price, approval deadline, etc. The input is the submitted request data. The output is the generated list of input fields.

[0844] Step 4:

[0845] The server uses a generative AI model to generate prompt messages based on the input item list. The generated prompt messages are sent to the terminal. The input is the input item list. The output is the prompt messages generated by the generative AI model and sent to the terminal.

[0846] Step 5:

[0847] The terminal displays prompt messages to the user. For example, it might display the message, "Please enter customer information." The input is the prompt message received from the server. The output is the generation of the prompt message displayed to the user.

[0848] Step 6:

[0849] The user enters information into each input field according to the prompts. For example, they might enter "ABC Corporation". The input is the data entered by the user in response to the prompt displayed on the terminal. The output is the user's input data.

[0850] Step 7:

[0851] The terminal sends user input data to the server. The input is the data entered by the user. The output is data generated that is formatted for transmission to the server.

[0852] Step 8:

[0853] The server validates the received data and verifies that all required fields have been entered correctly. For example, it performs error checking to ensure there are no missing fields or input errors. The input is user input data, and the output is the validation results.

[0854] Step 9:

[0855] The server saves the data to the database if it is correct. It accepts verified data as input and generates saved verification information as output.

[0856] Step 10:

[0857] The server generates a message notifying the terminal that saving is complete and sends it. The input is confirmation that saving is complete. The output is a generated save completion notification message sent to the terminal.

[0858] Step 11:

[0859] The terminal displays a save completion notification to the user. The input is the save completion notification message received from the server. The output is the generation of the save completion notification message that will be displayed to the user.

[0860] Example of a prompt:

[0861] "Please enter customer information."

[0862] Please enter your proposal details.

[0863] "Please enter the estimated price."

[0864] "Please enter the approval deadline."

[0865] 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.

[0866] This document specifically describes an embodiment of the present invention: a proposal approval system in which an emotion engine is combined with the user, terminal, and server.

[0867] The user instructs the terminal via voice or text, "I want to draft a proposal for company XX," in order to initiate a proposal approval process. The terminal receives this request, analyzes the request, and sends it to the server. The server confirms the request and generates a list of necessary input fields. This list of input fields includes customer information, proposal details, estimated price, and approval deadline.

[0868] Next, the server generates prompts for each input field based on the generated input field list, instructing the user to enter the information sequentially, and sends these prompts to the terminal. The terminal displays these prompts to the user, who then enters the specific information. For example, it might display "Please enter customer information," and the user would enter "ABC Corporation." Similarly, prompts are displayed sequentially for each input field, and the user enters the information accordingly.

[0869] The terminal collects the data entered by the user, and once all required fields are filled in, it sends the data to the server. The server verifies the received data to confirm that all fields have been entered correctly. If there are any missing entries or errors, it generates an error message and requests re-entry.

[0870] If all fields are entered correctly, the server saves the data to the database. Once saving is complete, the server sends a save completion message to the terminal, and the terminal notifies the user that "the proposal has been successfully submitted."

[0871] Furthermore, this system incorporates an emotion engine. The emotion engine analyzes the user's facial expressions, voice tone, and input speed to recognize the user's emotions. For example, if the user's voice suddenly becomes louder or their input slows down, the emotion engine will determine that the user is experiencing stress or confusion. In such cases, the server supports the user by generating prompts that provide supplementary explanations and guidance and sending them to the terminal.

[0872] For example, if the emotion engine detects that a user is slow to enter customer information, the server will send detailed guidance such as, "Please enter the company name and contact information for customer information." This allows users to submit proposals smoothly without feeling stressed.

[0873] In this way, this system, which incorporates an emotion engine, can respond flexibly to the user's emotional state, making the proposal approval process more efficient and accurate.

[0874] The following describes the processing flow.

[0875] Step 1:

[0876] The user instructs the terminal via voice or text, "I want to draft a proposal for company XX to approve." The terminal receives this request.

[0877] Step 2:

[0878] The terminal analyzes the user's request, confirms that it is a proposal approval request, and then sends the request details to the server.

[0879] Step 3:

[0880] The server analyzes the received proposal request and generates a list of input fields necessary for proposal approval. This list includes customer information, proposal details, estimated price, and approval deadline.

[0881] Step 4:

[0882] Based on the generated list of input items, the server generates prompts for each item to sequentially instruct the user to enter the information, and sends these prompts to the terminal.

[0883] Step 5:

[0884] The terminal displays the received prompt to the user. For example, a prompt such as "Please enter customer information" might be displayed.

[0885] Step 6:

[0886] The user enters the required information according to the displayed prompts. For example, they might enter "ABC Corporation".

[0887] Step 7:

[0888] The terminal collects input from the user and prompts for the next input field. This process is repeated for all required fields.

[0889] Step 8:

[0890] Once the terminal confirms that all fields have been entered, it sends the collected data to the server in a single batch.

[0891] Step 9:

[0892] The server checks the received user input data and verifies that all items have been entered completely and accurately.

[0893] Step 10:

[0894] If there are any missing or incorrect entries, the server generates an error message and sends it to the terminal along with a prompt for re-entry. The terminal then displays this message to the user again.

[0895] Step 11:

[0896] If all fields are entered correctly, the server will save the data to the database.

[0897] Step 12:

[0898] Once saving to the database is complete, the server generates a save completion message and sends it to the terminal.

[0899] Step 13:

[0900] The terminal displays a message to the user indicating that the saved document has been successfully saved. For example, it might notify the user that "The proposal has been successfully drafted."

[0901] Step 14:

[0902] The device activates an emotion engine when the user inputs data, analyzing the user's facial expressions, voice tone, and input speed in real time. This analysis is then sent to a server.

[0903] Step 15:

[0904] The server receives analysis results sent from the emotion engine and determines the user's emotional state. If stress or confusion is detected, the server generates a corresponding guidance prompt and sends it to the terminal.

[0905] Step 16:

[0906] Based on the analysis results of the emotion engine, the device will display prompts that provide supplementary explanations and guidance if the user is experiencing stress or confusion. For example, it might display, "You seem to be having trouble entering information, please enter the company name and contact information."

[0907] This series of steps allows users to accurately draft proposals for approval without experiencing stress. By combining this with an emotion engine, a system is created that can respond flexibly according to the user's emotional state.

[0908] (Example 2)

[0909] 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."

[0910] Conventional proposal approval systems often caused stress and frustration for users when performing cumbersome data entry tasks. Furthermore, the need to repeatedly re-enter data to correct errors and omissions reduced efficiency. Additionally, the lack of appropriate support tailored to users' emotional states exacerbated the burden of data entry.

[0911] 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.

[0912] In this invention, the server includes an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize emotions, means for generating prompts that provide supplementary explanations and guidance based on the user's emotional state, means for receiving a proposal request from the user, means for generating a list of necessary input items based on the proposal request, means for sending prompts to the user to sequentially input based on the input item list, means for receiving the user's response to each input item, means for confirming that all received input items have been entered correctly, means for saving the input items to a database if they have been entered correctly, and means for sending a notification to the user that the saving is complete. This makes it possible to respond flexibly according to the user's emotional state and to carry out the proposal approval process more efficiently and accurately.

[0913] A "proposal request" is an instruction or request that a user sends to the system to initiate the proposal approval process.

[0914] An "input item list" is a list that enumerates the items of information that the system requests from the user.

[0915] A "prompt" is a message or screen display that a system uses to instruct a user to enter information.

[0916] "Answer" refers to the information that the user enters in response to system prompts.

