system

Abstract

We provide the system. [Solution] A method for automatically creating documents using generative artificial intelligence, A means of revising materials based on user feedback, A means of sending user requests from the terminal to the server, A means of sending a prompt from the server to a generative artificial intelligence, A means of returning the generated materials to the terminal and displaying them, A system that includes this.

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 in 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] In the conventional negotiation document creation process, since the user creates and modifies the document manually, there is a problem that it takes time and labor and is inefficient. In addition, there is a lack of a system for efficiently reflecting the user's input and modification content, and the quality and accuracy of the document are unstable. As a result, there is a risk of affecting the success rate and professionalism of the negotiation.

Means for Solving the Problems

[0005] To solve these problems, the present invention provides a system that includes means for automatically creating documents using generative artificial intelligence, means for modifying documents based on user feedback, means for sending user requests from a terminal to a server, means for sending prompts from the server to the generative artificial intelligence, and means for returning and displaying the generated documents on the terminal. This enables the rapid and efficient creation and modification of business negotiation documents, reduces the burden on the user, and improves the quality and accuracy of the documents.

[0006] "Generative artificial intelligence" refers to algorithms or systems that automatically generate documents and materials based on user input data using natural language processing and machine learning techniques.

[0007] "User feedback" refers to opinions and instructions, such as requests for revisions or additional suggestions, that users submit regarding the generated materials.

[0008] A "terminal" is a device, such as a computer or smartphone, that a user uses to manipulate, input, and verify input data.

[0009] A "server" is a computer system that receives data from terminals and transmits that data to a generative artificial intelligence system.

[0010] A "prompt" is text data in the form of instructions or questions that form the basis for a generative artificial intelligence system when generating materials.

[0011] "Documents" refer to documents used in business negotiations, such as presentation slides and proposals.

[0012] "Automated creation" refers to the process of generating documents using generative artificial intelligence with minimal human intervention.

[0013] "Transmission" is the process of data communication in which data is moved from one computer system to another. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

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

[0018] In the following embodiments, a labeled 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 labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, 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] This invention relates to a system that automatically creates sales materials using generative artificial intelligence and modifies and regenerates the materials based on user feedback. This system includes a terminal, a server, and the generative artificial intelligence as components.

[0036] Specific Embodiments

[0037] User input

[0038] The user logs into the terminal and begins creating sales materials. The user enters the necessary information for the sales materials into a dedicated input form. For example, when creating a presentation document for a new product, the user would enter items such as "Introduction to New Product X," "Target Customer: A Certain Company," "Features: High Performance, Low Price," and "Layout: Simple" into the input form.

[0039] Data transmission on the device

[0040] The terminal collects data entered by the user and sends it to the server. This transmission is done via an HTTP POST request, and the data is delivered to the server in JSON format.

[0041] Server-based data analysis and prompt generation

[0042] The server parses the received JSON data. As a result of this analysis, prompts are generated to instruct the generative artificial intelligence. For example, text such as "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. Please keep the layout simple." might be generated.

[0043] Initial document creation using generative artificial intelligence

[0044] The server sends the generated prompt to the generative artificial intelligence. The generative AI generates initial documents based on this prompt. The generated documents are sent back to the server as an initial version of the sales negotiation materials. For example, a document like the following is generated:

[0045] 1. Introduction of New Product X

[0046] 1.1. High performance

[0047] 1.2. Low price

[0048] 2. Key points of the proposal

[0049] 2.1. A suitable solution for a particular company

[0050] Sending documents via server

[0051] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays this data to the user, allowing the user to review it.

[0052] User feedback

[0053] The user reviews the generated sales materials and enters any requests for revisions or additions. For example, a user might submit a revision request such as, "Please add an introductory paragraph to Chapter 1."

[0054] Sending additional requests from the device

[0055] The terminal resends the user's correction instructions to the server. This transmission is also done via an HTTP POST request, and the data is again sent to the server in JSON format.

[0056] Server-based re-analysis of data and prompt generation

[0057] The server analyzes the received feedback again and generates a new prompt. For example, it might generate a prompt such as, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X."

[0058] Regeneration by generative artificial intelligence

[0059] The server sends a new prompt to the generative artificial intelligence. Based on this prompt, the generative AI regenerates the sales proposal document and sends the revised document back to the server. For example, a document with an introductory sentence added to Chapter 1 is generated.

[0060] Server-based transmission of revised documents

[0061] The server sends the revised document to the terminal and displays it to the user. The user can review the regenerated document and make further corrections as needed.

[0062] User's final confirmation

[0063] The user makes a final review, and once they are satisfied with the sales materials, they use them in the sales negotiation.

[0064] As described above, the system of the present invention supports the efficient creation of business negotiation materials by collecting user input and automatically generating and modifying materials using generative artificial intelligence.

[0065] The following describes the processing flow.

[0066] Step 1:

[0067] The user logs into the terminal and begins creating the sales presentation materials. The user enters the requirements for the sales presentation materials (purpose, target customers, features, desired layout, etc.) into a dedicated input form.

[0068] Step 2:

[0069] The terminal converts the data entered by the user into JSON format and sends it to the server via an HTTP POST request.

[0070] Step 3:

[0071] The server analyzes the JSON data received from the terminal. Based on the analysis results, it generates prompts to send to the generative artificial intelligence.

[0072] Step 4:

[0073] The generative artificial intelligence generates initial sales materials based on prompts received from the server. The generated materials are then sent back to the server.

[0074] Step 5:

[0075] The server sends the initial data received from the generative artificial intelligence to the user's terminal. The terminal displays the data to the user, allowing them to review it.

[0076] Step 6:

[0077] The user reviews the displayed sales materials and enters requests for corrections or additions. For example, they might enter instructions such as, "Please add an introductory paragraph to Chapter 1," into the terminal.

[0078] Step 7:

[0079] The terminal converts the user's correction instructions into JSON data and sends it back to the server as an HTTP POST request.

[0080] Step 8:

[0081] The server analyzes the user feedback it receives again and generates a new prompt. For example, it might generate a prompt such as, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X."

[0082] Step 9:

[0083] The generative artificial intelligence regenerates the document based on the new prompt received from the server. The revised document is then sent back to the server.

[0084] Step 10:

[0085] The server sends the regenerated document to the user's terminal. The terminal displays the corrected document to the user, providing another opportunity for review.

[0086] Step 11:

[0087] The user reviews the regenerated document and provides further revision instructions as needed. This process is repeated until a satisfactory document is finalized.

[0088] Step 12:

[0089] The user reviews the final version of the sales proposal materials, and once completed, uses them in the sales negotiation.

[0090] The above outlines the specific processing flow in the sales negotiation document creation system.

[0091] (Example 1)

[0092] 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."

[0093] Creating sales materials requires users to expend a significant amount of time and effort. Furthermore, the process of incorporating revisions and additional requests to these materials is complex and time-consuming. This can reduce the efficiency of sales material creation and negatively impact the success rate of sales negotiations.

[0094] 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.

[0095] In this invention, the server includes means for transmitting user requests from a terminal, means for the server to analyze user requests and generate prompt messages for a generation AI model, and means for the generation AI model to automatically generate materials based on the received prompt messages. This enables the rapid and efficient creation of sales materials and easy modification based on user feedback.

[0096] "Terminal" refers to all devices used by users to create and modify sales materials and to communicate with the server.

[0097] A "server" refers to a computing system that has the function of analyzing requests received from users and generating prompt messages to send to the AI ​​model.

[0098] A "generative AI model" refers to artificial intelligence technology that automatically generates materials based on the received prompt text.

[0099] A "prompt" refers to a text-based instruction that provides guidance to a generative AI model regarding the content and format of the document.

[0100] "Documents" refers to documents containing various pieces of information used in business negotiations.

[0101] "Feedback" refers to the input information that users use to request corrections or additions after reviewing the generated materials.

[0102] "Revised document" refers to a document regenerated by the AI ​​model based on user feedback.

[0103] "Automatic generation" refers to the process in which a generation AI model creates documents based on prompt text without human intervention.

[0104] A "re-prompt" refers to a new prompt message generated based on corrections or additional instructions.

[0105] "Transmission" refers to the process of moving data from a terminal to a server, or from a server to a generated AI model.

[0106] This invention relates to a system that automatically creates sales materials using a generative AI model and modifies and regenerates the materials based on user feedback. This system includes components such as a terminal, a server, and a generative AI model.

[0107] Specific Embodiments

[0108] Hardware environment

[0109] Devices: PCs, tablets, smartphones, etc. Users access the system using these devices.

[0110] Server: Receives and analyzes data, generates prompt messages, and communicates with the AI ​​model. This could be a cloud server or an on-premises server.

[0111] Generative AI models: For example, GPT-3 (registered trademark) and ChatGPT (registered trademark) from OpenAI (registered trademark). They generate sales materials based on prompt messages generated by the server.

[0112] Software Environment

[0113] Server-side scripting: Uses programming languages ​​such as Python and Java (registered trademark) to parse user requests and generate prompt messages.

[0114] HTTP Requests: Used for sending data between the terminal and the server, and between the server and the generated AI model. Requests use HTTP POST requests.

[0115] User input

[0116] The user logs into the terminal and begins creating sales materials. The user enters the necessary information into a dedicated input form. For example, when creating a presentation document for a new product, the user would enter information such as: "Introduction to New Product X," "Target Customer: A Certain Company," "Features: High Performance, Low Price," and "Layout: Simple."

[0117] Data transmission on the device

[0118] The terminal collects data entered by the user and sends it to the server. This transmission is done via an HTTP POST request, and the data is delivered to the server in JSON format.

[0119] Server-based data analysis and prompt generation

[0120] The server parses the received JSON data and generates prompt messages to instruct the AI ​​model based on the results of this analysis. For example, it might generate text such as, "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. Please keep the layout simple."

[0121] Initial document creation using a generative AI model

[0122] Based on the generated prompt text, the AI ​​model generates an initial version of the sales presentation materials. These presentation materials will be in the following format:

[0123] 1. Introduction of New Product X

[0124] 1.1. High performance

[0125] 1.2. Low price

[0126] 2. Key points of the proposal

[0127] 2.1. A suitable solution for a particular company

[0128] The generated documents are sent to the terminal via the server.

[0129] User feedback and corrections

[0130] The user reviews the generated sales presentation materials and enters requests for revisions or additions. For example, they might instruct, "Please add an introductory paragraph to Chapter 1." The terminal resends the user's feedback to the server, which analyzes the feedback and generates a new prompt. The generation AI model regenerates the sales presentation materials based on this new prompt, and this revised material is sent back to the terminal via the server.

[0131] By repeating this process, users can efficiently create satisfactory sales materials. Furthermore, this system allows for repeated revision and improvement of materials generated based on user input and feedback, thereby improving the quality of materials used in sales negotiations.

[0132] As described above, the system of the present invention significantly improves the efficiency of creating sales materials by automating the sales material creation process using a generative AI model and enabling rapid revisions based on user feedback.

[0133] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0134] Step 1:

[0135] Users log in to the system using a terminal.

[0136] Specific steps: The user enters their user ID and password and clicks the "Login" button. The system sends the authentication information to the server, and if authentication is successful, the next screen is displayed.

[0137] Input: User ID, Password

[0138] Output: User authentication result, next operation screen

[0139] Step 2:

[0140] The user enters the necessary information into the input form to begin creating the sales presentation materials.

[0141] Specific operation: The user enters information such as "Introduction to new product X," "Target customer: A certain company," "Features: High performance, low price," and "Layout: Simple," and then clicks the "Submit" button.

[0142] Input: Each item in the sales presentation materials (new product name, target customers, features, layout, etc.)

[0143] Output: Request to send input information

[0144] Step 3:

[0145] The terminal sends the information entered by the user to the server via an HTTP POST request.

[0146] Specific operation: The terminal converts the input data into JSON format and sends it to the server.

[0147] Input: Information from sales materials entered by the user.

[0148] Output: Send data in JSON format

[0149] Step 4:

[0150] The server parses the received JSON data and generates prompt messages to send to the AI ​​model.

[0151] Specific operation: The server uses a Python script to parse the JSON data and generates a prompt message that reads, "Create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. The layout should be simple."

[0152] Input: Information from business negotiation materials sent in JSON format

[0153] Output: Prompt message to send to the generated AI model

[0154] Step 5:

[0155] The server sends the generated prompt message to the AI ​​model, requesting it to generate initial data.

[0156] Specific operation: The server sends a prompt message to the AI ​​generation model via an HTTP POST request. The AI ​​generation model generates sales materials based on the prompt message and sends them back to the server.

[0157] Input: Prompt text for the generated AI model

[0158] Output: Initial data generated by a generative AI model

[0159] Step 6:

[0160] The server sends the generated initial data to the terminal and displays it to the user.

[0161] Specific operation: The server uses an HTTP POST request to send the generated data to the terminal in JSON format. The terminal displays the received data to the user.

[0162] Input: Initial data returned from the generated AI model

[0163] Output: Display of initial materials in a format viewable by the user.

[0164] Step 7:

[0165] The user reviews the generated document and enters any necessary corrections or additional requests.

[0166] Specific actions: The user reviews the document, enters specific feedback such as "Please add an introductory paragraph to Chapter 1," and clicks the "Submit" button.

[0167] Input: User requests for modifications or additions

[0168] Output: Request to send correction instructions

[0169] Step 8:

[0170] The terminal then sends the user's correction instructions back to the server.

[0171] Specific operation: The terminal converts the modification request into JSON format and sends it to the server via an HTTP POST request.

[0172] Input: User requests for modifications or additions

[0173] Output: Sending correction instructions in JSON format

[0174] Step 9:

[0175] The server analyzes the received correction instructions and generates a new prompt message.

[0176] Specific operation: The server uses a Python script to analyze the feedback data and generates a new prompt message: "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X."

[0177] Input: Correction instructions in JSON format

[0178] Output: New prompt message to send to the generated AI model

[0179] Step 10:

[0180] The server sends a new prompt message to the AI ​​model, requesting it to generate the revised document.

[0181] Specific operation: The server sends a prompt message to the generating AI model via an HTTP POST request. The generating AI model generates revised data based on the prompt message and sends it back to the server.

[0182] Input: New prompt message to the generated AI model

[0183] Output: Revised document generated by an AI model

[0184] Step 11:

[0185] The server sends the revised document to the terminal and displays it to the user.

[0186] Specific operation: The server sends the revised document to the terminal in JSON format using an HTTP POST request. The terminal displays the received document to the user.

[0187] Input: Revised data returned from the generated AI model

[0188] Output: Display of the revised document in a format viewable by the user.

[0189] Step 12:

[0190] The user performs a final review, and once the materials meet their quality standards, they are used in business negotiations.

[0191] Specific actions: The user reviews the document one last time and, if necessary, submits a revision request, or reviews the document one last time and downloads or prints it.

[0192] Input: User's final confirmation

[0193] Output: Finalization of documents for use in business negotiations.

[0194] (Application Example 1)

[0195] 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."

[0196] In modern business negotiations and customer service at retail stores, it is crucial to be able to quickly prepare promotional and explanatory materials. However, creating these manually is time-consuming and inefficient. Furthermore, quickly gathering customer feedback is not easy. To solve these problems and improve customer satisfaction, there is a need for an automated material generation system utilizing generative artificial intelligence.

[0197] 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.

[0198] In this invention, the server includes means for automatically creating materials using generative artificial intelligence, means for modifying materials based on user feedback, means for transmitting user requests from a terminal to the server, means for generating and updating sales materials and promotional materials via a smart device, and means for incorporating customer feedback and regenerating materials. This makes it possible to provide sales materials and promotional materials quickly and efficiently, and to immediately reflect customer feedback.

[0199] "Generative artificial intelligence" refers to artificial intelligence that has the ability to generate new information or content based on input data.

[0200] "Methods for automatically creating documents" refers to a system that automatically creates documents using generative artificial intelligence based on user requests.

[0201] "Means of modifying materials based on user feedback" refers to methods of modifying existing materials using generative artificial intelligence to reflect user opinions and requests.

[0202] "Means of sending user requests from a terminal to a server" refers to a function that allows a user to send instructions to a server from their device for creating or modifying business negotiation materials.

[0203] "Means of sending prompts from a server to a generative artificial intelligence" refers to a method by which a server analyzes the user's request and sends instructions (prompts) based on that analysis to the generative artificial intelligence.

[0204] "A means of returning and displaying generated materials on a terminal" refers to a mechanism in which a server sends materials created by a generative artificial intelligence to a user's terminal, and the user can view and display them.

[0205] "Means for generating and updating sales materials and promotional materials via smart devices" refers to methods for generating sales materials and promotional materials using devices such as smart glasses and smartphones, and updating them as needed.

[0206] "Methods for incorporating customer feedback and regenerating materials" refers to a system that collects opinions and requests provided by customers and then regenerates materials with necessary updates based on that feedback.

[0207] A "smart device" refers to a glasses-type device or mobile phone equipped with internet connectivity and application execution capabilities.

[0208] This invention provides a system that automatically creates sales materials and promotional materials using generative artificial intelligence, and modifies and regenerates the materials based on user feedback. This system consists of a terminal, a server, and generative artificial intelligence.

[0209] System Configuration

[0210] terminal

[0211] The terminal utilizes smart devices (such as smart glasses or smartphones). Users use this terminal to input requests for the creation of business negotiation materials, and to review and modify the generated materials.

[0212] server

[0213] The server receives request data sent from the user via the terminal, analyzes it, and sends prompts to the generative artificial intelligence. The main functions of the server are as follows:

[0214] Analyze user requests and generate prompts.

[0215] A prompt is sent to the generative artificial intelligence, and the generated material is received.

[0216] The received documents are sent back to the user's device.

[0217] Generative artificial intelligence

[0218] Generative artificial intelligence generates sales materials and promotional materials based on prompts received from the server. The generated materials are sent back to the server and displayed again on the user's device.

[0219] Program Processing Description

[0220] Hardware:

[0221] Smart glasses (e.g., Google Glass®)

[0222] Smartphones (e.g., iPhone®, Android® devices)

[0223] Server Computer

[0224] software:

[0225] Flask (a web framework based on Python®)

[0226] requests (a Python module for sending HTTP requests)

[0227] APIs for generative AI models (e.g., OpenAI GPT, etc.)