[0917] A "database" is a structured collection of data used by a system to store and manage information.

[0918] A "save completion notification" is a message sent to the user informing them that the system has successfully finished saving information to the database.

[0919] The "emotion engine" is a system module that analyzes the user's facial expressions, voice tone, and input speed to recognize their emotions.

[0920] "Supplementary explanations and guidance" refer to additional instructions or explanations provided when a user experiences confusion or stress during input.

[0921] An "error message" is a message that the system sends to the user prompting them to re-enter data when there are errors or deficiencies in the input data.

[0922] This document specifically describes an embodiment of the present invention: a proposal approval system in which an emotion engine is combined with the user, terminal, and server.

[0923] The user instructs the terminal via voice or text, saying, "I want to draft a proposal for approval from company XX," with the intention of drafting a proposal for approval. The terminal, upon receiving this request, analyzes the request and sends it to the server. For example, the Google Speech-to-Text API is used for speech recognition, and a general natural language processing library is used for text analysis.

[0924] The server confirms the request and generates a list of required input fields. This list includes customer information, proposal details, estimated price, and approval deadline. Based on the input field list, the server generates prompts for each field, instructing the user to enter the information sequentially, and sends these prompts to the terminal. Generative AI models such as OpenAI GPT-4 are used to generate the prompts.

[0925] The terminal displays prompts to the user, who then enters specific information. For example, it might display "Please enter customer information," and the user would enter "ABC Corporation." Similarly, prompts are displayed sequentially for each input field, and the user enters the information accordingly. The data entered by the user is collected by the terminal, and once all required fields have been completed, the data is sent to the server.

[0926] The server validates the received data to ensure all fields are entered correctly. If there are any missing entries or errors, it generates an error message prompting the user to re-enter the information. The error message includes concise instructions for the user to re-enter the incorrect fields. For example, a message such as "The estimated amount is not entered; please enter it again."

[0927] If all fields are entered correctly, the server saves the data to the database. Once saving is complete, the server sends a save completion message to the terminal, which then notifies the user. For example, it might notify the user that "the proposal has been successfully drafted."

[0928] This system incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize their emotions. The emotion engine utilizes tools such as IBM Watson Tone Analyzer and Microsoft Azure Emotion API. For example, if a user's voice suddenly becomes louder or their input slows down, the emotion engine might determine that the user is experiencing stress or confusion. In such cases, the server generates and sends prompts providing supplementary explanations and guidance to the terminal.

[0929] For example, if the emotion engine detects that a user is slow to enter customer information in response to the prompt "Please enter customer information," the server will send detailed guidance such as "Please enter company name and contact information." This allows users to submit proposals smoothly without feeling stressed.

[0930] In this way, this system, which incorporates an emotion engine, can respond flexibly to the user's emotional state, making the proposal approval process more efficient and accurate.

[0931] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0932] Step 1:

[0933] To initiate a proposal approval process, the user instructs the terminal via voice or text, saying, "I would like to initiate a proposal approval process for Company XX." Based on this input, the terminal uses speech recognition software (e.g., Google Speech-to-Text API) or text analysis software to analyze the request. The analyzed data becomes the request statement, "I would like to initiate a proposal approval process for Company XX."

[0934] Step 2:

[0935] The terminal sends the parsed request statement to the server. This request statement is the input necessary to convey the user's intent to the server. The server parses the received request statement and determines the list of input items to be generated. As output, the server generates an input item list that includes customer information, proposal details, estimated amount, and approval deadline.

[0936] Step 3:

[0937] The server generates prompts that sequentially instruct the user to enter information based on a list of input fields. Generative AI models such as OpenAI GPT-4 are used for this prompt generation. An example prompt generated is "Please enter customer information." This prompt is sent to the terminal and displayed to the user.

[0938] Step 4:

[0939] The terminal displays prompts to the user, who then enters specific information for each input field. For example, the user might enter "ABC Corporation". This input data is received by the terminal. The data entered by the user is temporarily stored on the terminal.

[0940] Step 5:

[0941] The terminal sends all collected input data to the server. This data includes customer information, proposal details, estimated price, and approval deadline. The server analyzes the received data and verifies that each item has been entered correctly. As output, the server obtains the verification results.

[0942] Step 6:

[0943] The server performs error checking based on the validation results of the input data. If there are errors or missing entries, the server generates an error message and sends a command to the terminal requesting re-entry. The user corrects the data by re-entering it.

[0944] Step 7:

[0945] If all fields are confirmed to be entered correctly, the server saves the data to the database. Databases such as MySQL and PostgreSQL can be used. Once saving to the database is complete, the server generates a completion notification and sends it to the terminal. The terminal then notifies the user that "the proposal has been successfully submitted."

[0946] Step 8:

[0947] The server incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize emotions. Examples of emotion engines used include IBM Watson Tone Analyzer and Microsoft Azure Emotion API. If the emotion engine detects user stress or confusion, the server generates and sends prompts providing supplementary explanations and guidance to the terminal. For example, if a user is slow to input information in response to "Please enter customer information," the server sends detailed guidance such as "Please enter company name and contact information for customer information." This allows users to smoothly draft proposals for approval without feeling stressed.

[0948] (Application Example 2)

[0949] 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."

[0950] The work in logistics centers is complex and requires many steps to be performed instantly, placing a heavy burden on employees. Furthermore, the stress and confusion employees experience during work significantly reduce work efficiency. Additionally, errors or mistakes in data entry necessitate re-entry, resulting in additional time and effort.

[0951] 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. In this invention, the server includes means for receiving a proposal request from a user, means for generating a list of necessary input items based on the proposal request, means for sending prompts to the user to sequentially input based on the input item list, means for receiving responses from the user to each input item, means for confirming whether all received input items have been entered correctly, means for saving the input items to a database if they have been entered correctly, means for sending a notification to the user that the saving is complete, means including an emotion engine for analyzing emotional states, and means for providing supplementary explanations and guidance based on the emotion analysis results. This reduces the stress and confusion that employees feel while working in a logistics center, enabling efficient and accurate work execution.

[0952] A "user" is an entity that uses a system to input information and perform tasks.

[0953] A "proposal request" is a request from a user to initiate a task or perform a specific process within the system.

[0954] An "input item list" is a list of necessary information that the user must enter into the system.

[0955] A "prompt" is a message from the system that instructs the user to input information sequentially.

[0956] "Answer" refers to the information that a user provides to the system based on the input fields.

[0957] A "database" is a system for storing and managing collected data.

[0958] An "emotion engine" is a device or program that analyzes a user's emotional state and evaluates stress and confusion.

[0959] "Supplementary explanations and guidance" refer to additional explanations or instructions provided to users when using the system.

[0960] Modes for carrying out the invention

[0961] This invention is a proposal approval system for logistics centers that utilizes an emotion engine. The main components used to carry out this invention are described below.

[0962] System Overview

[0963] This system allows users to make requests via voice or text input, which the server then analyzes to generate the necessary input fields and presents prompts to the user based on those fields. Furthermore, it uses an emotion engine to analyze the user's emotional state and provides supplementary explanations and guidance as needed.

[0964] hardware

[0965] 1. Smartphone:

[0966] It is used by users for voice input and text input.

[0967] It is responsible for displaying prompts to the user and sending input data to the server.

[0968] 2. Server:

[0969] Receive and analyze requests from users.

[0970] Generate a list of required input fields and prepare prompts.

[0971] The system uses an emotion engine to analyze emotional states and generate appropriate guidance.

[0972] The received data is saved to the database.

[0973] software

[0974] 1. Flask:

[0975] It is used as a server-side web application framework.

[0976] 2. EmotionEngine:

[0977] A proprietary module for analyzing the emotional state of users.

[0978] It performs sentiment analysis based on voice and text input.

[0979] 3. Speech Recognition:

[0980] A library that converts voice input to text.

[0981] Processing flow

[0982] 1. User voice input:

[0983] The user uses their smartphone to input voice commands such as, "I want to ship the product."

[0984] 2. Converting speech to text:

[0985] The smartphone converts voice input into text and sends it to the server.

[0986] 3. Generating the input item list:

[0987] The server analyzes the text input via voice and generates a list of necessary input fields (such as product name, quantity, shipping address, and shipping deadline).

[0988] 4. Prompt presentation:

[0989] Based on the generated list of input fields, the server generates prompts that sequentially present the user with input fields and sends them to the smartphone.

[0990] Example: "Please enter the following information: Product name details" "Please enter the shipping address"

[0991] 5. Analysis of emotional state:

[0992] An emotion engine within the server analyzes the user's voice and input speed to determine if the user is experiencing stress or confusion.

[0993] 6. Supplementary explanations and guidance:

[0994] If the emotion engine detects a user's stress level, the server generates supplementary explanations and guidance and sends them to the smartphone.

[0995] Example: "Additional guidance: Please enter the product name, quantity, and shipping address."

[0996] 7. Saving input data:

[0997] If all user input fields are entered correctly, the server saves this information to the database.

[0998] 8. Completion notification:

[0999] Once data saving is complete, the server sends a saving completion notification to the user, which is then displayed to the user.

[1000] Specific example

[1001] When a user requests, "What should I do next?", the server provides detailed guidance such as, "Please enter the product name, quantity, and shipping address." This prompt might appear in a real-world scenario as follows:

[1002] "I want to ship the product. What should I do next?"

[1003] "I'm having trouble entering customer information. Please help me."

[1004] In this way, systems using emotion engines and prompts enable users to work efficiently in logistics centers without experiencing stress.

[1005] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1006] Step 1:

[1007] User voice input

[1008] The user uses their smartphone to make a voice input, such as "I want to ship the product." This voice data is then sent to the smartphone as input.

[1009] Step 2:

[1010] Speech-to-text conversion

[1011] The device (smartphone) uses the SpeechRecognition library to convert voice input into text data. Specifically, it inputs voice data into the speech recognition engine and outputs the resulting text data.

[1012] Step 3:

[1013] Send a request

[1014] The terminal sends the converted text data to the server. The text, as input data, is sent to the server in the form of an HTTP request. The server's endpoint receives this and prepares the data for analysis.

[1015] Step 4:

[1016] Generating an input item list

[1017] The server parses the received text data and generates a list of necessary input fields. For example, in response to a request such as "I want to ship the product," the server creates a list of input fields including product name, quantity, shipping address, and shipping deadline, and generates this as output data.

[1018] Step 5:

[1019] Prompt presentation

[1020] The server generates prompts that instruct the user to enter information sequentially based on the generated list of input fields. These prompts include text such as "Please enter the product name" or "Please enter the shipping address." These prompts are sent to the terminal and displayed to the user.

[1021] Step 6:

[1022] Receiving user input

[1023] The terminal receives text data entered by the user based on prompts and sends it to the server. The input data includes specific answers to each item provided by the user.

[1024] Step 7:

[1025] Analysis of emotional states

[1026] The server uses an emotion engine to analyze the user's input data, voice tone, and input speed. Based on the emotion engine's analysis, it determines whether the user is experiencing stress or confusion and outputs the result.

[1027] Step 8:

[1028] Providing supplementary explanations and guidance

[1029] Based on the analysis results of the emotion engine, the server generates prompts that provide supplementary explanations and guidance as needed. For example, if user stress is detected, it generates additional guidance such as "Please enter the product name, quantity, and shipping address" and sends it to the terminal.

[1030] Step 9:

[1031] Input data verification

[1032] The server verifies that all received user input data is entered correctly. If there are errors or missing data, it generates an error message and sends a prompt to the terminal requesting re-entry.

[1033] Step 10:

[1034] Data saving and completion notification

[1035] After all input data has been entered correctly and verified by the server, the data is saved to the database. Once saving is complete, the server generates a completion notification and sends it to the terminal. The user receives a completion notification on their terminal, such as "Proposal approval has been successfully submitted."

[1036] 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.

[1037] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[1038] 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.

[1039] [Fourth Embodiment]

[1040] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1041] 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.

[1042] 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).

[1043] 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.

[1044] 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.

[1045] 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).

[1046] 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.

[1047] 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.

[1048] 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.

[1049] 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.

[1050] 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.

[1051] 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.

[1052] 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".

[1053] In order to implement the present invention, it is necessary to provide a system in which the user, terminal, and server cooperate to accurately execute the proposal approval process. A specific embodiment of this system is described below.

[1054] First, the user initiates the proposal approval process by giving instructions to the terminal via voice or text. For example, they might enter a request such as, "I want to draft a proposal for company XX to approve."

[1055] Next, the terminal that receives this request parses the request content and sends it to the server. The server confirms the request and generates a list of necessary input fields. This includes customer information, proposal details, estimated price, and approval deadline.

[1056] Based on this list of input items, the server generates prompts that instruct the user to enter the information sequentially and sends them to the terminal.

[1057] The terminal displays the received prompt to the user. For example, it might display "Please enter customer information." The user then enters "ABC Corporation." Similarly, prompts are displayed sequentially for all input fields sent from the server, and the user enters the information.

[1058] Once all input is complete, the terminal sends the user's input data to the server. The server verifies the received data to ensure that all required fields are entered correctly. If there are any missing entries or errors, the server generates an error message and sends a prompt to the terminal requesting re-entry.

[1059] If all fields are entered correctly, the server saves this data to the database. Once saving is complete, the server sends the result to the terminal, which notifies the user that "the proposal has been successfully submitted."

[1060] As a concrete example, a user might type "I want to draft a proposal for approval from company XX," and then be prompted to "Please enter customer information." The user would then type "ABC Corporation," and then be prompted to "Please enter the proposal details," to which the user would type "Implementation of a new system." This process is repeated for all required fields, and finally the data is sent to the server. The server checks the data, and if everything is entered correctly, it saves it to the database and notifies the terminal that saving is complete.

[1061] In this way, this system can help users draft accurate and complete proposals for approval, thereby improving work efficiency.

[1062] The following describes the processing flow.

[1063] Step 1:

[1064] The user instructs the terminal via voice or text, "I want to initiate a proposal for company XX to approve." This request is received by the terminal.

[1065] Step 2:

[1066] The terminal analyzes the user's request, confirms that it is a proposal approval request, and then sends the request details to the server.

[1067] Step 3:

[1068] The server analyzes the received proposal request and generates a list of necessary input fields. This list includes customer information, proposal details, estimated price, and approval deadline.

[1069] Step 4:

[1070] Based on the generated list of input items, the server sequentially generates prompts for each item, requesting input from the user, and sends them to the terminal.

[1071] Step 5:

[1072] The terminal displays the received prompt to the user. For example, it might display "Please enter customer information."

[1073] Step 6:

[1074] The user enters the required information according to the displayed prompts, and the terminal receives that input. For example, the user might enter "ABC Corporation".

[1075] Step 7:

[1076] The terminal collects input from the user and prompts for the next input field. This process is repeated for all required fields.