[0228] The server analyzes user requests sent from smart devices and generates prompts for generative artificial intelligence. The generative AI model then creates prompt statements that generate materials. For example, a prompt might read: "A customer is requesting detailed information about the special features of new product Y. New product Y is highly durable and energy-efficient. Please create promotional materials that explain this in a way that does not require specialized knowledge."

[0229] This prompt is sent to a generative artificial intelligence system, the server receives the generated material, and sends it back to the terminal for display. The user can review the generated material, provide corrections or additional feedback, the server analyzes it again, and sends it to the generative AI model as a new prompt.

[0230] Specific example:

[0231] One scenario envisioned is that when a customer asks for details about a new product in a store, staff use smart glasses to instantly generate information and display it on a screen.

[0232] Customer question: "I would like to know more details about the special features of product X."

[0233] Staff operation: The staff member voice-inputs the following into the smart glasses: "Please generate documentation about the special features of the new product X."

[0234] System processing: Generates a prompt message, sends it to the generation AI model, and displays the generated document on the terminal.

[0235] This allows users to immediately provide materials to respond to customers and to quickly gather customer feedback.

[0236] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0237] Step 1:

[0238] User request input

[0239] Users use their devices (smart glasses or smartphones) to input requests for the creation of sales materials or promotional materials. For example, they might use the voice input function of their smart glasses to input a request such as, "Please create an introductory document for new product X." This input data is processed within the device and sent to the server.

[0240] Input: Request for creation of sales materials (e.g., introductory materials for new product X)

[0241] Output: Requested data

[0242] Step 2:

[0243] Sending request data

[0244] The terminal sends user input data to the server. The data is sent to the server in JSON format as an HTTP POST request. This process ensures the data is delivered to the server and ready for analysis.

[0245] Input: Request data

[0246] Output: HTTP POST request to the server

[0247] Step 3:

[0248] Server-based request data analysis

[0249] The server analyzes the received request data and creates a prompt to send to the generative artificial intelligence. For example, if a user requests, "Please create an introductory document for new product X," the server will generate a prompt such as, "Please create an introductory document for new product X. The target customers are general consumers. Its features are high performance and low price."

[0250] Input: Request data in an HTTP POST request

[0251] Output: Prompts for generative artificial intelligence

[0252] Step 4:

[0253] Send a prompt

[0254] The server sends the generated prompt to the generative AI. It sends the prompt as an API request to the generative AI, requesting the generation of data. At this time, an HTTP POST request is made to the generative AI's API endpoint.

[0255] Input: Prompt

[0256] Output: API request to a generative artificial intelligence system

[0257] Step 5:

[0258] Data generation

[0259] Generative artificial intelligence generates sales materials and promotional materials based on prompts. These generated materials are then sent back to the server. For example, a document containing sections such as "Introduction to New Product X," "High Performance," and "Low Price" is generated.

[0260] Input: Prompt

[0261] Output: Generated document

[0262] Step 6:

[0263] Return of generated documents

[0264] The server returns the data received from the generative artificial intelligence to the terminal. The data is sent as a response to an HTTP POST request and displayed on the terminal. The user can visually confirm the generated data.

[0265] Input: Generated document

[0266] Output: HTTP POST response to the terminal

[0267] Step 7:

[0268] Displaying documents and entering feedback

[0269] The user reviews the generated document on their device and provides feedback as needed. For example, they might enter a correction request such as, "Please add an introductory sentence to Chapter 1." This feedback data is then sent back to the server.

[0270] Input: Generated materials and feedback

[0271] Output: Feedback data

[0272] Step 8:

[0273] Sending feedback data

[0274] The device resends the user's feedback data to the server. The data is sent again to the server in JSON format as an HTTP POST request, and is ready for regeneration.

[0275] Input: Feedback data

[0276] Output: HTTP POST request to the server

[0277] Step 9:

[0278] Regeneration prompt generation

[0279] The server analyzes the feedback data and generates a new prompt. For example, it generates a new prompt such as "Please add an introduction paragraph to Chapter 1 of the introduction materials for the new product X." and sends it to the generative artificial intelligence.

[0280] Input: Feedback data in the HTTP POST request

[0281] Output: New prompt

[0282] Step 10:

[0283] Regeneration of materials and final transmission

[0284] The server sends the new prompt to the generative artificial intelligence to generate a revised version of the materials. The generated materials are returned to the server again and then sent to the terminal. The user finally checks the regenerated materials and uses them for business negotiations or promotions.

[0285] Input: New prompt

[0286] Output: Regenerated materials

[0287] Through the above steps, the user can quickly and efficiently generate, modify, and confirm business negotiation materials and promotion materials.

[0288] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0289] The present invention relates to a system for automatically creating and modifying business negotiation materials by combining a generative artificial intelligence and an emotion engine. This system has a function of analyzing the user's input data, automatically creating materials by the generative artificial intelligence, and further recognizing the user's emotional state to adjust the material content.

[0290] Specific Embodiments

[0291] User input

[0292] The user logs into the terminal and begins creating the sales presentation materials. The user enters the requirements for the sales presentation materials (purpose, target customer, features, desired layout, etc.) into a dedicated input form. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, the features are high performance and low price, and the layout should be simple."

[0293] Utilizing the Emotion Engine

[0294] The device analyzes the user's emotions in real time through the camera and microphone while the user is inputting data. The emotion engine analyzes data such as changes in facial expressions and tone of voice to recognize the user's emotional state. For example, it collects different emotional data depending on whether the user is excited or calm.

[0295] Data transmission on the device

[0296] The device combines user input data and sentiment data, converts it to JSON format, and sends it to the server. This transmission is done via an HTTP POST request, and the necessary data is passed to the server.

[0297] Server-based data analysis and prompt generation

[0298] The server parses the received JSON data. Based on the analysis results, it generates a prompt to send to the generative artificial intelligence. This prompt includes the user's requests and sentiment data. For example, it might generate text such as, "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. The user is excited, so please make the tone of the document cheerful."

[0299] Initial document creation using generative artificial intelligence

[0300] The generative artificial intelligence generates initial materials based on the prompts received from the server. The generated materials are sent back to the server. The generated materials reflect the tone and content according to the user's emotional state, considering the data of the emotion engine. For example, documents like the following are generated.

[0301] 1. Introduction of New Product X

[0302] 1.1. High Performance

[0303] 1.2. Low Price

[0304] 1.3. Great improvements can be expected by using this innovative product!

[0305] 2. Points of the Proposal

[0306] 2.1. A solution suitable for a certain company

[0307] Data Transmission by the Server

[0308] The server sends the initial materials received from the generative artificial intelligence to the terminal. The terminal displays the materials to the user so that the user can view them.

[0309] User Feedback

[0310] The user checks the generated negotiation materials and enters requests for corrections or additions. Even in this process, the emotion engine monitors the user's emotions and collects data such as which parts the user shows strong interest in. For example, instructions such as "Please add an introduction paragraph to Chapter 1. Also, please emphasize the price information more." can be given.

[0311] Sending Additional Requests on the Terminal

[0312] The terminal converts the user's correction instructions and emotion data into JSON-formatted data and sends them to the server again as an HTTP POST request.

[0313] Server-based re-analysis of data and prompt generation

[0314] The server then analyzes the user's feedback and sentiment data it receives again and generates a new prompt. For example, it might generate a prompt such as, "Add an introductory paragraph to Chapter 1 of the new product X introduction document. Write it in a tone that strongly emphasizes the pricing information."

[0315] Regeneration by generative artificial intelligence

[0316] The generative artificial intelligence regenerates the document based on new prompts received from the server. It then sends the revised document back to the server. This revised document incorporates user feedback and sentiment data, such as highlighting price information.

[0317] Server-based transmission of revised documents

[0318] The server sends the regenerated document to the terminal and displays it to the user. The user can review the corrected document again and provide further correction instructions if necessary.

[0319] User's final confirmation

[0320] The user performs a final review, and once the sales materials are satisfactory, they are used in the sales negotiation. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the materials are aligned with the user's intentions and emotions.

[0321] As described above, the system of the present invention, by combining generative artificial intelligence and an emotion engine, can efficiently and accurately create and modify business negotiation materials and reflect the user's emotional state.

[0322] The following describes the processing flow.

[0323] Step 1:

[0324] The user logs into the terminal and begins creating the sales presentation materials. The user enters the requirements for the sales presentation materials (purpose, target customer, features, desired layout, etc.) into a dedicated input form. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, the features are high performance and low price, and the layout should be simple."

[0325] Step 2:

[0326] The emotion engine uses the camera and microphone built into the device to analyze the user's emotions in real time. It collects data such as changes in facial expressions and tone of voice to recognize the user's emotional state. For example, if the user is talking happily, the emotion will be recognized as "joy."

[0327] Step 3:

[0328] The device combines user input data and sentiment data, converts it to JSON format, and sends it to the server via an HTTP POST request. The transmitted data includes the purpose of the deal, target customers, characteristics, desired layout, and sentiment data.

[0329] Step 4:

[0330] The server analyzes the JSON data received from the terminal. Based on data such as the purpose and characteristics of the business negotiation, as well as user sentiment data, it generates prompts to send to the generative artificial intelligence. For example, a prompt such as "Please create an introductory document for new product X. The target customer is a certain company, and its features are high performance and low price. The user seems to be enjoying themselves, so please make the tone of the document cheerful." might be generated.

[0331] Step 5:

[0332] The generative artificial intelligence generates initial sales materials based on prompts received from the server. At this stage, the tone and content of the materials are adjusted considering the user's emotional data. The generated materials are sent back to the server. For example, the following document is generated:

[0333] 1. Introduction of New Product X

[0334] 1.1. High performance

[0335] 1.2. Low price

[0336] 1.3. This innovative product will enrich your life even further!

[0337] 2. Key points of the proposal

[0338] 2.1. A suitable solution for a particular company

[0339] Step 6:

[0340] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays the data to the user, allowing the user to review it.

[0341] Step 7:

[0342] The user reviews the displayed sales materials and enters requests for revisions or additions. If revision requests are made, the device uses the emotion engine again to analyze the user's emotions and acquire emotion data. For example, a user might submit a revision request such as, "Please add an introductory sentence to Chapter 1. Also, please emphasize the pricing information more."

[0343] Step 8:

[0344] The device converts the user's correction instructions and sentiment data into JSON format and sends them to the server again via an HTTP POST request.

[0345] Step 9:

[0346] The server analyzes the feedback and sentiment data it receives and generates new prompts. For example, it might generate a prompt such as, "Add an introductory sentence to Chapter 1 of the new product X introduction document. Write it in a tone that emphasizes the pricing information."

[0347] Step 10:

[0348] The generative artificial intelligence regenerates the material based on the new prompt received from the server. At this stage, the re-feedback sentiment data is also taken into consideration. The revised material is sent back to the server. For example, the following revised material is generated:

[0349] 1. Introduction of New Product X

[0350] 1.1. High performance

[0351] 1.2. Low price

[0352] 1.3. This innovative product will enrich your life even further!

[0353] 1.4. Implementing XYZ products offers an opportunity to significantly improve your business.

[0354] 2. Key points of the proposal

[0355] 2.1. A suitable solution for a particular company

[0356] 2.2. Special pricing offer

[0357] Step 11:

[0358] The server sends the regenerated document to the terminal and displays it to the user. The user can review the corrected document again and provide further correction instructions if necessary.

[0359] Step 12:

[0360] Once the user has made a final review and is satisfied with the completed document, it is used in the sales negotiation. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the document always align with the user's intentions and emotions.

[0361] The above outlines the specific processing flow in a sales negotiation document creation system that combines generative artificial intelligence and an emotion engine.

[0362] (Example 2)

[0363] 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".

[0364] Conventional document creation systems generate documents in a fixed pattern without considering user emotions, making it difficult to create documents that reflect user intentions and feelings. Furthermore, users must manually revise documents after creation, highlighting the need for more efficient workflows.

[0365] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for the user to log in to the terminal and input requests, means for analyzing the user's emotional state using a camera and microphone, means for transmitting the user's input data and emotional data from the terminal to the server in JSON format, means for the server to generate a prompt based on the user's requests and emotional data and transmit it to a generative artificial intelligence, means for the generative artificial intelligence to generate materials based on the prompt and send them back to the server, and means for the server to transmit the generated materials to the terminal and display them. This makes it possible to efficiently create materials that reflect the user's intentions and emotions.

[0366] A "user" refers to a person who uses the system to create documents.

[0367] A "terminal" refers to an electronic device used by a user to manipulate input data. Examples include personal computers and smartphones.

[0368] An "emotion engine" refers to software or hardware that uses cameras and microphones to analyze a user's emotional state.

[0369] "JSON format" is a data serialization format that refers to a method of storing and exchanging data based on JavaScript® object notation.

[0370] A "server" refers to a central control unit that receives user input data and emotion data, performs analysis, and sends prompts to the generative artificial intelligence.

[0371] A "prompt" refers to text data or commands used to instruct a generative artificial intelligence system to generate data.

[0372] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates materials based on prompts.

[0373] "Documents" refer to documents and presentation materials generated for purposes such as business negotiations and proposals.

[0374] "Feedback" refers to correction instructions or additional requests made by users regarding materials they have generated.

[0375] This invention relates to a system that automatically creates and modifies business negotiation materials by combining generative artificial intelligence and an emotion engine. This system analyzes user input data and emotion data, automatically creates materials using generative artificial intelligence, and further has the function of recognizing the user's emotional state and adjusting the content of the materials.

[0376] 1. User input

[0377] The user logs into the terminal and enters the requirements for the sales materials through a dedicated input form. The user enters these items using a keyboard and mouse. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, its features are high performance and low price, and the layout should be simple."

[0378] 2. Utilizing the Emotional Engine

[0379] The emotion engine analyzes the user's facial expressions and voice in real time through the camera and microphone connected to the device. This allows it to detect the user's emotional state. For example, it can distinguish between when the user is excited and when they are calm. The emotion engine analyzes this data and uses that information to inform subsequent processing.

[0380] 3. Data transmission from the device

[0381] The terminal combines the user's input data and sentiment data, converts it to JSON format, and sends it to the server. This transmission is done using an HTTP POST request. For example, the following JSON data is generated:

[0382] json

[0383] {

[0384] "subject": "Introduction document for new product X",

[0385] "target_customer": "A certain company",

[0386] "features": ["high performance", "low price"],

[0387] "layout": "simple",

[0388] "emotion": "excitement"

[0389] }

[0390] 4. Server-based data analysis and prompt generation

[0391] The server parses the received JSON data and generates a prompt to send to the generative artificial intelligence based on the user's requests and sentiment data. The generated prompt is text data containing the user's requests and sentiment data. For example, a prompt such as "Please create an introductory document for new product X. The target customer is a certain company, and its features are high performance and low price. The user is excited, so please make the tone of the document cheerful." might be generated.

[0392] 5. Initial document creation using generative artificial intelligence

[0393] The generative artificial intelligence generates initial material based on prompts received from the server. The generated material is then sent back to the server. The generated material reflects the user's emotional state in tone and content. For example, the following document might be generated:

[0394] 1. Introduction of New Product X

[0395] 1.1. High performance

[0396] 1.2. Low price

[0397] 1.3. Significant improvements can be expected by using this innovative product!

[0398] 2. Key points of the proposal

[0399] 2.1. A suitable solution for a particular company

[0400] 6. Sending documents via server

[0401] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays the data to the user, allowing the user to review it.

[0402] 7. User Feedback

[0403] The user reviews the generated sales materials and enters requests for revisions or additions. For example, they might give instructions such as, "Please add an introductory sentence to Chapter 1. Also, please emphasize the pricing information more." Throughout this process, the emotion engine monitors the user's emotions and collects data such as which parts they show the most interest in.

[0404] 8. Sending additional requests from the device

[0405] The terminal converts the user's correction instructions and sentiment data into JSON format and sends it back to the server as an HTTP POST request. The server parses the received data and generates a new prompt. For example, a prompt such as "Add an introductory sentence to Chapter 1 of the new product X introduction document. Write it in a tone that strongly emphasizes the pricing information." might be generated.

[0406] 9. Regeneration by generative artificial intelligence

[0407] The generative artificial intelligence regenerates the document based on the new prompt and returns the revised document to the server. This revised document incorporates user feedback and sentiment data.

[0408] 10. Server-based submission of revised documents

[0409] The server sends the regenerated document to the terminal for the user to review. The user can then review the corrected document again and provide further correction instructions if necessary.

[0410] 11. User's final confirmation

[0411] The user makes a final review, and only uses the materials in a sales negotiation once they are satisfactory. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the materials are aligned with the user's intentions and emotions.

[0412] The above is a specific embodiment of the system of the present invention. This system can analyze user input data and emotional data, and efficiently and accurately create and modify materials using generative artificial intelligence.

[0413] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0414] Step 1:

[0415] The user logs into the terminal and begins creating sales materials. They enter the requirements for the sales materials (purpose, target customer, features, desired layout, etc.) into the input form. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, its features are high performance and low price, and the layout should be simple." The input data includes purpose, target customer, features, desired layout, etc. The output is the requirements entered by the user.

[0416] Step 2:

[0417] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time. The emotion engine acquires changes in the user's facial expressions and voice tone as input data and recognizes the user's emotional state (excitement, calmness, etc.). As a result of the analysis, the user's emotional data is obtained. For example, if the user is excited, the emotion engine collects that data and outputs the state of excitement.

[0418] Step 3:

[0419] The terminal combines user input data and sentiment data and converts it into JSON format. The data processing involves combining requirements and sentiment data. The resulting JSON data includes the following format:

[0420] json

[0421] {

[0422] "subject": "Introduction document for new product X",

[0423] "target_customer": "A certain company",

[0424] "features": ["high performance", "low price"],

[0425] "layout": "simple",

[0426] "emotion": "excitement"

[0427] }

[0428] Step 4:

[0429] The terminal sends the converted JSON data to the server as an HTTP POST request. The input contains data in JSON format, and the output verifies that the data is sent correctly to the server.