[1077] Step 8:

[1078] Once all required fields are entered, the device sends the collected data to the server in a single batch.

[1079] Step 9:

[1080] The server checks the received user input data and verifies that all fields have been entered completely. If there are any missing entries or errors, it generates an error message and sends a prompt to the terminal requesting re-entry.

[1081] Step 10:

[1082] If all fields are entered correctly, the server will save the data to the database.

[1083] Step 11:

[1084] Once saving to the database is complete, the server generates a save completion message and sends it to the terminal.

[1085] Step 12:

[1086] The terminal displays a message to the user indicating that the saved document has been successfully saved, and notifies them that "the proposal has been successfully submitted for approval."

[1087] (Example 1)

[1088] 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".

[1089] The current proposal approval system can be difficult for users to input all the necessary information completely and accurately, resulting in frequent errors and omissions. This leads to decreased work efficiency and increased re-entry time. Furthermore, manual data entry is time-consuming and prone to human error. Therefore, there is a need for a system that allows users to quickly and accurately submit proposals for approval.

[1090] 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.

[1091] In this invention, the server includes means for receiving a proposal request from a user, means for analyzing the proposal request, means for generating a list of necessary input items based on the proposal request, means for generating and sending prompts to the user to sequentially input based on the list of input items, means for receiving responses from the user for each input item, means for verifying whether all received input items have been entered correctly, means for generating an error message and requesting re-entry if there is an error in the input items, means for saving the input items to a database if they have been entered correctly, and means for sending a notification to the user that the saving is complete. This enables the user to quickly and accurately draft proposals for approval.

[1092] A "user" is a person who uses this system to initiate the proposal approval process and inputs the necessary information.

[1093] A "proposal request" is an instruction that a user enters via voice or text to initiate the proposal approval process.

[1094] A "terminal" is a device used by a user, specifically a device for entering requests and displaying prompts.

[1095] A "server" is a computer system that controls the entire system based on user input and requests, and processes and stores data.

[1096] "Natural language processing" is a technology that analyzes text and audio data and interprets the meaning and structure contained within them.

[1097] An "input item list" is a list that organizes the information necessary for proposal approval, and includes customer information, proposal details, estimated price, and approval deadline.

[1098] A "prompt" is a message or instruction that instructs the user to enter information based on a list of input fields.

[1099] An "error message" is a warning or instruction to re-enter information that is displayed when there is an error or deficiency in the user's input.

[1100] A "database" is an information aggregation system used to systematically manage and store data within a system.

[1101] A "save completion notification" is a confirmation message sent to the user after the server has successfully saved the data.

[1102] To implement the present invention, it is necessary to provide a system that enables users, terminals, and servers to work together to accurately execute the proposal approval process. This system aims to collect necessary data from user requests and quickly create error-free approval documents. A specific embodiment of this system is shown below.

[1103] First, the user gives instructions to the device via voice or text to begin drafting a proposal for approval. For example, the user inputs a request such as "I want to draft a proposal for approval for company XX" into a device such as a smartphone or computer. This device uses a natural language processing library (e.g., NLTK, spaCy) to analyze the content of the request. After analysis, the device sends the analysis results to the server.

[1104] Next, the server generates a list of input items necessary for proposal approval based on the received request. This list includes customer information, proposal details, estimated price, and approval deadline. Programming languages ​​such as Python or Java can be used for this, and database management systems (e.g., MySQL, PostgreSQL) can be utilized. The server then sends this input item list to the terminal in JSON format or another appropriate format.

[1105] The terminal displays prompts to the user sequentially based on a list of input fields received from the server. For example, a prompt saying "Please enter customer information" is displayed on a web browser. The user enters "ABC Corporation," then a prompt saying "Please enter proposal details" is displayed, and the user enters "Implementation of a new system." Specifically, these prompts are displayed as "Please enter customer information," "Please enter proposal details," "Please enter estimated price," and "Please enter approval deadline."

[1106] Once the user has completed all the inputs, the terminal sends the input data to the server. The server verifies the received data and checks that all required fields have been entered correctly. If there are any errors or missing entries in the data, the server generates an error message and sends it to the terminal along with a prompt to re-enter the information. For example, it might generate a message such as, "The estimated amount is not entered. Please re-enter it."

[1107] If all fields are entered correctly, the server saves the data to the database. After inserting the data using an SQL statement and saving is complete, the server notifies the terminal. The terminal then notifies the user that "the proposal has been successfully submitted," and this message is displayed as a pop-up in the web browser.

[1108] In this way, this system can help users accurately draft proposals for approval, thereby improving work efficiency. Furthermore, by utilizing a generative AI model, the system can further refine user input and achieve highly accurate data processing.

[1109] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1110] Step 1:

[1111] The user enters a request into their device via voice or text to begin drafting a proposal for approval. For example, they might type "I want to draft a proposal for company XX" into their smartphone or computer.

[1112] Input: User request via voice or text input.

[1113] Output: The terminal retrieves the request data.

[1114] Step 2:

[1115] The terminal receives a request from the user and parses the request using a natural language processing library (e.g., NLTK, spaCy). The parsing results include key information such as the name of the company subject to proposal approval and the content of the proposal. After parsing, the terminal sends these results to the server.

[1116] Input: User's request data

[1117] Data processing / calculations: Text analysis using natural language processing

[1118] Output: Send analysis results to the server

[1119] Step 3:

[1120] The server generates a list of input items necessary for proposal approval based on the received analysis results. This list includes customer information, proposal details, estimated price, and approval deadline. Programming languages ​​such as Python or Java are used to generate the list, and it is converted into a format compatible with the structure of the database management system (e.g., MySQL, PostgreSQL). The server sends this input item list to the terminal in JSON format or similar.

[1121] Input: Analysis results

[1122] Data processing / calculations: Generating a list of required input items.

[1123] Output: Send the list of input items to the terminal.

[1124] Step 4:

[1125] The terminal displays prompts to the user sequentially based on the list of input fields received from the server. For example, a prompt saying "Please enter customer information" is displayed on the web browser. The user enters "ABC Corporation," and then a prompt saying "Please enter your proposal" is displayed, to which the user enters "Implementation of a new system."

[1126] Input: Input item list

[1127] Output: Prompt displayed to the user

[1128] Step 5:

[1129] The user enters the required information sequentially according to the prompts displayed on the terminal.

[1130] Input: User input data in response to prompts (e.g., customer information, proposal details, estimated price, approval deadline)

[1131] Output: The terminal collects user input data.

[1132] Step 6:

[1133] The terminal collects all input data from the user and then sends that data to the server.

[1134] Input: User input data

[1135] Output: Input data sent to the server

[1136] Step 7:

[1137] The server validates the received input data. It checks if all required fields are entered correctly and generates an error message if any are missing or incorrect. Along with this error message, it sends a prompt to the terminal to re-enter the information. For example, it might generate a message such as, "The estimated amount is not entered. Please re-enter it."

[1138] Input: User input data

[1139] Data processing / calculations: Data validation and error message generation.

[1140] Output: Error messages and re-entry prompts sent to the terminal

[1141] Step 8:

[1142] The server verifies that all fields are entered correctly and then saves the input data to the database. It inserts the data using SQL statements, and once saving is complete, it generates a save completion notification and sends it to the terminal.

[1143] Input: Validated input data

[1144] Data processing / calculations: Saving data to a database.

[1145] Output: Sends a save completion notification to the device.

[1146] Step 9:

[1147] The terminal receives a notification from the server confirming that the save is complete and notifies the user that "the proposal has been successfully submitted." For example, this may appear as a pop-up message in the web browser.

[1148] Input: Save complete notification

[1149] Output: Completion notification to the user

[1150] (Application Example 1)

[1151] 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".

[1152] Conventional proposal approval systems faced challenges such as the significant time and effort required for users to accurately input the necessary information. Furthermore, frequent input errors and missing fields, along with the time-consuming corrections, often hindered the overall business process. Additionally, using voice input presented difficulties in accurately converting speech to text and generating appropriate prompts.

[1153] 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.

[1154] In this invention, the server includes means for receiving a proposal request from a user, means for generating a list of necessary input items based on the proposal request, means for sending prompts to the user to sequentially input based on the input item list, means for receiving the user's response to each input item, means for verifying whether all received input items have been entered correctly, means for saving the input items to a database if they have been entered correctly, means for sending a notification to the user that the saving is complete, means for analyzing voice input, and means for generating prompt sentences using a generation AI model. As a result, users can efficiently draft proposals for approval using voice input or text input, reducing input errors and missing items, and improving the overall efficiency of the business process.

[1155] A "user" refers to the person who enters a proposal approval request and then provides answers to the subsequent input fields.

[1156] A "proposal request" refers to the initial request a user enters to initiate the proposal approval process.

[1157] The "input item list" refers to a list that enumerates the data items necessary for drafting a proposal for approval.

[1158] A "prompt" refers to a series of input instructions displayed to the user based on a list of input fields.

[1159] "Answer" refers to the content that the user enters in response to a prompt.

[1160] A "database" refers to an information management system used to store accurate data received from users.

[1161] A "save completion notification" refers to a message that informs the user that the data has been accurately saved to the database.

[1162] "Voice input" refers to the sound a user makes through a microphone, and includes the process of recognizing, analyzing, and converting that sound into text.

[1163] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate appropriate prompt sentences in response to user requests.

[1164] In order to implement the present invention, a system is needed in which a server, terminal, and user cooperate to smoothly advance the proposal approval process.

[1165] First, to initiate the proposal approval process, the user sends a request to the terminal via voice input or text input. The voice input used here utilizes the speech_recognition library to convert the user's voice into text data. This voice data is collected and analyzed by the terminal's built-in microphone and speech recognition software.

[1166] Next, the terminal analyzes the received request and sends the data to the server. The server generates an input field list and sends it to the terminal. This input field list includes essential data such as customer information, proposal details, estimated price, and approval deadline.

[1167] The server then uses a generative AI model to generate prompt messages corresponding to each input item. This generative AI model employs algorithms based on natural language processing to construct prompt messages in a way that is easy for the user to understand. The generated prompt messages are sent to the terminal, which then displays them to the user.

[1168] The terminal displays prompts to the user sequentially, and the user enters the necessary data into each input field based on those prompts. For example, if the prompt is "Please enter customer information," the user would enter "ABC Corporation." Similarly, if the prompt is "Please enter proposal details," the user would enter "Implementation of a new system."

[1169] Once all inputs are complete, the terminal sends this data to the server. The server validates the received data to ensure that all input fields are filled in correctly. If there are any errors, it generates an error message and sends a prompt to the terminal requesting re-entry. If there are no errors, it saves the data to the database and sends a notification to the user that the data has been saved.

[1170] As a concrete example, the following prompt message may be displayed:

[1171] 1. "Please enter customer information."

[1172] 2. "Please enter your proposal."

[1173] 3. "Please enter the estimated price."

[1174] 4. "Please enter the approval deadline."

[1175] For example, if a user voice-inputs "I would like to submit a proposal for approval," the terminal will display "Please enter customer information," and the user will input "ABC Corporation." Similarly, when prompted to "Please enter proposal details," the user will input "Introduction of a new system," and the necessary information will be seamlessly collected on the server.

[1176] In this way, prompt generation using voice input analysis and generative AI models reduces the workload on users and enables the efficient and accurate drafting of proposals for approval.

[1177] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1178] Step 1:

[1179] The user inputs a request to initiate a proposal for approval. Specifically, in the case of voice input, the request is sent via the microphone using the speech_recognition library. This voice data is converted to text on the device. The input is the user's voice request, "I want to initiate a proposal for approval." The output is a text version of the request, "I want to initiate a proposal for approval."

[1180] Step 2:

[1181] The terminal analyzes the received request. The analyzed data is sent to the server as an HTTP request. The input is a text-based request: "I want to submit a proposal for approval." The output is a request that has been converted into a data format for transmission to the server.

[1182] Step 3:

[1183] The server analyzes the received request and generates a list of input fields for proposal approval. This list includes customer information, proposal details, estimated price, approval deadline, etc. The input is the submitted request data. The output is the generated list of input fields.

[1184] Step 4:

[1185] The server uses a generative AI model to generate prompt messages based on the input item list. The generated prompt messages are sent to the terminal. The input is the input item list. The output is the prompt messages generated by the generative AI model and sent to the terminal.

[1186] Step 5:

[1187] The terminal displays prompt messages to the user. For example, it might display the message, "Please enter customer information." The input is the prompt message received from the server. The output is the generation of the prompt message displayed to the user.

[1188] Step 6:

[1189] The user enters information into each input field according to the prompts. For example, they might enter "ABC Corporation". The input is the data entered by the user in response to the prompt displayed on the terminal. The output is the user's input data.

[1190] Step 7:

[1191] The terminal sends user input data to the server. The input is the data entered by the user. The output is data generated that is formatted for transmission to the server.

[1192] Step 8:

[1193] The server validates the received data and verifies that all required fields have been entered correctly. For example, it performs error checking to ensure there are no missing fields or input errors. The input is user input data, and the output is the validation results.

[1194] Step 9:

[1195] The server saves the data to the database if it is correct. It accepts verified data as input and generates saved verification information as output.

[1196] Step 10:

[1197] The server generates a message notifying the terminal that saving is complete and sends it. The input is confirmation that saving is complete. The output is a generated save completion notification message sent to the terminal.

[1198] Step 11:

[1199] The terminal displays a save completion notification to the user. The input is the save completion notification message received from the server. The output is the generation of the save completion notification message that will be displayed to the user.

[1200] Example of a prompt:

[1201] "Please enter customer information."

[1202] Please enter your proposal details.

[1203] "Please enter the estimated price."

[1204] "Please enter the approval deadline."

[1205] 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.

[1206] This document specifically describes an embodiment of the present invention: a proposal approval system in which an emotion engine is combined with the user, terminal, and server.

[1207] The user instructs the terminal via voice or text, "I want to draft a proposal for company XX," in order to initiate a proposal approval process. The terminal receives this request, analyzes the request, and sends it to the server. The server confirms the request and generates a list of necessary input fields. This list of input fields includes customer information, proposal details, estimated price, and approval deadline.

[1208] Next, the server generates prompts for each input field based on the generated input field list, instructing the user to enter the information sequentially, and sends these prompts to the terminal. The terminal displays these prompts to the user, who then enters the specific information. For example, it might display "Please enter customer information," and the user would enter "ABC Corporation." Similarly, prompts are displayed sequentially for each input field, and the user enters the information accordingly.

[1209] The terminal collects the data entered by the user, and once all required fields are filled in, it sends the data to the server. The server verifies the received data to confirm that all fields have been entered correctly. If there are any missing entries or errors, it generates an error message and requests re-entry.

[1210] If all fields are entered correctly, the server saves the data to the database. Once saving is complete, the server sends a save completion message to the terminal, and the terminal notifies the user that "the proposal has been successfully submitted."