[0430] Step 5:

[0431] The server parses the received JSON data and generates prompts to send to the generative artificial intelligence based on the user's requests and sentiment data. Data processing includes parsing the JSON data and converting it into prompts. For example, the generated prompts will be in the following text format:

[0432] "Please create a presentation document for our new product, X. The target customer is a specific company, and its key features are high performance and low price. The user is excited, so please make the document have a bright and positive tone."

[0433] Step 6:

[0434] The server sends the generated prompt to the generative AI, requesting it to generate initial data. The input includes the prompt, and the output is the initial data generated by the generative AI.

[0435] Step 7:

[0436] The generative artificial intelligence generates initial data based on prompts and sends it back to the server. For data processing, the generative AI performs text generation, and the generated data is obtained as output. For example, the following document is generated:

[0437] 1. Introduction of New Product X

[0438] 1.1. High performance

[0439] 1.2. Low price

[0440] 1.3. Significant improvements can be expected by using this innovative product!

[0441] 2. Key points of the proposal

[0442] 2.1. A suitable solution for a particular company

[0443] Step 8:

[0444] The server sends the initial data received from the generative artificial intelligence to the terminal and displays it to the user. The input includes the generated data, and the output confirms that the user can view the data.

[0445] Step 9:

[0446] The user reviews the generated document and enters requests for corrections or additions. For example, they might give instructions such as, "Add an introductory sentence to Chapter 1. Also, emphasize the pricing information more." The input includes user feedback, and the output is the feedback received.

[0447] Step 10:

[0448] The terminal converts the user's correction instructions and sentiment data into JSON format and sends it back to the server as an HTTP POST request. As part of the data processing, it is converted back to JSON format. The output is the JSON data sent to the server.

[0449] Step 11:

[0450] The server analyzes the re-received data and generates a new prompt. The input includes JSON data, and the output is a new prompt. For example, a prompt such as "Add an introductory sentence to Chapter 1 of the new product X introduction document. Write it in a tone that strongly emphasizes the pricing information." might be generated.

[0451] Step 12:

[0452] The generative artificial intelligence regenerates the document based on the new prompt and returns the revised document to the server. In terms of data calculation, the document is regenerated based on the revision instructions, and the revised document is obtained as output.

[0453] Step 13:

[0454] The server sends the regenerated document to the terminal for user review. It ensures that the input includes the corrected document and that the user can review the document again as output.

[0455] Step 14:

[0456] The user performs a final review, and once the document is satisfactory, it is used in the business negotiation. The input includes the final document, and the output is the finalized, reviewed document. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the document will be aligned with the user's intentions and emotions.

[0457] The above describes the specific flow of the program processing of this system and the actions performed at each step.

[0458] (Application Example 2)

[0459] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0460] Current automated document creation systems generate documents based on static user input data, but they struggle to respond to user emotional states or real-time feedback. Furthermore, because the tone of documents is not adjusted based on customer emotions during sales negotiations and sales activities, it is not possible to create documents that effectively appeal to customer interest and emotions. This limits the effectiveness of sales negotiations and sales activities.

[0461] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for automatically creating materials using generative artificial intelligence, means for modifying materials based on user feedback, means for transmitting user requests from a terminal to the server, means for transmitting prompts from the server to the generative artificial intelligence, means for returning and displaying the generated materials to the terminal, means for analyzing the user's emotional state using an emotion engine, means for adjusting the tone of the materials based on the analyzed emotional data, and means for collecting user input and emotional data via a smart device. This makes it possible to create materials and adjust the tone based on the user's emotional state and real-time feedback.

[0462] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates text and documents based on input data.

[0463] "Means for automatically creating documents" refers to a function that automatically generates sales materials and explanatory documents based on user requests.

[0464] "Means for modifying documents" refers to a function that modifies and updates already generated documents in response to user feedback.

[0465] A "terminal" refers to a device used by a user, such as a computer or smart device used for inputting information or receiving data.

[0466] A "server" is a computer system that processes and stores data on a network and responds to requests from other terminals.

[0467] A "prompt" is input text data used to instruct a generative artificial intelligence system to create or modify documents.

[0468] An "emotion engine" is a technology that analyzes and recognizes a user's emotional state in real time based on their facial expressions, tone of voice, and other factors.

[0469] "Emotional data" refers to data about the user's emotional state, analyzed by the emotion engine.

[0470] "Tone adjustment" refers to changing the content and wording of a document according to the user's emotional state.

[0471] A "smart device" is an internet-connected terminal equipped with a camera and microphone that can collect user input and emotional data.

[0472] This invention uses a system that combines generative artificial intelligence and an emotion engine to automatically create and modify sales materials, and to provide real-time emotional support. The specific system configuration consists of a smart device used by the user, a server, generative artificial intelligence, and an emotion engine.

[0473] Program generation

[0474] This system's program includes the following elements:

[0475] 1. Acquire customer input data and sentiment data using smart devices.

[0476] 2. Send data to the server and generate a prompt.

[0477] 3. Generative artificial intelligence generates and modifies documents based on prompts.

[0478] 4. The server sends the generated document back to the terminal and displays it on the terminal.

[0479] Hardware and software to use

[0480] hardware

[0481] Smart devices: These are internet-connected terminals equipped with cameras and microphones, such as smart glasses and smartphones, that collect user input and emotional data. Each device can analyze the user's facial expressions and voice tone in real time.

[0482] software

[0483] Emotion Engine: Uses the Affectiva API to analyze the user's emotional state and sends it to the server as emotion data.

[0484] Generative Artificial Intelligence: Uses the OpenAI GPT-3 model to generate and modify documents based on prompts.

[0485] Data processing and data calculation

[0486] Data collection

[0487] The device uses its camera and microphone to collect the user's facial expressions and voice tone, and analyzes them through an emotion engine (Affectiva API). The analyzed data is converted to JSON format and sent to the server as an HTTP POST request.

[0488] Prompt generation

[0489] The server analyzes the received data and generates prompts based on the user's input requests and sentiment data. For example, the following prompt message may be generated:

[0490] Please create a presentation document for our new product, X. The target customer is a specific company, and its key features are high performance and low price. Since the user is excited, please use a bright and positive tone in the document.

[0491] Document generation and correction

[0492] Generative artificial intelligence (OpenAI GPT-3) generates initial material based on prompts. This material reflects the user's emotional state (for example, a brighter tone if the user is excited). The generated material is sent back to the server, which then sends it to the terminal.

[0493] Display and Feedback

[0494] The terminal displays the generated document to the user. The user reviews the document and enters any necessary corrections or additional requests. This feedback is also analyzed through the emotion engine and sent back to the server. Based on the feedback and emotion data, the server generates a new prompt and requests the generative artificial intelligence to regenerate it.

[0495] Specific example

[0496] The user begins a business negotiation with a customer while wearing smart glasses in a store. If the customer shows interest in the new product X, the smart glasses' camera and microphone analyze the customer's facial expressions and voice in real time, and collect emotional data through the emotion engine (Affectiva API). When the user inputs, "I want to create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price, with a simple layout," the server generates the following prompt text and sends it to the generative artificial intelligence (OpenAI GPT-3).

[0497] Please create a presentation document for our new product, X. The target customer is a specific company, and its key features are high performance and low price. Since the user is excited, please use a bright and positive tone in the document.

[0498] The generated materials will contain specific descriptions of "high performance" and "low price," and will have a positive tone. These materials will be displayed on the user's smart glasses and presented to the customer.

[0499] In this way, this invention provides a system that combines an emotion engine and generative artificial intelligence to create and modify materials in accordance with the user's real-time emotional state.

[0500] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0501] Step 1:

[0502] The smart device, acting as the terminal, collects user input data and emotional data. The user inputs customer needs and requirements through smart glasses. Meanwhile, the terminal's camera and microphone analyze the user's facial expressions and voice tone in real time using an emotion engine (Affectiva API) to generate emotional data. In this case, the input data might be something like "I want to create an introductory document for new product X" or "high performance and low price," and the output is the analyzed emotional data (happiness, excitement, calmness, etc.).

[0503] Step 2:

[0504] The terminal collects input data and sentiment data, converts it to JSON format, and sends it to the server. The terminal uses an HTTP POST request to send the necessary data to the server. The input is the user's input data and sentiment data, and the output is the data converted to JSON format.

[0505] Step 3:

[0506] The server analyzes the received data and generates a prompt. The server analyzes the user's input requests and sentiment data to generate a specific prompt message to send to the generative artificial intelligence (OpenAI GPT-3). For example, the prompt message might be in the format of, "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. The user is excited, so please make the tone of the document cheerful." The input for this step is the received JSON data, and the output is the generated prompt message.

[0507] Step 4:

[0508] The server sends the generated prompt text to the generative artificial intelligence. The server sends the prompt text to OpenAI GPT-3 via an API request and requests the generation of data based on it. The input is the prompt text, and the output is the initial data returned by the generative artificial intelligence.

[0509] Step 5:

[0510] A generative artificial intelligence (AI) generates sales materials based on prompt messages received from the server and sends them back to the server. Here, the AI ​​considers the user's input data and sentiment data to create sales materials with an appropriate tone. The input is the prompt message, and the output is the generated initial material.

[0511] Step 6:

[0512] The server sends the generated initial data to the terminal. The server uses an HTTP response to send the data received from the generative artificial intelligence back to the terminal. The input is the generated initial data, and the output is the data sent to the terminal.

[0513] Step 7:

[0514] The terminal displays the received documents to the user. The generated sales materials are displayed on the smart device screen, and the user reviews them. The input is the generated documents, and the output is the displayed documents.

[0515] Step 8:

[0516] The user reviews the generated document and enters requests for corrections or additions. The user then uses a smart device to review the document and enters any necessary correction instructions. The input consists of the user's correction instructions, and the output is sentiment data that is then analyzed again by the sentiment engine.

[0517] Step 9:

[0518] The collected user correction instructions and sentiment data are converted to JSON format and sent to the server. The terminal converts the correction instructions, including the new input data, to JSON format and sends them to the server via an HTTP POST request. The input is correction instructions and sentiment data, and the output is data in JSON format.

[0519] Step 10:

[0520] The server parses the JSON data it receives again and generates a new prompt. Based on the user's correction instructions and sentiment data, the server creates a prompt sentence to request the generative artificial intelligence to regenerate. For example, the prompt sentence might be in the format of, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X. Please write it in a tone that strongly emphasizes the pricing information." The input for this step is the JSON data that is received again, and the output is the new prompt sentence.

[0521] Step 11:

[0522] The server sends a new prompt to the generative AI and retrieves the regenerated data. The generative AI then generates the data again based on the new prompt, and this is sent back to the server. The input is the new prompt, and the output is the regenerated data.

[0523] Step 12:

[0524] The server sends the regenerated document to the terminal, which displays it to the user. The user reviews the document again and makes a final confirmation. The input is the regenerated document, and the output is the final confirmed document.

[0525] The above describes the specific processing steps of the system for implementing this invention.

[0526] 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.

[0527] 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 (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.

[0528] 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.

[0529] [Second Embodiment]

[0530] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0531] 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.

[0532] 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).

[0533] 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.

[0534] 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.

[0535] 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).

[0536] 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.

[0537] 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.

[0538] 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.

[0539] 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.

[0540] 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.

[0541] 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".

[0542] This invention relates to a system that automatically creates sales materials using generative artificial intelligence and modifies and regenerates the materials based on user feedback. This system includes a terminal, a server, and the generative artificial intelligence as components.

[0543] Specific Embodiments

[0544] User input

[0545] The user logs into the terminal and begins creating sales materials. The user enters the necessary information for the sales materials into a dedicated input form. For example, when creating a presentation document for a new product, the user would enter items such as "Introduction to New Product X," "Target Customer: A Certain Company," "Features: High Performance, Low Price," and "Layout: Simple" into the input form.

[0546] Data transmission on the device

[0547] The terminal collects data entered by the user and sends it to the server. This transmission is done via an HTTP POST request, and the data is delivered to the server in JSON format.

[0548] Server-based data analysis and prompt generation

[0549] The server parses the received JSON data. As a result of this analysis, prompts are generated to instruct the generative artificial intelligence. For example, text such as "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. Please keep the layout simple." might be generated.

[0550] Initial document creation using generative artificial intelligence

[0551] The server sends the generated prompt to the generative artificial intelligence. The generative AI generates initial documents based on this prompt. The generated documents are sent back to the server as an initial version of the sales negotiation materials. For example, a document like the following is generated:

[0552] 1. Introduction of New Product X

[0553] 1.1. High performance

[0554] 1.2. Low price

[0555] 2. Key points of the proposal

[0556] 2.1. A suitable solution for a particular company

[0557] Sending documents via server

[0558] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays this data to the user, allowing the user to review it.

[0559] User feedback

[0560] The user reviews the generated sales materials and enters any requests for revisions or additions. For example, a user might submit a revision request such as, "Please add an introductory paragraph to Chapter 1."

[0561] Sending additional requests from the device

[0562] The terminal resends the user's correction instructions to the server. This transmission is also done via an HTTP POST request, and the data is again sent to the server in JSON format.

[0563] Server-based re-analysis of data and prompt generation

[0564] The server analyzes the received feedback again and generates a new prompt. For example, it might generate a prompt such as, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X."

[0565] Regeneration by generative artificial intelligence

[0566] The server sends a new prompt to the generative artificial intelligence. Based on this prompt, the generative AI regenerates the sales proposal document and sends the revised document back to the server. For example, a document with an introductory sentence added to Chapter 1 is generated.

[0567] Server-based transmission of revised documents

[0568] The server sends the revised document to the terminal and displays it to the user. The user can review the regenerated document and make further corrections as needed.

[0569] User's final confirmation

[0570] The user makes a final review, and once they are satisfied with the sales materials, they use them in the sales negotiation.

[0571] As described above, the system of the present invention supports the efficient creation of business negotiation materials by collecting user input and automatically generating and modifying materials using generative artificial intelligence.

[0572] The following describes the processing flow.

[0573] Step 1:

[0574] The user logs into the terminal and begins creating the sales presentation materials. The user enters the requirements for the sales presentation materials (purpose, target customers, features, desired layout, etc.) into a dedicated input form.

[0575] Step 2:

[0576] The terminal converts the data entered by the user into JSON format and sends it to the server via an HTTP POST request.

[0577] Step 3:

[0578] The server analyzes the JSON data received from the terminal. Based on the analysis results, it generates prompts to send to the generative artificial intelligence.

[0579] Step 4:

[0580] The generative artificial intelligence generates initial sales materials based on prompts received from the server. The generated materials are then sent back to the server.

[0581] Step 5:

[0582] The server sends the initial data received from the generative artificial intelligence to the user's terminal. The terminal displays the data to the user, allowing them to review it.

[0583] Step 6:

[0584] The user reviews the displayed sales materials and enters requests for corrections or additions. For example, they might enter instructions such as, "Please add an introductory paragraph to Chapter 1," into the terminal.

[0585] Step 7:

[0586] The terminal converts the user's correction instructions into JSON data and sends it back to the server as an HTTP POST request.

[0587] Step 8:

[0588] The server analyzes the user feedback it receives again and generates a new prompt. For example, it might generate a prompt such as, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X."

[0589] Step 9:

[0590] The generative artificial intelligence regenerates the document based on the new prompt received from the server. The revised document is then sent back to the server.

[0591] Step 10:

[0592] The server sends the regenerated document to the user's terminal. The terminal displays the corrected document to the user, providing another opportunity for review.

[0593] Step 11:

[0594] The user reviews the regenerated document and provides further revision instructions as needed. This process is repeated until a satisfactory document is finalized.

[0595] Step 12:

[0596] The user reviews the final version of the sales proposal materials, and once completed, uses them in the sales negotiation.

[0597] The above outlines the specific processing flow in the sales negotiation document creation system.

[0598] (Example 1)

[0599] 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".

[0600] Creating sales materials requires users to expend a significant amount of time and effort. Furthermore, the process of incorporating revisions and additional requests to these materials is complex and time-consuming. This can reduce the efficiency of sales material creation and negatively impact the success rate of sales negotiations.

[0601] 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.

[0602] In this invention, the server includes means for transmitting user requests from a terminal, means for the server to analyze user requests and generate prompt messages for a generation AI model, and means for the generation AI model to automatically generate materials based on the received prompt messages. This enables the rapid and efficient creation of sales materials and easy modification based on user feedback.

[0603] "Terminal" refers to all devices used by users to create and modify sales materials and to communicate with the server.

[0604] A "server" refers to a computing system that has the function of analyzing requests received from users and generating prompt messages to send to the AI ​​model.

[0605] A "generative AI model" refers to artificial intelligence technology that automatically generates materials based on the received prompt text.

[0606] A "prompt" refers to a text-based instruction that provides guidance to a generative AI model regarding the content and format of the document.

[0607] "Documents" refers to documents containing various pieces of information used in business negotiations.

[0608] "Feedback" refers to the input information that users use to request corrections or additions after reviewing the generated materials.

[0609] "Revised document" refers to a document regenerated by the AI ​​model based on user feedback.

[0610] "Automatic generation" refers to the process in which a generation AI model creates documents based on prompt text without human intervention.

[0611] A "re-prompt" refers to a new prompt message generated based on corrections or additional instructions.

[0612] "Transmission" refers to the process of moving data from a terminal to a server, or from a server to a generated AI model.

[0613] This invention relates to a system that automatically creates sales materials using a generative AI model and modifies and regenerates the materials based on user feedback. This system includes components such as a terminal, a server, and a generative AI model.

[0614] Specific Embodiments

[0615] Hardware environment

[0616] Devices: PCs, tablets, smartphones, etc. Users access the system using these devices.

[0617] Server: Receives and analyzes data, generates prompt messages, and communicates with the AI ​​model. This could be a cloud server or an on-premises server.

[0618] Generative AI models: For example, OpenAI's GPT-3 or ChatGPT. They generate sales materials based on prompt messages generated by the server.

[0619] Software Environment

[0620] Server-side scripts: These use programming languages ​​such as Python and Java to parse user requests and generate prompt messages.

[0621] HTTP Requests: Used for sending data between the terminal and the server, and between the server and the generated AI model. Requests use HTTP POST requests.

[0622] User input

[0623] The user logs into the terminal and begins creating sales materials. The user enters the necessary information into a dedicated input form. For example, when creating a presentation document for a new product, the user would enter information such as: "Introduction to New Product X," "Target Customer: A Certain Company," "Features: High Performance, Low Price," and "Layout: Simple."

[0624] Data transmission on the device

[0625] The terminal collects data entered by the user and sends it to the server. This transmission is done via an HTTP POST request, and the data is delivered to the server in JSON format.

[0626] Server-based data analysis and prompt generation

[0627] The server parses the received JSON data and generates prompt messages to instruct the AI ​​model based on the results of this analysis. For example, it might generate text such as, "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. Please keep the layout simple."

[0628] Initial document creation using a generative AI model

[0629] Based on the generated prompt text, the AI ​​model generates an initial version of the sales presentation materials. These presentation materials will be in the following format:

[0630] 1. Introduction of New Product X

[0631] 1.1. High performance

[0632] 1.2. Low price

[0633] 2. Key points of the proposal

[0634] 2.1. A suitable solution for a particular company

[0635] The generated documents are sent to the terminal via the server.

[0636] User feedback and corrections

[0637] The user reviews the generated sales presentation materials and enters requests for revisions or additions. For example, they might instruct, "Please add an introductory paragraph to Chapter 1." The terminal resends the user's feedback to the server, which analyzes the feedback and generates a new prompt. The generation AI model regenerates the sales presentation materials based on this new prompt, and this revised material is sent back to the terminal via the server.

[0638] By repeating this process, users can efficiently create satisfactory sales materials. Furthermore, this system allows for repeated revision and improvement of materials generated based on user input and feedback, thereby improving the quality of materials used in sales negotiations.

[0639] As described above, the system of the present invention significantly improves the efficiency of creating sales materials by automating the sales material creation process using a generative AI model and enabling rapid revisions based on user feedback.

[0640] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0641] Step 1:

[0642] Users log in to the system using a terminal.

[0643] Specific steps: The user enters their user ID and password and clicks the "Login" button. The system sends the authentication information to the server, and if authentication is successful, the next screen is displayed.

[0644] Input: User ID, Password

[0645] Output: User authentication result, next operation screen

[0646] Step 2:

[0647] The user enters the necessary information into the input form to begin creating the sales presentation materials.

[0648] Specific operation: The user enters information such as "Introduction to new product X," "Target customer: A certain company," "Features: High performance, low price," and "Layout: Simple," and then clicks the "Submit" button.

[0649] Input: Each item in the sales presentation materials (new product name, target customers, features, layout, etc.)

[0650] Output: Request to send input information

[0651] Step 3:

[0652] The terminal sends the information entered by the user to the server via an HTTP POST request.

[0653] Specific operation: The terminal converts the input data into JSON format and sends it to the server.

[0654] Input: Information from sales materials entered by the user.

[0655] Output: Send data in JSON format

[0656] Step 4:

[0657] The server parses the received JSON data and generates prompt messages to send to the AI ​​model.

[0658] Specific operation: The server uses a Python script to parse the JSON data and generates a prompt message that reads, "Create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. The layout should be simple."

[0659] Input: Information from business negotiation materials sent in JSON format

[0660] Output: Prompt message to send to the generated AI model

[0661] Step 5:

[0662] The server sends the generated prompt message to the AI ​​model, requesting it to generate initial data.

[0663] Specific operation: The server sends a prompt message to the AI ​​generation model via an HTTP POST request. The AI ​​generation model generates sales materials based on the prompt message and sends them back to the server.

[0664] Input: Prompt text for the generated AI model

[0665] Output: Initial data generated by a generative AI model

[0666] Step 6:

[0667] The server sends the generated initial data to the terminal and displays it to the user.

[0668] Specific operation: The server uses an HTTP POST request to send the generated data to the terminal in JSON format. The terminal displays the received data to the user.

[0669] Input: Initial data returned from the generated AI model

[0670] Output: Display of initial materials in a format viewable by the user.

[0671] Step 7:

[0672] The user reviews the generated document and enters any necessary corrections or additional requests.

[0673] Specific actions: The user reviews the document, enters specific feedback such as "Please add an introductory paragraph to Chapter 1," and clicks the "Submit" button.

[0674] Input: User requests for modifications or additions

[0675] Output: Request to send correction instructions

[0676] Step 8:

[0677] The terminal then sends the user's correction instructions back to the server.

[0678] Specific operation: The terminal converts the modification request into JSON format and sends it to the server via an HTTP POST request.

[0679] Input: User requests for modifications or additions

[0680] Output: Sending correction instructions in JSON format

[0681] Step 9:

[0682] The server analyzes the received correction instructions and generates a new prompt message.

[0683] Specific operation: The server uses a Python script to analyze the feedback data and generates a new prompt message: "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X."

[0684] Input: Correction instructions in JSON format

[0685] Output: New prompt message to send to the generated AI model

[0686] Step 10:

[0687] The server sends a new prompt message to the AI ​​model, requesting it to generate the revised document.

[0688] Specific operation: The server sends a prompt message to the generating AI model via an HTTP POST request. The generating AI model generates revised data based on the prompt message and sends it back to the server.

[0689] Input: New prompt message to the generated AI model

[0690] Output: Revised document generated by an AI model

[0691] Step 11:

[0692] The server sends the revised document to the terminal and displays it to the user.

[0693] Specific operation: The server sends the revised document to the terminal in JSON format using an HTTP POST request. The terminal displays the received document to the user.

[0694] Input: Revised data returned from the generated AI model

[0695] Output: Display of the revised document in a format viewable by the user.

[0696] Step 12:

[0697] The user performs a final review, and once the materials meet their quality standards, they are used in business negotiations.

[0698] Specific actions: The user reviews the document one last time and, if necessary, submits a revision request, or reviews the document one last time and downloads or prints it.

[0699] Input: User's final confirmation

[0700] Output: Finalization of documents for use in business negotiations.

[0701] (Application Example 1)

[0702] 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."

[0703] In modern business negotiations and customer service at retail stores, it is crucial to be able to quickly prepare promotional and explanatory materials. However, creating these manually is time-consuming and inefficient. Furthermore, quickly gathering customer feedback is not easy. To solve these problems and improve customer satisfaction, there is a need for an automated material generation system utilizing generative artificial intelligence.

[0704] 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.

[0705] In this invention, the server includes means for automatically creating materials using generative artificial intelligence, means for modifying materials based on user feedback, means for transmitting user requests from a terminal to the server, means for generating and updating sales materials and promotional materials via a smart device, and means for incorporating customer feedback and regenerating materials. This makes it possible to provide sales materials and promotional materials quickly and efficiently, and to immediately reflect customer feedback.

[0706] "Generative artificial intelligence" refers to artificial intelligence that has the ability to generate new information or content based on input data.

[0707] "Methods for automatically creating documents" refers to a system that automatically creates documents using generative artificial intelligence based on user requests.

[0708] "Means of modifying materials based on user feedback" refers to methods of modifying existing materials using generative artificial intelligence to reflect user opinions and requests.

[0709] "Means of sending user requests from a terminal to a server" refers to a function that allows a user to send instructions to a server from their device for creating or modifying business negotiation materials.

[0710] "Means of sending prompts from a server to a generative artificial intelligence" refers to a method by which a server analyzes the user's request and sends instructions (prompts) based on that analysis to the generative artificial intelligence.

[0711] "A means of returning and displaying generated materials on a terminal" refers to a mechanism in which a server sends materials created by a generative artificial intelligence to a user's terminal, and the user can view and display them.

[0712] "Means for generating and updating sales materials and promotional materials via smart devices" refers to methods for generating sales materials and promotional materials using devices such as smart glasses and smartphones, and updating them as needed.

[0713] "Methods for incorporating customer feedback and regenerating materials" refers to a system that collects opinions and requests provided by customers and then regenerates materials with necessary updates based on that feedback.

[0714] A "smart device" refers to a glasses-type device or mobile phone equipped with internet connectivity and application execution capabilities.

[0715] This invention provides a system that automatically creates sales materials and promotional materials using generative artificial intelligence, and modifies and regenerates the materials based on user feedback. This system consists of a terminal, a server, and generative artificial intelligence.

[0716] System Configuration

[0717] terminal

[0718] The terminal utilizes smart devices (such as smart glasses or smartphones). Users use this terminal to input requests for the creation of business negotiation materials, and to review and modify the generated materials.

[0719] server

[0720] The server receives request data sent from the user via the terminal, analyzes it, and sends prompts to the generative artificial intelligence. The main functions of the server are as follows:

[0721] Analyze user requests and generate prompts.

[0722] A prompt is sent to the generative artificial intelligence, and the generated material is received.

[0723] The received documents are sent back to the user's device.

[0724] Generative artificial intelligence

[0725] Generative artificial intelligence generates sales materials and promotional materials based on prompts received from the server. The generated materials are sent back to the server and displayed again on the user's device.

[0726] Program Processing Description

[0727] Hardware:

[0728] Smart glasses (e.g., Google Glass)

[0729] Smartphones (e.g., iPhone, Android devices)

[0730] Server Computer

[0731] software:

[0732] Flask (a Python-based web framework)

[0733] requests (a Python module for sending HTTP requests)

[0734] APIs for generative AI models (e.g., OpenAI GPT, etc.)

[0735] The server analyzes user requests sent from smart devices and generates prompts for generative artificial intelligence. The generative AI model then creates prompt statements that generate materials. For example, a prompt might read: "A customer is requesting detailed information about the special features of new product Y. New product Y is highly durable and energy-efficient. Please create promotional materials that explain this in a way that does not require specialized knowledge."

[0736] This prompt is sent to a generative artificial intelligence system, the server receives the generated material, and sends it back to the terminal for display. The user can review the generated material, provide corrections or additional feedback, the server analyzes it again, and sends it to the generative AI model as a new prompt.

[0737] Specific example:

[0738] One scenario envisioned is that when a customer asks for details about a new product in a store, staff use smart glasses to instantly generate information and display it on a screen.

[0739] Customer question: "I would like to know more details about the special features of product X."

[0740] Staff operation: The staff member voice-inputs the following into the smart glasses: "Please generate documentation about the special features of the new product X."

[0741] System processing: Generates a prompt message, sends it to the generation AI model, and displays the generated document on the terminal.

[0742] This allows users to immediately provide materials to respond to customers and to quickly gather customer feedback.

[0743] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0744] Step 1:

[0745] User request input

[0746] Users use their devices (smart glasses or smartphones) to input requests for the creation of sales materials or promotional materials. For example, they might use the voice input function of their smart glasses to input a request such as, "Please create an introductory document for new product X." This input data is processed within the device and sent to the server.

[0747] Input: Request for creation of sales materials (e.g., introductory materials for new product X)

[0748] Output: Requested data

[0749] Step 2:

[0750] Sending request data

[0751] The terminal sends user input data to the server. The data is sent to the server in JSON format as an HTTP POST request. This process ensures the data is delivered to the server and ready for analysis.

[0752] Input: Request data

[0753] Output: HTTP POST request to the server

[0754] Step 3:

[0755] Server-based request data analysis

[0756] The server analyzes the received request data and creates a prompt to send to the generative artificial intelligence. For example, if a user requests, "Please create an introductory document for new product X," the server will generate a prompt such as, "Please create an introductory document for new product X. The target customers are general consumers. Its features are high performance and low price."

[0757] Input: Request data in an HTTP POST request

[0758] Output: Prompts for generative artificial intelligence

[0759] Step 4:

[0760] Send a prompt

[0761] The server sends the generated prompt to the generative AI. It sends the prompt as an API request to the generative AI, requesting the generation of data. At this time, an HTTP POST request is made to the generative AI's API endpoint.

[0762] Input: Prompt

[0763] Output: API request to a generative artificial intelligence system

[0764] Step 5:

[0765] Data generation

[0766] Generative artificial intelligence generates sales materials and promotional materials based on prompts. These generated materials are then sent back to the server. For example, a document containing sections such as "Introduction to New Product X," "High Performance," and "Low Price" is generated.

[0767] Input: Prompt

[0768] Output: Generated document

[0769] Step 6:

[0770] Return of generated documents

[0771] The server returns the data received from the generative artificial intelligence to the terminal. The data is sent as a response to an HTTP POST request and displayed on the terminal. The user can visually confirm the generated data.

[0772] Input: Generated document

[0773] Output: HTTP POST response to the terminal

[0774] Step 7:

[0775] Displaying documents and entering feedback

[0776] The user reviews the generated document on their device and provides feedback as needed. For example, they might enter a correction request such as, "Please add an introductory sentence to Chapter 1." This feedback data is then sent back to the server.

[0777] Input: Generated materials and feedback

[0778] Output: Feedback data

[0779] Step 8:

[0780] Sending feedback data

[0781] The device resends the user's feedback data to the server. The data is sent again to the server in JSON format as an HTTP POST request, and is ready for regeneration.

[0782] Input: Feedback data

[0783] Output: HTTP POST request to the server

[0784] Step 9:

[0785] Regeneration prompt generation

[0786] The server analyzes the feedback data and generates a new prompt. For example, it might generate a new prompt such as, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X," and send it to the generative artificial intelligence.

[0787] Input: Feedback data in an HTTP POST request

[0788] Output: New prompt

[0789] Step 10:

[0790] Regeneration and final transmission of documents

[0791] The server sends a new prompt to the generative artificial intelligence, which generates a revised version of the document. The generated document is sent back to the server and then transmitted to the terminal. The user then makes a final review of the regenerated document and uses it for business negotiations or promotions.

[0792] Input: New prompt

[0793] Output: Regenerated materials

[0794] Through the steps outlined above, users can quickly and efficiently generate, modify, and review sales materials and promotional materials.

[0795] 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.

[0796] This invention relates to a system that combines generative artificial intelligence and an emotion engine to automatically create and modify business negotiation materials. This system analyzes user input data, automatically creates materials using generative artificial intelligence, and further has the function of recognizing the user's emotional state and adjusting the content of the materials.

[0797] Specific Embodiments

[0798] User input

[0799] The user logs into the terminal and begins creating the sales presentation materials. The user enters the requirements for the sales presentation materials (purpose, target customer, features, desired layout, etc.) into a dedicated input form. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, the features are high performance and low price, and the layout should be simple."

[0800] Utilizing the Emotion Engine

[0801] The device analyzes the user's emotions in real time through the camera and microphone while the user is inputting data. The emotion engine analyzes data such as changes in facial expressions and tone of voice to recognize the user's emotional state. For example, it collects different emotional data depending on whether the user is excited or calm.

[0802] Data transmission on the device

[0803] The device combines user input data and sentiment data, converts it to JSON format, and sends it to the server. This transmission is done via an HTTP POST request, and the necessary data is passed to the server.

[0804] Server-based data analysis and prompt generation

[0805] The server parses the received JSON data. Based on the analysis results, it generates a prompt to send to the generative artificial intelligence. This prompt includes the user's requests and sentiment data. For example, it might generate text such as, "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. The user is excited, so please make the tone of the document cheerful."

[0806] Initial document creation using generative artificial intelligence

[0807] The generative artificial intelligence generates initial materials based on prompts received from the server. The generated materials are then sent back to the server. The generated materials reflect the tone and content of the user's emotional state, taking into account data from the emotion engine. For example, a document like the following might be generated:

[0808] 1. Introduction of New Product X

[0809] 1.1. High performance

[0810] 1.2. Low price

[0811] 1.3. Significant improvements can be expected by using this innovative product!

[0812] 2. Key points of the proposal

[0813] 2.1. A suitable solution for a particular company

[0814] Sending documents via server

[0815] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays the data to the user, allowing the user to review it.

[0816] User feedback

[0817] The user reviews the generated sales materials and enters requests for revisions or additions. Throughout this process, the sentiment engine monitors the user's emotions and collects data such as which parts the user shows the most interest in. For example, the user can give instructions such as, "Please add an introductory sentence to Chapter 1. Also, please emphasize the pricing information more."

[0818] Sending additional requests from the device

[0819] The device converts the user's correction instructions and sentiment data into JSON format and sends it back to the server as an HTTP POST request.

[0820] Server-based re-analysis of data and prompt generation

[0821] The server then analyzes the user's feedback and sentiment data it receives again and generates a new prompt. For example, it might generate a prompt such as, "Add an introductory paragraph to Chapter 1 of the new product X introduction document. Write it in a tone that strongly emphasizes the pricing information."

[0822] Regeneration by generative artificial intelligence

[0823] The generative artificial intelligence regenerates the document based on new prompts received from the server. It then sends the revised document back to the server. This revised document incorporates user feedback and sentiment data, such as highlighting price information.

[0824] Server-based transmission of revised documents

[0825] The server sends the regenerated document to the terminal and displays it to the user. The user can review the corrected document again and provide further correction instructions if necessary.

[0826] User's final confirmation

[0827] The user performs a final review, and once the sales materials are satisfactory, they are used in the sales negotiation. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the materials are aligned with the user's intentions and emotions.

[0828] As described above, the system of the present invention, by combining generative artificial intelligence and an emotion engine, can efficiently and accurately create and modify business negotiation materials and reflect the user's emotional state.

[0829] The following describes the processing flow.

[0830] Step 1:

[0831] The user logs into the terminal and begins creating the sales presentation materials. The user enters the requirements for the sales presentation materials (purpose, target customer, features, desired layout, etc.) into a dedicated input form. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, the features are high performance and low price, and the layout should be simple."

[0832] Step 2:

[0833] The emotion engine uses the camera and microphone built into the device to analyze the user's emotions in real time. It collects data such as changes in facial expressions and tone of voice to recognize the user's emotional state. For example, if the user is talking happily, the emotion will be recognized as "joy."

[0834] Step 3:

[0835] The device combines user input data and sentiment data, converts it to JSON format, and sends it to the server via an HTTP POST request. The transmitted data includes the purpose of the deal, target customers, characteristics, desired layout, and sentiment data.

[0836] Step 4:

[0837] The server analyzes the JSON data received from the terminal. Based on data such as the purpose and characteristics of the business negotiation, as well as user sentiment data, it generates prompts to send to the generative artificial intelligence. For example, a prompt such as "Please create an introductory document for new product X. The target customer is a certain company, and its features are high performance and low price. The user seems to be enjoying themselves, so please make the tone of the document cheerful." might be generated.