[1211] Furthermore, this system incorporates an emotion engine. The emotion engine analyzes the user's facial expressions, voice tone, and input speed to recognize the user's emotions. For example, if the user's voice suddenly becomes louder or their input slows down, the emotion engine will determine that the user is experiencing stress or confusion. In such cases, the server supports the user by generating prompts that provide supplementary explanations and guidance and sending them to the terminal.

[1212] For example, if the emotion engine detects that a user is slow to enter customer information, the server will send detailed guidance such as, "Please enter the company name and contact information for customer information." This allows users to submit proposals smoothly without feeling stressed.

[1213] In this way, this system, which incorporates an emotion engine, can respond flexibly to the user's emotional state, making the proposal approval process more efficient and accurate.

[1214] The following describes the processing flow.

[1215] Step 1:

[1216] The user instructs the terminal via voice or text, "I want to draft a proposal for company XX to approve." The terminal receives this request.

[1217] Step 2:

[1218] The terminal analyzes the user's request, confirms that it is a proposal approval request, and then sends the request details to the server.

[1219] Step 3:

[1220] The server analyzes the received proposal request and generates a list of input fields necessary for proposal approval. This list includes customer information, proposal details, estimated price, and approval deadline.

[1221] Step 4:

[1222] Based on the generated list of input items, the server generates prompts for each item to sequentially instruct the user to enter the information, and sends these prompts to the terminal.

[1223] Step 5:

[1224] The terminal displays the received prompt to the user. For example, a prompt such as "Please enter customer information" might be displayed.

[1225] Step 6:

[1226] The user enters the required information according to the displayed prompts. For example, they might enter "ABC Corporation".

[1227] Step 7:

[1228] The terminal collects input from the user and prompts for the next input field. This process is repeated for all required fields.

[1229] Step 8:

[1230] Once the terminal confirms that all fields have been entered, it sends the collected data to the server in a single batch.

[1231] Step 9:

[1232] The server checks the received user input data and verifies that all items have been entered completely and accurately.

[1233] Step 10:

[1234] If there are any missing or incorrect entries, the server generates an error message and sends it to the terminal along with a prompt for re-entry. The terminal then displays this message to the user again.

[1235] Step 11:

[1236] If all fields are entered correctly, the server will save the data to the database.

[1237] Step 12:

[1238] Once saving to the database is complete, the server generates a save completion message and sends it to the terminal.

[1239] Step 13:

[1240] The terminal displays a message to the user indicating that the saved document has been successfully saved. For example, it might notify the user that "The proposal has been successfully drafted."

[1241] Step 14:

[1242] The device activates an emotion engine when the user inputs data, analyzing the user's facial expressions, voice tone, and input speed in real time. This analysis is then sent to a server.

[1243] Step 15:

[1244] The server receives analysis results sent from the emotion engine and determines the user's emotional state. If stress or confusion is detected, the server generates a corresponding guidance prompt and sends it to the terminal.

[1245] Step 16:

[1246] Based on the analysis results of the emotion engine, the device will display prompts that provide supplementary explanations and guidance if the user is experiencing stress or confusion. For example, it might display, "You seem to be having trouble entering information, please enter the company name and contact information."

[1247] This series of steps allows users to accurately draft proposals for approval without experiencing stress. By combining this with an emotion engine, a system is created that can respond flexibly according to the user's emotional state.

[1248] (Example 2)

[1249] 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".

[1250] Conventional proposal approval systems often caused stress and frustration for users when performing cumbersome data entry tasks. Furthermore, the need to repeatedly re-enter data to correct errors and omissions reduced efficiency. Additionally, the lack of appropriate support tailored to users' emotional states exacerbated the burden of data entry.

[1251] 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.

[1252] In this invention, the server includes an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize emotions, means for generating prompts that provide supplementary explanations and guidance based on the user's emotional state, means for receiving a proposal request from the user, means for generating a list of necessary input items based on the proposal request, means for sending prompts to the user to sequentially input based on the input item list, means for receiving the user's response to each input item, means for confirming that all received input items have been entered correctly, means for saving the input items to a database if they have been entered correctly, and means for sending a notification to the user that the saving is complete. This makes it possible to respond flexibly according to the user's emotional state and to carry out the proposal approval process more efficiently and accurately.

[1253] A "proposal request" is an instruction or request that a user sends to the system to initiate the proposal approval process.

[1254] An "input item list" is a list that enumerates the items of information that the system requests from the user.

[1255] A "prompt" is a message or screen display that a system uses to instruct a user to enter information.

[1256] "Answer" refers to the information that the user enters in response to system prompts.

[1257] A "database" is a structured collection of data used by a system to store and manage information.

[1258] A "save completion notification" is a message sent to the user informing them that the system has successfully finished saving information to the database.

[1259] The "emotion engine" is a system module that analyzes the user's facial expressions, voice tone, and input speed to recognize their emotions.

[1260] "Supplementary explanations and guidance" refer to additional instructions or explanations provided when a user experiences confusion or stress during input.

[1261] An "error message" is a message that the system sends to the user prompting them to re-enter data when there are errors or deficiencies in the input data.

[1262] This document specifically describes an embodiment of the present invention: a proposal approval system in which an emotion engine is combined with the user, terminal, and server.

[1263] The user instructs the terminal via voice or text, saying, "I want to draft a proposal for approval from company XX," with the intention of drafting a proposal for approval. The terminal, upon receiving this request, analyzes the request and sends it to the server. For example, the Google Speech-to-Text API is used for speech recognition, and a general natural language processing library is used for text analysis.

[1264] The server confirms the request and generates a list of required input fields. This list includes customer information, proposal details, estimated price, and approval deadline. Based on the input field list, the server generates prompts for each field, instructing the user to enter the information sequentially, and sends these prompts to the terminal. Generative AI models such as OpenAI GPT-4 are used to generate the prompts.

[1265] The terminal displays prompts to the user, who then enters specific information. For example, it might display "Please enter customer information," and the user would enter "ABC Corporation." Similarly, prompts are displayed sequentially for each input field, and the user enters the information accordingly. The data entered by the user is collected by the terminal, and once all required fields have been completed, the data is sent to the server.

[1266] The server validates the received data to ensure all fields are entered correctly. If there are any missing entries or errors, it generates an error message prompting the user to re-enter the information. The error message includes concise instructions for the user to re-enter the incorrect fields. For example, a message such as "The estimated amount is not entered; please enter it again."

[1267] If all fields are entered correctly, the server saves the data to the database. Once saving is complete, the server sends a save completion message to the terminal, which then notifies the user. For example, it might notify the user that "the proposal has been successfully drafted."

[1268] This system incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize their emotions. The emotion engine utilizes tools such as IBM Watson Tone Analyzer and Microsoft Azure Emotion API. For example, if a user's voice suddenly becomes louder or their input slows down, the emotion engine might determine that the user is experiencing stress or confusion. In such cases, the server generates and sends prompts providing supplementary explanations and guidance to the terminal.

[1269] For example, if the emotion engine detects that a user is slow to enter customer information in response to the prompt "Please enter customer information," the server will send detailed guidance such as "Please enter company name and contact information." This allows users to submit proposals smoothly without feeling stressed.

[1270] In this way, this system, which incorporates an emotion engine, can respond flexibly to the user's emotional state, making the proposal approval process more efficient and accurate.