[0838] Step 5:

[0839] The generative artificial intelligence generates initial sales materials based on prompts received from the server. At this stage, the tone and content of the materials are adjusted considering the user's emotional data. The generated materials are sent back to the server. For example, the following document is generated:

[0840] 1. Introduction of New Product X

[0841] 1.1. High performance

[0842] 1.2. Low price

[0843] 1.3. This innovative product will enrich your life even further!

[0844] 2. Key points of the proposal

[0845] 2.1. A suitable solution for a particular company

[0846] Step 6:

[0847] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays the data to the user, allowing the user to review it.

[0848] Step 7:

[0849] The user reviews the displayed sales materials and enters requests for revisions or additions. If revision requests are made, the device uses the emotion engine again to analyze the user's emotions and acquire emotion data. For example, a user might submit a revision request such as, "Please add an introductory sentence to Chapter 1. Also, please emphasize the pricing information more."

[0850] Step 8:

[0851] The device converts the user's correction instructions and sentiment data into JSON format and sends them to the server again via an HTTP POST request.

[0852] Step 9:

[0853] The server analyzes the feedback and sentiment data it receives and generates new prompts. For example, it might generate a prompt such as, "Add an introductory sentence to Chapter 1 of the new product X introduction document. Write it in a tone that emphasizes the pricing information."

[0854] Step 10:

[0855] The generative artificial intelligence regenerates the material based on the new prompt received from the server. At this stage, the re-feedback sentiment data is also taken into consideration. The revised material is sent back to the server. For example, the following revised material is generated:

[0856] 1. Introduction of New Product X

[0857] 1.1. High performance

[0858] 1.2. Low price

[0859] 1.3. This innovative product will enrich your life even further!

[0860] 1.4. Implementing XYZ products offers an opportunity to significantly improve your business.

[0861] 2. Key points of the proposal

[0862] 2.1. A suitable solution for a particular company

[0863] 2.2. Special pricing offer

[0864] Step 11:

[0865] The server sends the regenerated document to the terminal and displays it to the user. The user can review the corrected document again and provide further correction instructions if necessary.

[0866] Step 12:

[0867] Once the user has made a final review and is satisfied with the completed document, it is used in the sales negotiation. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the document always align with the user's intentions and emotions.

[0868] The above outlines the specific processing flow in a sales negotiation document creation system that combines generative artificial intelligence and an emotion engine.

[0869] (Example 2)

[0870] 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".

[0871] Conventional document creation systems generate documents in a fixed pattern without considering user emotions, making it difficult to create documents that reflect user intentions and feelings. Furthermore, users must manually revise documents after creation, highlighting the need for more efficient workflows.

[0872] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for the user to log in to the terminal and input requests, means for analyzing the user's emotional state using a camera and microphone, means for transmitting the user's input data and emotional data from the terminal to the server in JSON format, means for the server to generate a prompt based on the user's requests and emotional data and transmit it to a generative artificial intelligence, means for the generative artificial intelligence to generate materials based on the prompt and send them back to the server, and means for the server to transmit the generated materials to the terminal and display them. This makes it possible to efficiently create materials that reflect the user's intentions and emotions.

[0873] A "user" refers to a person who uses the system to create documents.

[0874] A "terminal" refers to an electronic device used by a user to manipulate input data. Examples include personal computers and smartphones.

[0875] An "emotion engine" refers to software or hardware that uses cameras and microphones to analyze a user's emotional state.

[0876] "JSON format" is a data serialization format that refers to a method of storing and exchanging data based on JavaScript object notation.

[0877] A "server" refers to a central control unit that receives user input data and emotion data, performs analysis, and sends prompts to the generative artificial intelligence.

[0878] A "prompt" refers to text data or commands used to instruct a generative artificial intelligence system to generate data.

[0879] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates materials based on prompts.

[0880] "Documents" refer to documents and presentation materials generated for purposes such as business negotiations and proposals.

[0881] "Feedback" refers to correction instructions or additional requests made by users regarding materials they have generated.

[0882] This invention relates to a system that automatically creates and modifies business negotiation materials by combining generative artificial intelligence and an emotion engine. This system analyzes user input data and emotion data, automatically creates materials using generative artificial intelligence, and further has the function of recognizing the user's emotional state and adjusting the content of the materials.

[0883] 1. User input

[0884] The user logs into the terminal and enters the requirements for the sales materials through a dedicated input form. The user enters these items using a keyboard and mouse. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, its features are high performance and low price, and the layout should be simple."

[0885] 2. Utilizing the Emotional Engine

[0886] The emotion engine analyzes the user's facial expressions and voice in real time through the camera and microphone connected to the device. This allows it to detect the user's emotional state. For example, it can distinguish between when the user is excited and when they are calm. The emotion engine analyzes this data and uses that information to inform subsequent processing.

[0887] 3. Data transmission from the device

[0888] The terminal combines the user's input data and sentiment data, converts it to JSON format, and sends it to the server. This transmission is done using an HTTP POST request. For example, the following JSON data is generated:

[0889] json

[0890] {

[0891] "subject": "Introduction document for new product X",

[0892] "target_customer": "A certain company",

[0893] "features": ["high performance", "low price"],

[0894] "layout": "simple",

[0895] "emotion": "excitement"

[0896] }

[0897] 4. Server-based data analysis and prompt generation

[0898] The server parses the received JSON data and generates a prompt to send to the generative artificial intelligence based on the user's requests and sentiment data. The generated prompt is text data containing the user's requests and sentiment data. For example, a prompt such as "Please create an introductory document for new product X. The target customer is a certain company, and its features are high performance and low price. The user is excited, so please make the tone of the document cheerful." might be generated.

[0899] 5. Initial document creation using generative artificial intelligence

[0900] The generative artificial intelligence generates initial material based on prompts received from the server. The generated material is then sent back to the server. The generated material reflects the user's emotional state in tone and content. For example, the following document might be generated:

[0901] 1. Introduction of New Product X

[0902] 1.1. High performance

[0903] 1.2. Low price

[0904] 1.3. Significant improvements can be expected by using this innovative product!

[0905] 2. Key points of the proposal

[0906] 2.1. A suitable solution for a particular company

[0907] 6. Sending documents via server

[0908] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays the data to the user, allowing the user to review it.

[0909] 7. User Feedback

[0910] The user reviews the generated sales materials and enters requests for revisions or additions. For example, they might give instructions such as, "Please add an introductory sentence to Chapter 1. Also, please emphasize the pricing information more." Throughout this process, the emotion engine monitors the user's emotions and collects data such as which parts they show the most interest in.

[0911] 8. Sending additional requests from the device

[0912] The terminal converts the user's correction instructions and sentiment data into JSON format and sends it back to the server as an HTTP POST request. The server parses the received data and generates a new prompt. For example, a prompt such as "Add an introductory sentence to Chapter 1 of the new product X introduction document. Write it in a tone that strongly emphasizes the pricing information." might be generated.

[0913] 9. Regeneration by generative artificial intelligence

[0914] The generative artificial intelligence regenerates the document based on the new prompt and returns the revised document to the server. This revised document incorporates user feedback and sentiment data.

[0915] 10. Server-based submission of revised documents

[0916] The server sends the regenerated document to the terminal for the user to review. The user can then review the corrected document again and provide further correction instructions if necessary.

[0917] 11. User's final confirmation

[0918] The user makes a final review, and only uses the materials in a sales negotiation once they are satisfactory. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the materials are aligned with the user's intentions and emotions.

[0919] The above is a specific embodiment of the system of the present invention. This system can analyze user input data and emotional data, and efficiently and accurately create and modify materials using generative artificial intelligence.

[0920] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0921] Step 1:

[0922] The user logs into the terminal and begins creating sales materials. They enter the requirements for the sales materials (purpose, target customer, features, desired layout, etc.) into the input form. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, its features are high performance and low price, and the layout should be simple." The input data includes purpose, target customer, features, desired layout, etc. The output is the requirements entered by the user.

[0923] Step 2:

[0924] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time. The emotion engine acquires changes in the user's facial expressions and voice tone as input data and recognizes the user's emotional state (excitement, calmness, etc.). As a result of the analysis, the user's emotional data is obtained. For example, if the user is excited, the emotion engine collects that data and outputs the state of excitement.

[0925] Step 3:

[0926] The terminal combines user input data and sentiment data and converts it into JSON format. The data processing involves combining requirements and sentiment data. The resulting JSON data includes the following format:

[0927] json

[0928] {

[0929] "subject": "Introduction document for new product X",

[0930] "target_customer": "A certain company",

[0931] "features": ["high performance", "low price"],

[0932] "layout": "simple",

[0933] "emotion": "excitement"

[0934] }

[0935] Step 4:

[0936] The terminal sends the converted JSON data to the server as an HTTP POST request. The input contains data in JSON format, and the output verifies that the data is sent correctly to the server.

[0937] Step 5:

[0938] The server parses the received JSON data and generates prompts to send to the generative artificial intelligence based on the user's requests and sentiment data. Data processing includes parsing the JSON data and converting it into prompts. For example, the generated prompts will be in the following text format:

[0939] "Please create a presentation document for our new product, X. The target customer is a specific company, and its key features are high performance and low price. The user is excited, so please make the document have a bright and positive tone."

[0940] Step 6:

[0941] The server sends the generated prompt to the generative AI, requesting it to generate initial data. The input includes the prompt, and the output is the initial data generated by the generative AI.

[0942] Step 7:

[0943] The generative artificial intelligence generates initial data based on prompts and sends it back to the server. For data processing, the generative AI performs text generation, and the generated data is obtained as output. For example, the following document is generated:

[0944] 1. Introduction of New Product X

[0945] 1.1. High performance

[0946] 1.2. Low price

[0947] 1.3. Significant improvements can be expected by using this innovative product!

[0948] 2. Key points of the proposal

[0949] 2.1. A suitable solution for a particular company

[0950] Step 8:

[0951] The server sends the initial data received from the generative artificial intelligence to the terminal and displays it to the user. The input includes the generated data, and the output confirms that the user can view the data.

[0952] Step 9:

[0953] The user reviews the generated document and enters requests for corrections or additions. For example, they might give instructions such as, "Add an introductory sentence to Chapter 1. Also, emphasize the pricing information more." The input includes user feedback, and the output is the feedback received.

[0954] Step 10:

[0955] The terminal converts the user's correction instructions and sentiment data into JSON format and sends it back to the server as an HTTP POST request. As part of the data processing, it is converted back to JSON format. The output is the JSON data sent to the server.

[0956] Step 11:

[0957] The server analyzes the re-received data and generates a new prompt. The input includes JSON data, and the output is a new prompt. For example, a prompt such as "Add an introductory sentence to Chapter 1 of the new product X introduction document. Write it in a tone that strongly emphasizes the pricing information." might be generated.

[0958] Step 12:

[0959] The generative artificial intelligence regenerates the document based on the new prompt and returns the revised document to the server. In terms of data calculation, the document is regenerated based on the revision instructions, and the revised document is obtained as output.

[0960] Step 13:

[0961] The server sends the regenerated document to the terminal for user review. It ensures that the input includes the corrected document and that the user can review the document again as output.

[0962] Step 14:

[0963] The user performs a final review, and once the document is satisfactory, it is used in the business negotiation. The input includes the final document, and the output is the finalized, reviewed document. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the document will be aligned with the user's intentions and emotions.

[0964] The above describes the specific flow of the program processing of this system and the actions performed at each step.

[0965] (Application Example 2)

[0966] 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."

[0967] Current automated document creation systems generate documents based on static user input data, but they struggle to respond to user emotional states or real-time feedback. Furthermore, because the tone of documents is not adjusted based on customer emotions during sales negotiations and sales activities, it is not possible to create documents that effectively appeal to customer interest and emotions. This limits the effectiveness of sales negotiations and sales activities.

[0968] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for automatically creating materials using generative artificial intelligence, means for modifying materials based on user feedback, means for transmitting user requests from a terminal to the server, means for transmitting prompts from the server to the generative artificial intelligence, means for returning and displaying the generated materials to the terminal, means for analyzing the user's emotional state using an emotion engine, means for adjusting the tone of the materials based on the analyzed emotional data, and means for collecting user input and emotional data via a smart device. This makes it possible to create materials and adjust the tone based on the user's emotional state and real-time feedback.

[0969] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates text and documents based on input data.

[0970] "Means for automatically creating documents" refers to a function that automatically generates sales materials and explanatory documents based on user requests.

[0971] "Means for modifying documents" refers to a function that modifies and updates already generated documents in response to user feedback.

[0972] A "terminal" refers to a device used by a user, such as a computer or smart device used for inputting information or receiving data.

[0973] A "server" is a computer system that processes and stores data on a network and responds to requests from other terminals.

[0974] A "prompt" is input text data used to instruct a generative artificial intelligence system to create or modify documents.

[0975] An "emotion engine" is a technology that analyzes and recognizes a user's emotional state in real time based on their facial expressions, tone of voice, and other factors.

[0976] "Emotional data" refers to data about the user's emotional state, analyzed by the emotion engine.

[0977] "Tone adjustment" refers to changing the content and wording of a document according to the user's emotional state.

[0978] A "smart device" is an internet-connected terminal equipped with a camera and microphone that can collect user input and emotional data.

[0979] This invention uses a system that combines generative artificial intelligence and an emotion engine to automatically create and modify sales materials, and to provide real-time emotional support. The specific system configuration consists of a smart device used by the user, a server, generative artificial intelligence, and an emotion engine.

[0980] Program generation

[0981] This system's program includes the following elements:

[0982] 1. Acquire customer input data and sentiment data using smart devices.

[0983] 2. Send data to the server and generate a prompt.

[0984] 3. Generative artificial intelligence generates and modifies documents based on prompts.

[0985] 4. The server sends the generated document back to the terminal and displays it on the terminal.

[0986] Hardware and software to use

[0987] hardware

[0988] Smart devices: These are internet-connected terminals equipped with cameras and microphones, such as smart glasses and smartphones, that collect user input and emotional data. Each device can analyze the user's facial expressions and voice tone in real time.

[0989] software

[0990] Emotion Engine: Uses the Affectiva API to analyze the user's emotional state and sends it to the server as emotion data.

[0991] Generative Artificial Intelligence: Uses the OpenAI GPT-3 model to generate and modify documents based on prompts.

[0992] Data processing and data calculation

[0993] Data collection

[0994] The device uses its camera and microphone to collect the user's facial expressions and voice tone, and analyzes them through an emotion engine (Affectiva API). The analyzed data is converted to JSON format and sent to the server as an HTTP POST request.

[0995] Prompt generation

[0996] The server analyzes the received data and generates prompts based on the user's input requests and sentiment data. For example, the following prompt message may be generated:

[0997] Please create a presentation document for our new product, X. The target customer is a specific company, and its key features are high performance and low price. Since the user is excited, please use a bright and positive tone in the document.

[0998] Document generation and correction

[0999] Generative artificial intelligence (OpenAI GPT-3) generates initial material based on prompts. This material reflects the user's emotional state (for example, a brighter tone if the user is excited). The generated material is sent back to the server, which then sends it to the terminal.

[1000] Display and Feedback

[1001] The terminal displays the generated document to the user. The user reviews the document and enters any necessary corrections or additional requests. This feedback is also analyzed through the emotion engine and sent back to the server. Based on the feedback and emotion data, the server generates a new prompt and requests the generative artificial intelligence to regenerate it.

[1002] Specific example

[1003] The user begins a business negotiation with a customer while wearing smart glasses in a store. If the customer shows interest in the new product X, the smart glasses' camera and microphone analyze the customer's facial expressions and voice in real time, and collect emotional data through the emotion engine (Affectiva API). When the user inputs, "I want to create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price, with a simple layout," the server generates the following prompt text and sends it to the generative artificial intelligence (OpenAI GPT-3).

[1004] Please create a presentation document for our new product, X. The target customer is a specific company, and its key features are high performance and low price. Since the user is excited, please use a bright and positive tone in the document.

[1005] The generated materials will contain specific descriptions of "high performance" and "low price," and will have a positive tone. These materials will be displayed on the user's smart glasses and presented to the customer.

[1006] In this way, this invention provides a system that combines an emotion engine and generative artificial intelligence to create and modify materials in accordance with the user's real-time emotional state.

[1007] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1008] Step 1:

[1009] The smart device, acting as the terminal, collects user input data and emotional data. The user inputs customer needs and requirements through smart glasses. Meanwhile, the terminal's camera and microphone analyze the user's facial expressions and voice tone in real time using an emotion engine (Affectiva API) to generate emotional data. In this case, the input data might be something like "I want to create an introductory document for new product X" or "high performance and low price," and the output is the analyzed emotional data (happiness, excitement, calmness, etc.).

[1010] Step 2:

[1011] The terminal collects input data and sentiment data, converts it to JSON format, and sends it to the server. The terminal uses an HTTP POST request to send the necessary data to the server. The input is the user's input data and sentiment data, and the output is the data converted to JSON format.

[1012] Step 3:

[1013] The server analyzes the received data and generates a prompt. The server analyzes the user's input requests and sentiment data to generate a specific prompt message to send to the generative artificial intelligence (OpenAI GPT-3). For example, the prompt message might be in the format of, "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. The user is excited, so please make the tone of the document cheerful." The input for this step is the received JSON data, and the output is the generated prompt message.

[1014] Step 4:

[1015] The server sends the generated prompt text to the generative artificial intelligence. The server sends the prompt text to OpenAI GPT-3 via an API request and requests the generation of data based on it. The input is the prompt text, and the output is the initial data returned by the generative artificial intelligence.

[1016] Step 5:

[1017] A generative artificial intelligence (AI) generates sales materials based on prompt messages received from the server and sends them back to the server. Here, the AI ​​considers the user's input data and sentiment data to create sales materials with an appropriate tone. The input is the prompt message, and the output is the generated initial material.

[1018] Step 6:

[1019] The server sends the generated initial data to the terminal. The server uses an HTTP response to send the data received from the generative artificial intelligence back to the terminal. The input is the generated initial data, and the output is the data sent to the terminal.

[1020] Step 7:

[1021] The terminal displays the received documents to the user. The generated sales materials are displayed on the smart device screen, and the user reviews them. The input is the generated documents, and the output is the displayed documents.

[1022] Step 8:

[1023] The user reviews the generated document and enters requests for corrections or additions. The user then uses a smart device to review the document and enters any necessary correction instructions. The input consists of the user's correction instructions, and the output is sentiment data that is then analyzed again by the sentiment engine.

[1024] Step 9:

[1025] The collected user correction instructions and sentiment data are converted to JSON format and sent to the server. The terminal converts the correction instructions, including the new input data, to JSON format and sends them to the server via an HTTP POST request. The input is correction instructions and sentiment data, and the output is data in JSON format.

[1026] Step 10:

[1027] The server parses the JSON data it receives again and generates a new prompt. Based on the user's correction instructions and sentiment data, the server creates a prompt sentence to request the generative artificial intelligence to regenerate. For example, the prompt sentence might be in the format of, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X. Please write it in a tone that strongly emphasizes the pricing information." The input for this step is the JSON data that is received again, and the output is the new prompt sentence.

[1028] Step 11:

[1029] The server sends a new prompt to the generative AI and retrieves the regenerated data. The generative AI then generates the data again based on the new prompt, and this is sent back to the server. The input is the new prompt, and the output is the regenerated data.

[1030] Step 12:

[1031] The server sends the regenerated document to the terminal, which displays it to the user. The user reviews the document again and makes a final confirmation. The input is the regenerated document, and the output is the final confirmed document.

[1032] The above describes the specific processing steps of the system for implementing this invention.

[1033] 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.

[1034] 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.

[1035] 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.

[1036] [Third Embodiment]

[1037] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1038] 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.

[1039] 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).

[1040] 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.

[1041] 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.

[1042] 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).

[1043] 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.

[1044] 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.

[1045] 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.

[1046] 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.

[1047] 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.

[1048] 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".

[1049] This invention relates to a system that automatically creates sales materials using generative artificial intelligence and modifies and regenerates the materials based on user feedback. This system includes a terminal, a server, and the generative artificial intelligence as components.

[1050] Specific Embodiments

[1051] User input

[1052] The user logs into the terminal and begins creating sales materials. The user enters the necessary information for the sales materials into a dedicated input form. For example, when creating a presentation document for a new product, the user would enter items such as "Introduction to New Product X," "Target Customer: A Certain Company," "Features: High Performance, Low Price," and "Layout: Simple" into the input form.

[1053] Data transmission on the device

[1054] The terminal collects data entered by the user and sends it to the server. This transmission is done via an HTTP POST request, and the data is delivered to the server in JSON format.

[1055] Server-based data analysis and prompt generation

[1056] The server parses the received JSON data. As a result of this analysis, prompts are generated to instruct the generative artificial intelligence. For example, text such as "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. Please keep the layout simple." might be generated.

[1057] Initial document creation using generative artificial intelligence

[1058] The server sends the generated prompt to the generative artificial intelligence. The generative AI generates initial documents based on this prompt. The generated documents are sent back to the server as an initial version of the sales negotiation materials. For example, a document like the following is generated:

[1059] 1. Introduction of New Product X

[1060] 1.1. High performance

[1061] 1.2. Low price

[1062] 2. Key points of the proposal

[1063] 2.1. A suitable solution for a particular company

[1064] Sending documents via server

[1065] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays this data to the user, allowing the user to review it.

[1066] User feedback

[1067] The user reviews the generated sales materials and enters any requests for revisions or additions. For example, a user might submit a revision request such as, "Please add an introductory paragraph to Chapter 1."

[1068] Sending additional requests from the device

[1069] The terminal resends the user's correction instructions to the server. This transmission is also done via an HTTP POST request, and the data is again sent to the server in JSON format.

[1070] Server-based re-analysis of data and prompt generation

[1071] The server analyzes the received feedback again and generates a new prompt. For example, it might generate a prompt such as, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X."

[1072] Regeneration by generative artificial intelligence

[1073] The server sends a new prompt to the generative artificial intelligence. Based on this prompt, the generative AI regenerates the sales proposal document and sends the revised document back to the server. For example, a document with an introductory sentence added to Chapter 1 is generated.

[1074] Server-based transmission of revised documents

[1075] The server sends the revised document to the terminal and displays it to the user. The user can review the regenerated document and make further corrections as needed.

[1076] User's final confirmation

[1077] The user makes a final review, and once they are satisfied with the sales materials, they use them in the sales negotiation.

[1078] As described above, the system of the present invention supports the efficient creation of business negotiation materials by collecting user input and automatically generating and modifying materials using generative artificial intelligence.

[1079] The following describes the processing flow.

[1080] Step 1:

[1081] The user logs into the terminal and begins creating the sales presentation materials. The user enters the requirements for the sales presentation materials (purpose, target customers, features, desired layout, etc.) into a dedicated input form.

[1082] Step 2:

[1083] The terminal converts the data entered by the user into JSON format and sends it to the server via an HTTP POST request.

[1084] Step 3:

[1085] The server analyzes the JSON data received from the terminal. Based on the analysis results, it generates prompts to send to the generative artificial intelligence.

[1086] Step 4:

[1087] The generative artificial intelligence generates initial sales materials based on prompts received from the server. The generated materials are then sent back to the server.

[1088] Step 5:

[1089] The server sends the initial data received from the generative artificial intelligence to the user's terminal. The terminal displays the data to the user, allowing them to review it.

[1090] Step 6:

[1091] The user reviews the displayed sales materials and enters requests for corrections or additions. For example, they might enter instructions such as, "Please add an introductory paragraph to Chapter 1," into the terminal.

[1092] Step 7:

[1093] The terminal converts the user's correction instructions into JSON data and sends it back to the server as an HTTP POST request.

[1094] Step 8:

[1095] The server analyzes the user feedback it receives again and generates a new prompt. For example, it might generate a prompt such as, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X."

[1096] Step 9:

[1097] The generative artificial intelligence regenerates the document based on the new prompt received from the server. The revised document is then sent back to the server.

[1098] Step 10:

[1099] The server sends the regenerated document to the user's terminal. The terminal displays the corrected document to the user, providing another opportunity for review.

[1100] Step 11:

[1101] The user reviews the regenerated document and provides further revision instructions as needed. This process is repeated until a satisfactory document is finalized.

[1102] Step 12:

[1103] The user reviews the final version of the sales proposal materials, and once completed, uses them in the sales negotiation.

[1104] The above outlines the specific processing flow in the sales negotiation document creation system.

[1105] (Example 1)

[1106] 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."

[1107] Creating sales materials requires users to expend a significant amount of time and effort. Furthermore, the process of incorporating revisions and additional requests to these materials is complex and time-consuming. This can reduce the efficiency of sales material creation and negatively impact the success rate of sales negotiations.

[1108] 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.

[1109] In this invention, the server includes means for transmitting user requests from a terminal, means for the server to analyze user requests and generate prompt messages for a generation AI model, and means for the generation AI model to automatically generate materials based on the received prompt messages. This enables the rapid and efficient creation of sales materials and easy modification based on user feedback.

[1110] "Terminal" refers to all devices used by users to create and modify sales materials and to communicate with the server.

[1111] A "server" refers to a computing system that has the function of analyzing requests received from users and generating prompt messages to send to the AI ​​model.

[1112] A "generative AI model" refers to artificial intelligence technology that automatically generates materials based on the received prompt text.

[1113] A "prompt" refers to a text-based instruction that provides guidance to a generative AI model regarding the content and format of the document.

[1114] "Documents" refers to documents containing various pieces of information used in business negotiations.

[1115] "Feedback" refers to the input information that users use to request corrections or additions after reviewing the generated materials.

[1116] "Revised document" refers to a document regenerated by the AI ​​model based on user feedback.

[1117] "Automatic generation" refers to the process in which a generation AI model creates documents based on prompt text without human intervention.

[1118] A "re-prompt" refers to a new prompt message generated based on corrections or additional instructions.

[1119] "Transmission" refers to the process of moving data from a terminal to a server, or from a server to a generated AI model.

[1120] This invention relates to a system that automatically creates sales materials using a generative AI model and modifies and regenerates the materials based on user feedback. This system includes components such as a terminal, a server, and a generative AI model.

[1121] Specific Embodiments

[1122] Hardware environment

[1123] Devices: PCs, tablets, smartphones, etc. Users access the system using these devices.

[1124] Server: Receives and analyzes data, generates prompt messages, and communicates with the AI ​​model. This could be a cloud server or an on-premises server.

[1125] Generative AI models: For example, OpenAI's GPT-3 or ChatGPT. They generate sales materials based on prompt messages generated by the server.

[1126] Software Environment

[1127] Server-side scripts: These use programming languages ​​such as Python and Java to parse user requests and generate prompt messages.

[1128] HTTP Requests: Used for sending data between the terminal and the server, and between the server and the generated AI model. Requests use HTTP POST requests.

[1129] User input

[1130] The user logs into the terminal and begins creating sales materials. The user enters the necessary information into a dedicated input form. For example, when creating a presentation document for a new product, the user would enter information such as: "Introduction to New Product X," "Target Customer: A Certain Company," "Features: High Performance, Low Price," and "Layout: Simple."

[1131] Data transmission on the device

[1132] The terminal collects data entered by the user and sends it to the server. This transmission is done via an HTTP POST request, and the data is delivered to the server in JSON format.

[1133] Server-based data analysis and prompt generation

[1134] The server parses the received JSON data and generates prompt messages to instruct the AI ​​model based on the results of this analysis. For example, it might generate text such as, "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. Please keep the layout simple."

[1135] Initial document creation using a generative AI model

[1136] Based on the generated prompt text, the AI ​​model generates an initial version of the sales presentation materials. These presentation materials will be in the following format:

[1137] 1. Introduction of New Product X

[1138] 1.1. High performance

[1139] 1.2. Low price

[1140] 2. Key points of the proposal

[1141] 2.1. A suitable solution for a particular company

[1142] The generated documents are sent to the terminal via the server.

[1143] User feedback and corrections

[1144] The user reviews the generated sales presentation materials and enters requests for revisions or additions. For example, they might instruct, "Please add an introductory paragraph to Chapter 1." The terminal resends the user's feedback to the server, which analyzes the feedback and generates a new prompt. The generation AI model regenerates the sales presentation materials based on this new prompt, and this revised material is sent back to the terminal via the server.

[1145] By repeating this process, users can efficiently create satisfactory sales materials. Furthermore, this system allows for repeated revision and improvement of materials generated based on user input and feedback, thereby improving the quality of materials used in sales negotiations.

[1146] As described above, the system of the present invention significantly improves the efficiency of creating sales materials by automating the sales material creation process using a generative AI model and enabling rapid revisions based on user feedback.

[1147] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1148] Step 1:

[1149] Users log in to the system using a terminal.

[1150] Specific steps: The user enters their user ID and password and clicks the "Login" button. The system sends the authentication information to the server, and if authentication is successful, the next screen is displayed.

[1151] Input: User ID, Password

[1152] Output: User authentication result, next operation screen

[1153] Step 2:

[1154] The user enters the necessary information into the input form to begin creating the sales presentation materials.

[1155] Specific operation: The user enters information such as "Introduction to new product X," "Target customer: A certain company," "Features: High performance, low price," and "Layout: Simple," and then clicks the "Submit" button.

[1156] Input: Each item in the sales presentation materials (new product name, target customers, features, layout, etc.)

[1157] Output: Request to send input information

[1158] Step 3:

[1159] The terminal sends the information entered by the user to the server via an HTTP POST request.

[1160] Specific operation: The terminal converts the input data into JSON format and sends it to the server.

[1161] Input: Information from sales materials entered by the user.

[1162] Output: Send data in JSON format

[1163] Step 4:

[1164] The server parses the received JSON data and generates prompt messages to send to the AI ​​model.

[1165] Specific operation: The server uses a Python script to parse the JSON data and generates a prompt message that reads, "Create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. The layout should be simple."

[1166] Input: Information from business negotiation materials sent in JSON format

[1167] Output: Prompt message to send to the generated AI model

[1168] Step 5:

[1169] The server sends the generated prompt message to the AI ​​model, requesting it to generate initial data.

[1170] Specific operation: The server sends a prompt message to the AI ​​generation model via an HTTP POST request. The AI ​​generation model generates sales materials based on the prompt message and sends them back to the server.

[1171] Input: Prompt text for the generated AI model

[1172] Output: Initial data generated by a generative AI model

[1173] Step 6:

[1174] The server sends the generated initial data to the terminal and displays it to the user.

[1175] Specific operation: The server uses an HTTP POST request to send the generated data to the terminal in JSON format. The terminal displays the received data to the user.

[1176] Input: Initial data returned from the generated AI model

[1177] Output: Display of initial materials in a format viewable by the user.

[1178] Step 7:

[1179] The user reviews the generated document and enters any necessary corrections or additional requests.

[1180] Specific actions: The user reviews the document, enters specific feedback such as "Please add an introductory paragraph to Chapter 1," and clicks the "Submit" button.

[1181] Input: User requests for modifications or additions

[1182] Output: Request to send correction instructions

[1183] Step 8:

[1184] The terminal then sends the user's correction instructions back to the server.

[1185] Specific operation: The terminal converts the modification request into JSON format and sends it to the server via an HTTP POST request.

[1186] Input: User requests for modifications or additions

[1187] Output: Sending correction instructions in JSON format

[1188] Step 9:

[1189] The server analyzes the received correction instructions and generates a new prompt message.

[1190] Specific operation: The server uses a Python script to analyze the feedback data and generates a new prompt message: "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X."

[1191] Input: Correction instructions in JSON format

[1192] Output: New prompt message to send to the generated AI model

[1193] Step 10:

[1194] The server sends a new prompt message to the AI ​​model, requesting it to generate the revised document.

[1195] Specific operation: The server sends a prompt message to the generating AI model via an HTTP POST request. The generating AI model generates revised data based on the prompt message and sends it back to the server.

[1196] Input: New prompt message to the generated AI model

[1197] Output: Revised document generated by an AI model

[1198] Step 11:

[1199] The server sends the revised document to the terminal and displays it to the user.

[1200] Specific operation: The server sends the revised document to the terminal in JSON format using an HTTP POST request. The terminal displays the received document to the user.

[1201] Input: Revised data returned from the generated AI model

[1202] Output: Display of the revised document in a format viewable by the user.

[1203] Step 12:

[1204] The user performs a final review, and once the materials meet their quality standards, they are used in business negotiations.

[1205] Specific actions: The user reviews the document one last time and, if necessary, submits a revision request, or reviews the document one last time and downloads or prints it.

[1206] Input: User's final confirmation

[1207] Output: Finalization of documents for use in business negotiations.

[1208] (Application Example 1)

[1209] 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."

[1210] In modern business negotiations and customer service at retail stores, it is crucial to be able to quickly prepare promotional and explanatory materials. However, creating these manually is time-consuming and inefficient. Furthermore, quickly gathering customer feedback is not easy. To solve these problems and improve customer satisfaction, there is a need for an automated material generation system utilizing generative artificial intelligence.

[1211] 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.

[1212] In this invention, the server includes means for automatically creating materials using generative artificial intelligence, means for modifying materials based on user feedback, means for transmitting user requests from a terminal to the server, means for generating and updating sales materials and promotional materials via a smart device, and means for incorporating customer feedback and regenerating materials. This makes it possible to provide sales materials and promotional materials quickly and efficiently, and to immediately reflect customer feedback.

[1213] "Generative artificial intelligence" refers to artificial intelligence that has the ability to generate new information or content based on input data.

[1214] "Methods for automatically creating documents" refers to a system that automatically creates documents using generative artificial intelligence based on user requests.

[1215] "Means of modifying materials based on user feedback" refers to methods of modifying existing materials using generative artificial intelligence to reflect user opinions and requests.

[1216] "Means of sending user requests from a terminal to a server" refers to a function that allows a user to send instructions to a server from their device for creating or modifying business negotiation materials.

[1217] "Means of sending prompts from a server to a generative artificial intelligence" refers to a method by which a server analyzes the user's request and sends instructions (prompts) based on that analysis to the generative artificial intelligence.

[1218] "A means of returning and displaying generated materials on a terminal" refers to a mechanism in which a server sends materials created by a generative artificial intelligence to a user's terminal, and the user can view and display them.

[1219] "Means for generating and updating sales materials and promotional materials via smart devices" refers to methods for generating sales materials and promotional materials using devices such as smart glasses and smartphones, and updating them as needed.

[1220] "Methods for incorporating customer feedback and regenerating materials" refers to a system that collects opinions and requests provided by customers and then regenerates materials with necessary updates based on that feedback.

[1221] A "smart device" refers to a glasses-type device or mobile phone equipped with internet connectivity and application execution capabilities.

[1222] This invention provides a system that automatically creates sales materials and promotional materials using generative artificial intelligence, and modifies and regenerates the materials based on user feedback. This system consists of a terminal, a server, and generative artificial intelligence.

[1223] System Configuration

[1224] terminal

[1225] The terminal utilizes smart devices (such as smart glasses or smartphones). Users use this terminal to input requests for the creation of business negotiation materials, and to review and modify the generated materials.

[1226] server

[1227] The server receives request data sent from the user via the terminal, analyzes it, and sends prompts to the generative artificial intelligence. The main functions of the server are as follows:

[1228] Analyze user requests and generate prompts.

[1229] A prompt is sent to the generative artificial intelligence, and the generated material is received.

[1230] The received documents are sent back to the user's device.

[1231] Generative artificial intelligence

[1232] Generative artificial intelligence generates sales materials and promotional materials based on prompts received from the server. The generated materials are sent back to the server and displayed again on the user's device.

[1233] Program Processing Description

[1234] Hardware:

[1235] Smart glasses (e.g., Google Glass)

[1236] Smartphones (e.g., iPhone, Android devices)

[1237] Server Computer

[1238] software:

[1239] Flask (a Python-based web framework)

[1240] requests (a Python module for sending HTTP requests)

[1241] APIs for generative AI models (e.g., OpenAI GPT, etc.)

[1242] The server analyzes user requests sent from smart devices and generates prompts for generative artificial intelligence. The generative AI model then creates prompt statements that generate materials. For example, a prompt might read: "A customer is requesting detailed information about the special features of new product Y. New product Y is highly durable and energy-efficient. Please create promotional materials that explain this in a way that does not require specialized knowledge."