[1271] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1272] Step 1:

[1273] To initiate a proposal approval process, the user instructs the terminal via voice or text, saying, "I would like to initiate a proposal approval process for Company XX." Based on this input, the terminal uses speech recognition software (e.g., Google Speech-to-Text API) or text analysis software to analyze the request. The analyzed data becomes the request statement, "I would like to initiate a proposal approval process for Company XX."

[1274] Step 2:

[1275] The terminal sends the parsed request statement to the server. This request statement is the input necessary to convey the user's intent to the server. The server parses the received request statement and determines the list of input items to be generated. As output, the server generates an input item list that includes customer information, proposal details, estimated amount, and approval deadline.

[1276] Step 3:

[1277] The server generates prompts that sequentially instruct the user to enter information based on a list of input fields. Generative AI models such as OpenAI GPT-4 are used for this prompt generation. An example prompt generated is "Please enter customer information." This prompt is sent to the terminal and displayed to the user.

[1278] Step 4:

[1279] The terminal displays prompts to the user, who then enters specific information for each input field. For example, the user might enter "ABC Corporation". This input data is received by the terminal. The data entered by the user is temporarily stored on the terminal.

[1280] Step 5:

[1281] The terminal sends all collected input data to the server. This data includes customer information, proposal details, estimated price, and approval deadline. The server analyzes the received data and verifies that each item has been entered correctly. As output, the server obtains the verification results.

[1282] Step 6:

[1283] The server performs error checking based on the validation results of the input data. If there are errors or missing entries, the server generates an error message and sends a command to the terminal requesting re-entry. The user corrects the data by re-entering it.

[1284] Step 7:

[1285] If all fields are confirmed to be entered correctly, the server saves the data to the database. Databases such as MySQL and PostgreSQL can be used. Once saving to the database is complete, the server generates a completion notification and sends it to the terminal. The terminal then notifies the user that "the proposal has been successfully submitted."

[1286] Step 8:

[1287] The server incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize emotions. Examples of emotion engines used include IBM Watson Tone Analyzer and Microsoft Azure Emotion API. If the emotion engine detects user stress or confusion, the server generates and sends prompts providing supplementary explanations and guidance to the terminal. For example, if a user is slow to input information in response to "Please enter customer information," the server sends detailed guidance such as "Please enter company name and contact information for customer information." This allows users to smoothly draft proposals for approval without feeling stressed.

[1288] (Application Example 2)

[1289] 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".

[1290] The work in logistics centers is complex and requires many steps to be performed instantly, placing a heavy burden on employees. Furthermore, the stress and confusion employees experience during work significantly reduce work efficiency. Additionally, errors or mistakes in data entry necessitate re-entry, resulting in additional time and effort.

[1291] 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. In this invention, the server includes means for receiving a proposal request from a user, means for generating a list of necessary input items based on the proposal request, means for sending prompts to the user to sequentially input based on the input item list, means for receiving responses from the user to each input item, means for confirming whether all received input items have been entered correctly, means for saving the input items to a database if they have been entered correctly, means for sending a notification to the user that the saving is complete, means including an emotion engine for analyzing emotional states, and means for providing supplementary explanations and guidance based on the emotion analysis results. This reduces the stress and confusion that employees feel while working in a logistics center, enabling efficient and accurate work execution.

[1292] A "user" is an entity that uses a system to input information and perform tasks.

[1293] A "proposal request" is a request from a user to initiate a task or perform a specific process within the system.

[1294] An "input item list" is a list of necessary information that the user must enter into the system.

[1295] A "prompt" is a message from the system that instructs the user to input information sequentially.

[1296] "Answer" refers to the information that a user provides to the system based on the input fields.

[1297] A "database" is a system for storing and managing collected data.

[1298] An "emotion engine" is a device or program that analyzes a user's emotional state and evaluates stress and confusion.

[1299] "Supplementary explanations and guidance" refer to additional explanations or instructions provided to users when using the system.

[1300] Modes for carrying out the invention

[1301] This invention is a proposal approval system for logistics centers that utilizes an emotion engine. The main components used to carry out this invention are described below.

[1302] System Overview

[1303] This system allows users to make requests via voice or text input, which the server then analyzes to generate the necessary input fields and presents prompts to the user based on those fields. Furthermore, it uses an emotion engine to analyze the user's emotional state and provides supplementary explanations and guidance as needed.

[1304] hardware

[1305] 1. Smartphone:

[1306] It is used by users for voice input and text input.

[1307] It is responsible for displaying prompts to the user and sending input data to the server.

[1308] 2. Server:

[1309] Receive and analyze requests from users.

[1310] Generate a list of required input fields and prepare prompts.

[1311] The system uses an emotion engine to analyze emotional states and generate appropriate guidance.

[1312] The received data is saved to the database.

[1313] software

[1314] 1. Flask:

[1315] It is used as a server-side web application framework.

[1316] 2. EmotionEngine:

[1317] A proprietary module for analyzing the emotional state of users.

[1318] It performs sentiment analysis based on voice and text input.

[1319] 3. Speech Recognition:

[1320] A library that converts voice input to text.

[1321] Processing flow

[1322] 1. User voice input:

[1323] The user uses their smartphone to input voice commands such as, "I want to ship the product."

[1324] 2. Converting speech to text:

[1325] The smartphone converts voice input into text and sends it to the server.

[1326] 3. Generating the input item list:

[1327] The server analyzes the text input via voice and generates a list of necessary input fields (such as product name, quantity, shipping address, and shipping deadline).

[1328] 4. Prompt presentation:

[1329] Based on the generated list of input fields, the server generates prompts that sequentially present the user with input fields and sends them to the smartphone.

[1330] Example: "Please enter the following information: Product name details" "Please enter the shipping address"

[1331] 5. Analysis of emotional state:

[1332] An emotion engine within the server analyzes the user's voice and input speed to determine if the user is experiencing stress or confusion.

[1333] 6. Supplementary explanations and guidance:

[1334] If the emotion engine detects a user's stress level, the server generates supplementary explanations and guidance and sends them to the smartphone.

[1335] Example: "Additional guidance: Please enter the product name, quantity, and shipping address."

[1336] 7. Saving input data:

[1337] If all user input fields are entered correctly, the server saves this information to the database.

[1338] 8. Completion notification:

[1339] Once data saving is complete, the server sends a saving completion notification to the user, which is then displayed to the user.

[1340] Specific example

[1341] When a user requests, "What should I do next?", the server provides detailed guidance such as, "Please enter the product name, quantity, and shipping address." This prompt might appear in a real-world scenario as follows:

[1342] "I want to ship the product. What should I do next?"

[1343] "I'm having trouble entering customer information. Please help me."

[1344] In this way, systems using emotion engines and prompts enable users to work efficiently in logistics centers without experiencing stress.

[1345] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1346] Step 1:

[1347] User voice input

[1348] The user uses their smartphone to make a voice input, such as "I want to ship the product." This voice data is then sent to the smartphone as input.

[1349] Step 2:

[1350] Speech-to-text conversion

[1351] The device (smartphone) uses the SpeechRecognition library to convert voice input into text data. Specifically, it inputs voice data into the speech recognition engine and outputs the resulting text data.

[1352] Step 3:

[1353] Send a request

[1354] The terminal sends the converted text data to the server. The text, as input data, is sent to the server in the form of an HTTP request. The server's endpoint receives this and prepares the data for analysis.

[1355] Step 4:

[1356] Generating an input item list

[1357] The server parses the received text data and generates a list of necessary input fields. For example, in response to a request such as "I want to ship the product," the server creates a list of input fields including product name, quantity, shipping address, and shipping deadline, and generates this as output data.