[1243] This prompt is sent to a generative artificial intelligence system, the server receives the generated material, and sends it back to the terminal for display. The user can review the generated material, provide corrections or additional feedback, the server analyzes it again, and sends it to the generative AI model as a new prompt.

[1244] Specific example:

[1245] One scenario envisioned is that when a customer asks for details about a new product in a store, staff use smart glasses to instantly generate information and display it on a screen.

[1246] Customer question: "I would like to know more details about the special features of product X."

[1247] Staff operation: The staff member voice-inputs the following into the smart glasses: "Please generate documentation about the special features of the new product X."

[1248] System processing: Generates a prompt message, sends it to the generation AI model, and displays the generated document on the terminal.

[1249] This allows users to immediately provide materials to respond to customers and to quickly gather customer feedback.

[1250] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1251] Step 1:

[1252] User request input

[1253] Users use their devices (smart glasses or smartphones) to input requests for the creation of sales materials or promotional materials. For example, they might use the voice input function of their smart glasses to input a request such as, "Please create an introductory document for new product X." This input data is processed within the device and sent to the server.

[1254] Input: Request for creation of sales materials (e.g., introductory materials for new product X)

[1255] Output: Requested data

[1256] Step 2:

[1257] Sending request data

[1258] The terminal sends user input data to the server. The data is sent to the server in JSON format as an HTTP POST request. This process ensures the data is delivered to the server and ready for analysis.

[1259] Input: Request data

[1260] Output: HTTP POST request to the server

[1261] Step 3:

[1262] Server-based request data analysis

[1263] The server analyzes the received request data and creates a prompt to send to the generative artificial intelligence. For example, if a user requests, "Please create an introductory document for new product X," the server will generate a prompt such as, "Please create an introductory document for new product X. The target customers are general consumers. Its features are high performance and low price."

[1264] Input: Request data in an HTTP POST request

[1265] Output: Prompts for generative artificial intelligence

[1266] Step 4:

[1267] Send a prompt

[1268] The server sends the generated prompt to the generative AI. It sends the prompt as an API request to the generative AI, requesting the generation of data. At this time, an HTTP POST request is made to the generative AI's API endpoint.

[1269] Input: Prompt

[1270] Output: API request to a generative artificial intelligence system

[1271] Step 5:

[1272] Data generation

[1273] Generative artificial intelligence generates sales materials and promotional materials based on prompts. These generated materials are then sent back to the server. For example, a document containing sections such as "Introduction to New Product X," "High Performance," and "Low Price" is generated.

[1274] Input: Prompt

[1275] Output: Generated document

[1276] Step 6:

[1277] Return of generated documents

[1278] The server returns the data received from the generative artificial intelligence to the terminal. The data is sent as a response to an HTTP POST request and displayed on the terminal. The user can visually confirm the generated data.

[1279] Input: Generated document

[1280] Output: HTTP POST response to the terminal

[1281] Step 7:

[1282] Displaying documents and entering feedback

[1283] The user reviews the generated document on their device and provides feedback as needed. For example, they might enter a correction request such as, "Please add an introductory sentence to Chapter 1." This feedback data is then sent back to the server.

[1284] Input: Generated materials and feedback

[1285] Output: Feedback data

[1286] Step 8:

[1287] Sending feedback data

[1288] The device resends the user's feedback data to the server. The data is sent again to the server in JSON format as an HTTP POST request, and is ready for regeneration.

[1289] Input: Feedback data

[1290] Output: HTTP POST request to the server

[1291] Step 9:

[1292] Regeneration prompt generation

[1293] The server analyzes the feedback data and generates a new prompt. For example, it might generate a new prompt such as, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X," and send it to the generative artificial intelligence.

[1294] Input: Feedback data in an HTTP POST request

[1295] Output: New prompt

[1296] Step 10:

[1297] Regeneration and final transmission of documents

[1298] The server sends a new prompt to the generative artificial intelligence, which generates a revised version of the document. The generated document is sent back to the server and then transmitted to the terminal. The user then makes a final review of the regenerated document and uses it for business negotiations or promotions.

[1299] Input: New prompt

[1300] Output: Regenerated materials

[1301] Through the steps outlined above, users can quickly and efficiently generate, modify, and review sales materials and promotional materials.

[1302] 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.

[1303] This invention relates to a system that combines generative artificial intelligence and an emotion engine to automatically create and modify business negotiation materials. This system analyzes user input data, automatically creates materials using generative artificial intelligence, and further has the function of recognizing the user's emotional state and adjusting the content of the materials.

[1304] Specific Embodiments

[1305] User input

[1306] The user logs into the terminal and begins creating the sales presentation materials. The user enters the requirements for the sales presentation materials (purpose, target customer, features, desired layout, etc.) into a dedicated input form. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, the features are high performance and low price, and the layout should be simple."

[1307] Utilizing the Emotion Engine

[1308] The device analyzes the user's emotions in real time through the camera and microphone while the user is inputting data. The emotion engine analyzes data such as changes in facial expressions and tone of voice to recognize the user's emotional state. For example, it collects different emotional data depending on whether the user is excited or calm.

[1309] Data transmission on the device

[1310] The device combines user input data and sentiment data, converts it to JSON format, and sends it to the server. This transmission is done via an HTTP POST request, and the necessary data is passed to the server.

[1311] Server-based data analysis and prompt generation

[1312] The server parses the received JSON data. Based on the analysis results, it generates a prompt to send to the generative artificial intelligence. This prompt includes the user's requests and sentiment data. For example, it might generate text such as, "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. The user is excited, so please make the tone of the document cheerful."

[1313] Initial document creation using generative artificial intelligence

[1314] The generative artificial intelligence generates initial materials based on prompts received from the server. The generated materials are then sent back to the server. The generated materials reflect the tone and content of the user's emotional state, taking into account data from the emotion engine. For example, a document like the following might be generated:

[1315] 1. Introduction of New Product X

[1316] 1.1. High performance

[1317] 1.2. Low price

[1318] 1.3. Significant improvements can be expected by using this innovative product!

[1319] 2. Key points of the proposal

[1320] 2.1. A suitable solution for a particular company

[1321] Sending documents via server

[1322] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays the data to the user, allowing the user to review it.

[1323] User feedback

[1324] The user reviews the generated sales materials and enters requests for revisions or additions. Throughout this process, the sentiment engine monitors the user's emotions and collects data such as which parts the user shows the most interest in. For example, the user can give instructions such as, "Please add an introductory sentence to Chapter 1. Also, please emphasize the pricing information more."

[1325] Sending additional requests from the device

[1326] The device converts the user's correction instructions and sentiment data into JSON format and sends it back to the server as an HTTP POST request.

[1327] Server-based re-analysis of data and prompt generation

[1328] The server then analyzes the user's feedback and sentiment data it receives again and generates a new prompt. For example, it might generate a prompt such as, "Add an introductory paragraph to Chapter 1 of the new product X introduction document. Write it in a tone that strongly emphasizes the pricing information."

[1329] Regeneration by generative artificial intelligence

[1330] The generative artificial intelligence regenerates the document based on new prompts received from the server. It then sends the revised document back to the server. This revised document incorporates user feedback and sentiment data, such as highlighting price information.

[1331] Server-based transmission of revised documents

[1332] The server sends the regenerated document to the terminal and displays it to the user. The user can review the corrected document again and provide further correction instructions if necessary.

[1333] User's final confirmation

[1334] The user performs a final review, and once the sales materials are satisfactory, they are used in the sales negotiation. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the materials are aligned with the user's intentions and emotions.

[1335] As described above, the system of the present invention, by combining generative artificial intelligence and an emotion engine, can efficiently and accurately create and modify business negotiation materials and reflect the user's emotional state.

[1336] The following describes the processing flow.

[1337] Step 1:

[1338] The user logs into the terminal and begins creating the sales presentation materials. The user enters the requirements for the sales presentation materials (purpose, target customer, features, desired layout, etc.) into a dedicated input form. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, the features are high performance and low price, and the layout should be simple."

[1339] Step 2:

[1340] The emotion engine uses the camera and microphone built into the device to analyze the user's emotions in real time. It collects data such as changes in facial expressions and tone of voice to recognize the user's emotional state. For example, if the user is talking happily, the emotion will be recognized as "joy."

[1341] Step 3:

[1342] The device combines user input data and sentiment data, converts it to JSON format, and sends it to the server via an HTTP POST request. The transmitted data includes the purpose of the deal, target customers, characteristics, desired layout, and sentiment data.

[1343] Step 4:

[1344] The server analyzes the JSON data received from the terminal. Based on data such as the purpose and characteristics of the business negotiation, as well as user sentiment data, it generates prompts to send to the generative artificial intelligence. For example, a prompt such as "Please create an introductory document for new product X. The target customer is a certain company, and its features are high performance and low price. The user seems to be enjoying themselves, so please make the tone of the document cheerful." might be generated.

[1345] Step 5:

[1346] The generative artificial intelligence generates initial sales materials based on prompts received from the server. At this stage, the tone and content of the materials are adjusted considering the user's emotional data. The generated materials are sent back to the server. For example, the following document is generated:

[1347] 1. Introduction of New Product X

[1348] 1.1. High performance

[1349] 1.2. Low price

[1350] 1.3. This innovative product will enrich your life even further!

[1351] 2. Key points of the proposal

[1352] 2.1. A suitable solution for a particular company

[1353] Step 6:

[1354] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays the data to the user, allowing the user to review it.

[1355] Step 7:

[1356] The user reviews the displayed sales materials and enters requests for revisions or additions. If revision requests are made, the device uses the emotion engine again to analyze the user's emotions and acquire emotion data. For example, a user might submit a revision request such as, "Please add an introductory sentence to Chapter 1. Also, please emphasize the pricing information more."

[1357] Step 8:

[1358] The device converts the user's correction instructions and sentiment data into JSON format and sends them to the server again via an HTTP POST request.

[1359] Step 9:

[1360] The server analyzes the feedback and sentiment data it receives and generates new prompts. For example, it might generate a prompt such as, "Add an introductory sentence to Chapter 1 of the new product X introduction document. Write it in a tone that emphasizes the pricing information."

[1361] Step 10:

[1362] The generative artificial intelligence regenerates the material based on the new prompt received from the server. At this stage, the re-feedback sentiment data is also taken into consideration. The revised material is sent back to the server. For example, the following revised material is generated:

[1363] 1. Introduction of New Product X

[1364] 1.1. High performance

[1365] 1.2. Low price

[1366] 1.3. This innovative product will enrich your life even further!

[1367] 1.4. Implementing XYZ products offers an opportunity to significantly improve your business.

[1368] 2. Key points of the proposal

[1369] 2.1. A suitable solution for a particular company

[1370] 2.2. Special pricing offer

[1371] Step 11:

[1372] The server sends the regenerated document to the terminal and displays it to the user. The user can review the corrected document again and provide further correction instructions if necessary.

[1373] Step 12:

[1374] Once the user has made a final review and is satisfied with the completed document, it is used in the sales negotiation. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the document always align with the user's intentions and emotions.

[1375] The above outlines the specific processing flow in a sales negotiation document creation system that combines generative artificial intelligence and an emotion engine.

[1376] (Example 2)

[1377] 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."

[1378] Conventional document creation systems generate documents in a fixed pattern without considering user emotions, making it difficult to create documents that reflect user intentions and feelings. Furthermore, users must manually revise documents after creation, highlighting the need for more efficient workflows.

[1379] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for the user to log in to the terminal and input requests, means for analyzing the user's emotional state using a camera and microphone, means for transmitting the user's input data and emotional data from the terminal to the server in JSON format, means for the server to generate a prompt based on the user's requests and emotional data and transmit it to a generative artificial intelligence, means for the generative artificial intelligence to generate materials based on the prompt and send them back to the server, and means for the server to transmit the generated materials to the terminal and display them. This makes it possible to efficiently create materials that reflect the user's intentions and emotions.

[1380] A "user" refers to a person who uses the system to create documents.

[1381] A "terminal" refers to an electronic device used by a user to manipulate input data. Examples include personal computers and smartphones.

[1382] An "emotion engine" refers to software or hardware that uses cameras and microphones to analyze a user's emotional state.

[1383] "JSON format" is a data serialization format that refers to a method of storing and exchanging data based on JavaScript object notation.

[1384] A "server" refers to a central control unit that receives user input data and emotion data, performs analysis, and sends prompts to the generative artificial intelligence.

[1385] A "prompt" refers to text data or commands used to instruct a generative artificial intelligence system to generate data.

[1386] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates materials based on prompts.

[1387] "Documents" refer to documents and presentation materials generated for purposes such as business negotiations and proposals.

[1388] "Feedback" refers to correction instructions or additional requests made by users regarding materials they have generated.

[1389] This invention relates to a system that automatically creates and modifies business negotiation materials by combining generative artificial intelligence and an emotion engine. This system analyzes user input data and emotion data, automatically creates materials using generative artificial intelligence, and further has the function of recognizing the user's emotional state and adjusting the content of the materials.

[1390] 1. User input

[1391] The user logs into the terminal and enters the requirements for the sales materials through a dedicated input form. The user enters these items using a keyboard and mouse. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, its features are high performance and low price, and the layout should be simple."

[1392] 2. Utilizing the Emotional Engine

[1393] The emotion engine analyzes the user's facial expressions and voice in real time through the camera and microphone connected to the device. This allows it to detect the user's emotional state. For example, it can distinguish between when the user is excited and when they are calm. The emotion engine analyzes this data and uses that information to inform subsequent processing.

[1394] 3. Data transmission from the device

[1395] The terminal combines the user's input data and sentiment data, converts it to JSON format, and sends it to the server. This transmission is done using an HTTP POST request. For example, the following JSON data is generated:

[1396] json

[1397] {

[1398] "subject": "Introduction document for new product X",

[1399] "target_customer": "A certain company",

[1400] "features": ["high performance", "low price"],

[1401] "layout": "simple",

[1402] "emotion": "excitement"

[1403] }

[1404] 4. Server-based data analysis and prompt generation

[1405] The server parses the received JSON data and generates a prompt to send to the generative artificial intelligence based on the user's requests and sentiment data. The generated prompt is text data containing the user's requests and sentiment data. For example, a prompt such as "Please create an introductory document for new product X. The target customer is a certain company, and its features are high performance and low price. The user is excited, so please make the tone of the document cheerful." might be generated.

[1406] 5. Initial document creation using generative artificial intelligence

[1407] The generative artificial intelligence generates initial material based on prompts received from the server. The generated material is then sent back to the server. The generated material reflects the user's emotional state in tone and content. For example, the following document might be generated:

[1408] 1. Introduction of New Product X

[1409] 1.1. High performance

[1410] 1.2. Low price

[1411] 1.3. Significant improvements can be expected by using this innovative product!

[1412] 2. Key points of the proposal

[1413] 2.1. A suitable solution for a particular company

[1414] 6. Sending documents via server

[1415] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays the data to the user, allowing the user to review it.

[1416] 7. User Feedback

[1417] The user reviews the generated sales materials and enters requests for revisions or additions. For example, they might give instructions such as, "Please add an introductory sentence to Chapter 1. Also, please emphasize the pricing information more." Throughout this process, the emotion engine monitors the user's emotions and collects data such as which parts they show the most interest in.

[1418] 8. Sending additional requests from the device

[1419] The terminal converts the user's correction instructions and sentiment data into JSON format and sends it back to the server as an HTTP POST request. The server parses the received data and generates a new prompt. For example, a prompt such as "Add an introductory sentence to Chapter 1 of the new product X introduction document. Write it in a tone that strongly emphasizes the pricing information." might be generated.

[1420] 9. Regeneration by generative artificial intelligence

[1421] The generative artificial intelligence regenerates the document based on the new prompt and returns the revised document to the server. This revised document incorporates user feedback and sentiment data.

[1422] 10. Server-based submission of revised documents

[1423] The server sends the regenerated document to the terminal for the user to review. The user can then review the corrected document again and provide further correction instructions if necessary.

[1424] 11. User's final confirmation

[1425] The user makes a final review, and only uses the materials in a sales negotiation once they are satisfactory. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the materials are aligned with the user's intentions and emotions.

[1426] The above is a specific embodiment of the system of the present invention. This system can analyze user input data and emotional data, and efficiently and accurately create and modify materials using generative artificial intelligence.

[1427] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1428] Step 1:

[1429] The user logs into the terminal and begins creating sales materials. They enter the requirements for the sales materials (purpose, target customer, features, desired layout, etc.) into the input form. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, its features are high performance and low price, and the layout should be simple." The input data includes purpose, target customer, features, desired layout, etc. The output is the requirements entered by the user.

[1430] Step 2:

[1431] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time. The emotion engine acquires changes in the user's facial expressions and voice tone as input data and recognizes the user's emotional state (excitement, calmness, etc.). As a result of the analysis, the user's emotional data is obtained. For example, if the user is excited, the emotion engine collects that data and outputs the state of excitement.

[1432] Step 3:

[1433] The terminal combines user input data and sentiment data and converts it into JSON format. The data processing involves combining requirements and sentiment data. The resulting JSON data includes the following format:

[1434] json

[1435] {

[1436] "subject": "Introduction document for new product X",

[1437] "target_customer": "A certain company",

[1438] "features": ["high performance", "low price"],

[1439] "layout": "simple",

[1440] "emotion": "excitement"

[1441] }

[1442] Step 4:

[1443] The terminal sends the converted JSON data to the server as an HTTP POST request. The input contains data in JSON format, and the output verifies that the data is sent correctly to the server.

[1444] Step 5:

[1445] The server parses the received JSON data and generates prompts to send to the generative artificial intelligence based on the user's requests and sentiment data. Data processing includes parsing the JSON data and converting it into prompts. For example, the generated prompts will be in the following text format:

[1446] "Please create a presentation document for our new product, X. The target customer is a specific company, and its key features are high performance and low price. The user is excited, so please make the document have a bright and positive tone."

[1447] Step 6:

[1448] The server sends the generated prompt to the generative AI, requesting it to generate initial data. The input includes the prompt, and the output is the initial data generated by the generative AI.