[1358] Step 5:

[1359] Prompt presentation

[1360] The server generates prompts that instruct the user to enter information sequentially based on the generated list of input fields. These prompts include text such as "Please enter the product name" or "Please enter the shipping address." These prompts are sent to the terminal and displayed to the user.

[1361] Step 6:

[1362] Receiving user input

[1363] The terminal receives text data entered by the user based on prompts and sends it to the server. The input data includes specific answers to each item provided by the user.

[1364] Step 7:

[1365] Analysis of emotional states

[1366] The server uses an emotion engine to analyze the user's input data, voice tone, and input speed. Based on the emotion engine's analysis, it determines whether the user is experiencing stress or confusion and outputs the result.

[1367] Step 8:

[1368] Providing supplementary explanations and guidance

[1369] Based on the analysis results of the emotion engine, the server generates prompts that provide supplementary explanations and guidance as needed. For example, if user stress is detected, it generates additional guidance such as "Please enter the product name, quantity, and shipping address" and sends it to the terminal.

[1370] Step 9:

[1371] Input data verification

[1372] The server verifies that all received user input data is entered correctly. If there are errors or missing data, it generates an error message and sends a prompt to the terminal requesting re-entry.

[1373] Step 10:

[1374] Data saving and completion notification

[1375] After all input data has been entered correctly and verified by the server, the data is saved to the database. Once saving is complete, the server generates a completion notification and sends it to the terminal. The user receives a completion notification on their terminal, such as "Proposal approval has been successfully submitted."

[1376] 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.

[1377] 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.

[1378] 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.

[1379] 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.

[1380] 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.

[1381] 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.

[1382] 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.

[1383] 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.

[1384] 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."

[1385] 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.

[1386] 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.

[1387] 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.

[1388] 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.

[1389] 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.

[1390] 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.

[1391] 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.

[1392] 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.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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.

[1397] The following is further disclosed regarding the embodiments described above.

[1398] (Claim 1)

[1399] A means of receiving proposal requests from users,

[1400] A means for generating a list of necessary input items based on the aforementioned drafting request,

[1401] A means for sending prompts to the user to sequentially input information based on the aforementioned list of input items,

[1402] A means of receiving responses from the user for each input field,

[1403] A means to verify that all received input fields have been entered correctly,

[1404] If the aforementioned input items are entered correctly, a means for saving them to the database,

[1405] A means for sending a notification to the user that the saving process is complete,

[1406] A system that includes this.

[1407] (Claim 2)

[1408] The system according to claim 1, wherein the input item list includes customer information, proposal details, estimated amount, and approval deadline.

[1409] (Claim 3)

[1410] The system according to claim 1, further comprising means for sending an error message to the user and prompting them to re-enter the information if there are errors or missing entries in the input fields.

[1411] "Example 1"

[1412] (Claim 1)

[1413] A means of receiving proposal requests from users,

[1414] A means for analyzing the aforementioned draft request,

[1415] A means for generating a list of necessary input items based on the aforementioned drafting request,

[1416] A means for generating and sending prompts to the user to sequentially input information based on the aforementioned list of input items,

[1417] A means of receiving responses from the user for each input field,

[1418] A means to verify that all received input fields have been entered correctly,

[1419] If there is an error in the aforementioned input field, a means is provided to generate an error message and request re-entry.

[1420] If the aforementioned input items are entered correctly, a means for saving them to the database,

[1421] A means for sending a notification to the user that the saving process is complete,

[1422] A system that includes this.

[1423] (Claim 2)

[1424] The system according to claim 1, wherein the input item list includes customer information, proposal details, estimated amount, and approval deadline.

[1425] (Claim 3)

[1426] The system according to claim 1, further comprising means for using natural language processing in the analysis of the draft request.

[1427] "Application Example 1"

[1428] (Claim 1)

[1429] A means of receiving proposal requests from users,

[1430] A means for generating a list of necessary input items based on the aforementioned drafting request,

[1431] A means for sending prompts to the user to sequentially input information based on the aforementioned list of input items,

[1432] A means of receiving responses from the user for each input field,

[1433] A means to verify that all received input fields have been entered correctly,

[1434] If the aforementioned input items are entered correctly, a means for saving them to the database,

[1435] A means for sending a notification to the user that the saving process is complete,

[1436] A means of analyzing voice input,

[1437] A means for generating prompt sentences using a generative AI model,

[1438] A system that includes this.

[1439] (Claim 2)

[1440] The system according to claim 1, wherein the input item list includes customer information, proposal details, estimated amount, and approval deadline.

[1441] (Claim 3)

[1442] The system according to claim 1, further comprising means for sending an error message to the user and prompting them to re-enter the information if there are errors or missing entries in the input fields.

[1443] "Example 2 of combining an emotion engine"

[1444] (Claim 1)

[1445] A means of receiving proposal requests from users,

[1446] A means for generating a list of necessary input items based on the aforementioned drafting request,

[1447] A means for sending prompts to the user to sequentially input information based on the aforementioned list of input items,

[1448] A means of receiving responses from the user for each input field,

[1449] A means to verify that all received input fields have been entered correctly,

[1450] If the aforementioned input items are entered correctly, a means for saving them to the database,

[1451] A means for sending a notification to the user that the saving process is complete,

[1452] A system having an emotion engine that analyzes the user's facial expressions, voice tone, and input speed to recognize emotions, and further including means for generating prompts that provide supplementary explanations and guidance based on the user's emotional state.

[1453] (Claim 2)

[1454] The system according to claim 1, wherein the input item list includes customer information, proposal details, estimated amount, and approval deadline.

[1455] (Claim 3)

[1456] The system according to claim 1, further comprising means for sending an error message to the user and prompting them to re-enter the information if there are errors or missing entries in the input fields.

[1457] "Application example 2 of combining emotional engines"

[1458] (Claim 1)

[1459] A means of receiving proposal requests from users,

[1460] A means for generating a list of necessary input items based on the aforementioned drafting request,

[1461] A means for sending prompts to the user to sequentially input information based on the aforementioned list of input items,

[1462] A means of receiving responses from the user for each input field,

[1463] A means to verify that all received input fields have been entered correctly,

[1464] If the aforementioned input items are entered correctly, a means for saving them to the database,

[1465] A means for sending a notification to the user that the saving process is complete,

[1466] A means including an emotion engine for analyzing emotional states,

[1467] Based on the aforementioned emotion analysis results, means for providing supplementary explanations and guidance,

[1468] A system that includes this.

[1469] (Claim 2)

[1470] The system according to claim 1, wherein the input item list includes customer information, proposal details, estimated amount, and approval deadline.

[1471] (Claim 3)

[1472] The system according to claim 1, further comprising means for sending an error message to the user and prompting them to re-enter the information if there are errors or missing entries in the input fields. [Explanation of symbols]

[1473] 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 receiving proposal requests from users, A means for generating a list of necessary input items based on the aforementioned drafting request, A means for sending prompts to the user to sequentially input information based on the aforementioned list of input items, A means of receiving responses from the user for each input field, A means to verify that all received input fields have been entered correctly, If the aforementioned input items are entered correctly, a means for saving them to the database, A means for sending a notification to the user that the saving process is complete, A system that includes this.

2. The system according to claim 1, wherein the input item list includes customer information, proposal details, estimated amount, and approval deadline.

3. The system according to claim 1, further comprising means for sending an error message to the user and requesting re-entry if there are errors or missing entries in the input fields.

Images