[1449] Step 7:

[1450] The generative artificial intelligence generates initial data based on prompts and sends it back to the server. For data processing, the generative AI performs text generation, and the generated data is obtained as output. For example, the following document is generated:

[1451] 1. Introduction of New Product X

[1452] 1.1. High performance

[1453] 1.2. Low price

[1454] 1.3. Significant improvements can be expected by using this innovative product!

[1455] 2. Key points of the proposal

[1456] 2.1. A suitable solution for a particular company

[1457] Step 8:

[1458] The server sends the initial data received from the generative artificial intelligence to the terminal and displays it to the user. The input includes the generated data, and the output confirms that the user can view the data.

[1459] Step 9:

[1460] The user reviews the generated document and enters requests for corrections or additions. For example, they might give instructions such as, "Add an introductory sentence to Chapter 1. Also, emphasize the pricing information more." The input includes user feedback, and the output is the feedback received.

[1461] Step 10:

[1462] The terminal converts the user's correction instructions and sentiment data into JSON format and sends it back to the server as an HTTP POST request. As part of the data processing, it is converted back to JSON format. The output is the JSON data sent to the server.

[1463] Step 11:

[1464] The server analyzes the re-received data and generates a new prompt. The input includes JSON data, and the output is a new prompt. For example, a prompt such as "Add an introductory sentence to Chapter 1 of the new product X introduction document. Write it in a tone that strongly emphasizes the pricing information." might be generated.

[1465] Step 12:

[1466] The generative artificial intelligence regenerates the document based on the new prompt and returns the revised document to the server. In terms of data calculation, the document is regenerated based on the revision instructions, and the revised document is obtained as output.

[1467] Step 13:

[1468] The server sends the regenerated document to the terminal for user review. It ensures that the input includes the corrected document and that the user can review the document again as output.

[1469] Step 14:

[1470] The user performs a final review, and once the document is satisfactory, it is used in the business negotiation. The input includes the final document, and the output is the finalized, reviewed document. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the document will be aligned with the user's intentions and emotions.

[1471] The above describes the specific flow of the program processing of this system and the actions performed at each step.

[1472] (Application Example 2)

[1473] 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."

[1474] Current automated document creation systems generate documents based on static user input data, but they struggle to respond to user emotional states or real-time feedback. Furthermore, because the tone of documents is not adjusted based on customer emotions during sales negotiations and sales activities, it is not possible to create documents that effectively appeal to customer interest and emotions. This limits the effectiveness of sales negotiations and sales activities.

[1475] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for automatically creating materials using generative artificial intelligence, means for modifying materials based on user feedback, means for transmitting user requests from a terminal to the server, means for transmitting prompts from the server to the generative artificial intelligence, means for returning and displaying the generated materials to the terminal, means for analyzing the user's emotional state using an emotion engine, means for adjusting the tone of the materials based on the analyzed emotional data, and means for collecting user input and emotional data via a smart device. This makes it possible to create materials and adjust the tone based on the user's emotional state and real-time feedback.

[1476] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates text and documents based on input data.

[1477] "Means for automatically creating documents" refers to a function that automatically generates sales materials and explanatory documents based on user requests.

[1478] "Means for modifying documents" refers to a function that modifies and updates already generated documents in response to user feedback.

[1479] A "terminal" refers to a device used by a user, such as a computer or smart device used for inputting information or receiving data.

[1480] A "server" is a computer system that processes and stores data on a network and responds to requests from other terminals.

[1481] A "prompt" is input text data used to instruct a generative artificial intelligence system to create or modify documents.

[1482] An "emotion engine" is a technology that analyzes and recognizes a user's emotional state in real time based on their facial expressions, tone of voice, and other factors.

[1483] "Emotional data" refers to data about the user's emotional state, analyzed by the emotion engine.

[1484] "Tone adjustment" refers to changing the content and wording of a document according to the user's emotional state.

[1485] A "smart device" is an internet-connected terminal equipped with a camera and microphone that can collect user input and emotional data.

[1486] This invention uses a system that combines generative artificial intelligence and an emotion engine to automatically create and modify sales materials, and to provide real-time emotional support. The specific system configuration consists of a smart device used by the user, a server, generative artificial intelligence, and an emotion engine.

[1487] Program generation

[1488] This system's program includes the following elements:

[1489] 1. Acquire customer input data and sentiment data using smart devices.

[1490] 2. Send data to the server and generate a prompt.

[1491] 3. Generative artificial intelligence generates and modifies documents based on prompts.

[1492] 4. The server sends the generated document back to the terminal and displays it on the terminal.

[1493] Hardware and software to use

[1494] hardware

[1495] Smart devices: These are internet-connected terminals equipped with cameras and microphones, such as smart glasses and smartphones, that collect user input and emotional data. Each device can analyze the user's facial expressions and voice tone in real time.

[1496] software

[1497] Emotion Engine: Uses the Affectiva API to analyze the user's emotional state and sends it to the server as emotion data.

[1498] Generative Artificial Intelligence: Uses the OpenAI GPT-3 model to generate and modify documents based on prompts.

[1499] Data processing and data calculation

[1500] Data collection

[1501] The device uses its camera and microphone to collect the user's facial expressions and voice tone, and analyzes them through an emotion engine (Affectiva API). The analyzed data is converted to JSON format and sent to the server as an HTTP POST request.

[1502] Prompt generation

[1503] The server analyzes the received data and generates prompts based on the user's input requests and sentiment data. For example, the following prompt message may be generated:

[1504] Please create a presentation document for our new product, X. The target customer is a specific company, and its key features are high performance and low price. Since the user is excited, please use a bright and positive tone in the document.

[1505] Document generation and correction

[1506] Generative artificial intelligence (OpenAI GPT-3) generates initial material based on prompts. This material reflects the user's emotional state (for example, a brighter tone if the user is excited). The generated material is sent back to the server, which then sends it to the terminal.

[1507] Display and Feedback

[1508] The terminal displays the generated document to the user. The user reviews the document and enters any necessary corrections or additional requests. This feedback is also analyzed through the emotion engine and sent back to the server. Based on the feedback and emotion data, the server generates a new prompt and requests the generative artificial intelligence to regenerate it.

[1509] Specific example

[1510] The user begins a business negotiation with a customer while wearing smart glasses in a store. If the customer shows interest in the new product X, the smart glasses' camera and microphone analyze the customer's facial expressions and voice in real time, and collect emotional data through the emotion engine (Affectiva API). When the user inputs, "I want to create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price, with a simple layout," the server generates the following prompt text and sends it to the generative artificial intelligence (OpenAI GPT-3).

[1511] Please create a presentation document for our new product, X. The target customer is a specific company, and its key features are high performance and low price. Since the user is excited, please use a bright and positive tone in the document.

[1512] The generated materials will contain specific descriptions of "high performance" and "low price," and will have a positive tone. These materials will be displayed on the user's smart glasses and presented to the customer.

[1513] In this way, this invention provides a system that combines an emotion engine and generative artificial intelligence to create and modify materials in accordance with the user's real-time emotional state.

[1514] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1515] Step 1:

[1516] The smart device, acting as the terminal, collects user input data and emotional data. The user inputs customer needs and requirements through smart glasses. Meanwhile, the terminal's camera and microphone analyze the user's facial expressions and voice tone in real time using an emotion engine (Affectiva API) to generate emotional data. In this case, the input data might be something like "I want to create an introductory document for new product X" or "high performance and low price," and the output is the analyzed emotional data (happiness, excitement, calmness, etc.).

[1517] Step 2:

[1518] The terminal collects input data and sentiment data, converts it to JSON format, and sends it to the server. The terminal uses an HTTP POST request to send the necessary data to the server. The input is the user's input data and sentiment data, and the output is the data converted to JSON format.

[1519] Step 3:

[1520] The server analyzes the received data and generates a prompt. The server analyzes the user's input requests and sentiment data to generate a specific prompt message to send to the generative artificial intelligence (OpenAI GPT-3). For example, the prompt message might be in the format of, "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. The user is excited, so please make the tone of the document cheerful." The input for this step is the received JSON data, and the output is the generated prompt message.

[1521] Step 4:

[1522] The server sends the generated prompt text to the generative artificial intelligence. The server sends the prompt text to OpenAI GPT-3 via an API request and requests the generation of data based on it. The input is the prompt text, and the output is the initial data returned by the generative artificial intelligence.

[1523] Step 5:

[1524] A generative artificial intelligence (AI) generates sales materials based on prompt messages received from the server and sends them back to the server. Here, the AI ​​considers the user's input data and sentiment data to create sales materials with an appropriate tone. The input is the prompt message, and the output is the generated initial material.

[1525] Step 6:

[1526] The server sends the generated initial data to the terminal. The server uses an HTTP response to send the data received from the generative artificial intelligence back to the terminal. The input is the generated initial data, and the output is the data sent to the terminal.

[1527] Step 7:

[1528] The terminal displays the received documents to the user. The generated sales materials are displayed on the smart device screen, and the user reviews them. The input is the generated documents, and the output is the displayed documents.

[1529] Step 8:

[1530] The user reviews the generated document and enters requests for corrections or additions. The user then uses a smart device to review the document and enters any necessary correction instructions. The input consists of the user's correction instructions, and the output is sentiment data that is then analyzed again by the sentiment engine.

[1531] Step 9:

[1532] The collected user correction instructions and sentiment data are converted to JSON format and sent to the server. The terminal converts the correction instructions, including the new input data, to JSON format and sends them to the server via an HTTP POST request. The input is correction instructions and sentiment data, and the output is data in JSON format.

[1533] Step 10:

[1534] The server parses the JSON data it receives again and generates a new prompt. Based on the user's correction instructions and sentiment data, the server creates a prompt sentence to request the generative artificial intelligence to regenerate. For example, the prompt sentence might be in the format of, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X. Please write it in a tone that strongly emphasizes the pricing information." The input for this step is the JSON data that is received again, and the output is the new prompt sentence.

[1535] Step 11:

[1536] The server sends a new prompt to the generative AI and retrieves the regenerated data. The generative AI then generates the data again based on the new prompt, and this is sent back to the server. The input is the new prompt, and the output is the regenerated data.

[1537] Step 12:

[1538] The server sends the regenerated document to the terminal, which displays it to the user. The user reviews the document again and makes a final confirmation. The input is the regenerated document, and the output is the final confirmed document.

[1539] The above describes the specific processing steps of the system for implementing this invention.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] [Fourth Embodiment]

[1544] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1545] 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.

[1546] 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).

[1547] 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.

[1548] 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.

[1549] 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).

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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.

[1556] 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".

[1557] This invention relates to a system that automatically creates sales materials using generative artificial intelligence and modifies and regenerates the materials based on user feedback. This system includes a terminal, a server, and the generative artificial intelligence as components.

[1558] Specific Embodiments

[1559] User input

[1560] The user logs into the terminal and begins creating sales materials. The user enters the necessary information for the sales materials into a dedicated input form. For example, when creating a presentation document for a new product, the user would enter items such as "Introduction to New Product X," "Target Customer: A Certain Company," "Features: High Performance, Low Price," and "Layout: Simple" into the input form.

[1561] Data transmission on the device

[1562] The terminal collects data entered by the user and sends it to the server. This transmission is done via an HTTP POST request, and the data is delivered to the server in JSON format.

[1563] Server-based data analysis and prompt generation

[1564] The server parses the received JSON data. As a result of this analysis, prompts are generated to instruct the generative artificial intelligence. For example, text such as "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. Please keep the layout simple." might be generated.

[1565] Initial document creation using generative artificial intelligence

[1566] The server sends the generated prompt to the generative artificial intelligence. The generative AI generates initial documents based on this prompt. The generated documents are sent back to the server as an initial version of the sales negotiation materials. For example, a document like the following is generated:

[1567] 1. Introduction of New Product X

[1568] 1.1. High performance

[1569] 1.2. Low price

[1570] 2. Key points of the proposal

[1571] 2.1. A suitable solution for a particular company

[1572] Sending documents via server

[1573] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays this data to the user, allowing the user to review it.

[1574] User feedback

[1575] The user reviews the generated sales materials and enters any requests for revisions or additions. For example, a user might submit a revision request such as, "Please add an introductory paragraph to Chapter 1."

[1576] Sending additional requests from the device

[1577] The terminal resends the user's correction instructions to the server. This transmission is also done via an HTTP POST request, and the data is again sent to the server in JSON format.

[1578] Server-based re-analysis of data and prompt generation

[1579] The server analyzes the received feedback again and generates a new prompt. For example, it might generate a prompt such as, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X."

[1580] Regeneration by generative artificial intelligence

[1581] The server sends a new prompt to the generative artificial intelligence. Based on this prompt, the generative AI regenerates the sales proposal document and sends the revised document back to the server. For example, a document with an introductory sentence added to Chapter 1 is generated.

[1582] Server-based transmission of revised documents

[1583] The server sends the revised document to the terminal and displays it to the user. The user can review the regenerated document and make further corrections as needed.

[1584] User's final confirmation

[1585] The user makes a final review, and once they are satisfied with the sales materials, they use them in the sales negotiation.

[1586] As described above, the system of the present invention supports the efficient creation of business negotiation materials by collecting user input and automatically generating and modifying materials using generative artificial intelligence.

[1587] The following describes the processing flow.

[1588] Step 1:

[1589] The user logs into the terminal and begins creating the sales presentation materials. The user enters the requirements for the sales presentation materials (purpose, target customers, features, desired layout, etc.) into a dedicated input form.

[1590] Step 2:

[1591] The terminal converts the data entered by the user into JSON format and sends it to the server via an HTTP POST request.

[1592] Step 3:

[1593] The server analyzes the JSON data received from the terminal. Based on the analysis results, it generates prompts to send to the generative artificial intelligence.

[1594] Step 4:

[1595] The generative artificial intelligence generates initial sales materials based on prompts received from the server. The generated materials are then sent back to the server.

[1596] Step 5:

[1597] The server sends the initial data received from the generative artificial intelligence to the user's terminal. The terminal displays the data to the user, allowing them to review it.

[1598] Step 6:

[1599] The user reviews the displayed sales materials and enters requests for corrections or additions. For example, they might enter instructions such as, "Please add an introductory paragraph to Chapter 1," into the terminal.

[1600] Step 7:

[1601] The terminal converts the user's correction instructions into JSON data and sends it back to the server as an HTTP POST request.

[1602] Step 8:

[1603] The server analyzes the user feedback it receives again and generates a new prompt. For example, it might generate a prompt such as, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X."

[1604] Step 9:

[1605] The generative artificial intelligence regenerates the document based on the new prompt received from the server. The revised document is then sent back to the server.

[1606] Step 10:

[1607] The server sends the regenerated document to the user's terminal. The terminal displays the corrected document to the user, providing another opportunity for review.

[1608] Step 11:

[1609] The user reviews the regenerated document and provides further revision instructions as needed. This process is repeated until a satisfactory document is finalized.

[1610] Step 12:

[1611] The user reviews the final version of the sales proposal materials, and once completed, uses them in the sales negotiation.

[1612] The above outlines the specific processing flow in the sales negotiation document creation system.

[1613] (Example 1)

[1614] 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".

[1615] Creating sales materials requires users to expend a significant amount of time and effort. Furthermore, the process of incorporating revisions and additional requests to these materials is complex and time-consuming. This can reduce the efficiency of sales material creation and negatively impact the success rate of sales negotiations.

[1616] 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.

[1617] In this invention, the server includes means for transmitting user requests from a terminal, means for the server to analyze user requests and generate prompt messages for a generation AI model, and means for the generation AI model to automatically generate materials based on the received prompt messages. This enables the rapid and efficient creation of sales materials and easy modification based on user feedback.

[1618] "Terminal" refers to all devices used by users to create and modify sales materials and to communicate with the server.

[1619] A "server" refers to a computing system that has the function of analyzing requests received from users and generating prompt messages to send to the AI ​​model.

[1620] A "generative AI model" refers to artificial intelligence technology that automatically generates materials based on the received prompt text.

[1621] A "prompt" refers to a text-based instruction that provides guidance to a generative AI model regarding the content and format of the document.

[1622] "Documents" refers to documents containing various pieces of information used in business negotiations.

[1623] "Feedback" refers to the input information that users use to request corrections or additions after reviewing the generated materials.

[1624] "Revised document" refers to a document regenerated by the AI ​​model based on user feedback.

[1625] "Automatic generation" refers to the process in which a generation AI model creates documents based on prompt text without human intervention.

[1626] A "re-prompt" refers to a new prompt message generated based on corrections or additional instructions.

[1627] "Transmission" refers to the process of moving data from a terminal to a server, or from a server to a generated AI model.

[1628] This invention relates to a system that automatically creates sales materials using a generative AI model and modifies and regenerates the materials based on user feedback. This system includes components such as a terminal, a server, and a generative AI model.

[1629] Specific Embodiments

[1630] Hardware environment

[1631] Devices: PCs, tablets, smartphones, etc. Users access the system using these devices.

[1632] Server: Receives and analyzes data, generates prompt messages, and communicates with the AI ​​model. This could be a cloud server or an on-premises server.

[1633] Generative AI models: For example, OpenAI's GPT-3 or ChatGPT. They generate sales materials based on prompt messages generated by the server.

[1634] Software Environment

[1635] Server-side scripts: These use programming languages ​​such as Python and Java to parse user requests and generate prompt messages.

[1636] HTTP Requests: Used for sending data between the terminal and the server, and between the server and the generated AI model. Requests use HTTP POST requests.

[1637] User input

[1638] The user logs into the terminal and begins creating sales materials. The user enters the necessary information into a dedicated input form. For example, when creating a presentation document for a new product, the user would enter information such as: "Introduction to New Product X," "Target Customer: A Certain Company," "Features: High Performance, Low Price," and "Layout: Simple."

[1639] Data transmission on the device

[1640] The terminal collects data entered by the user and sends it to the server. This transmission is done via an HTTP POST request, and the data is delivered to the server in JSON format.

[1641] Server-based data analysis and prompt generation

[1642] The server parses the received JSON data and generates prompt messages to instruct the AI ​​model based on the results of this analysis. For example, it might generate text such as, "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. Please keep the layout simple."

[1643] Initial document creation using a generative AI model

[1644] Based on the generated prompt text, the AI ​​model generates an initial version of the sales presentation materials. These presentation materials will be in the following format:

[1645] 1. Introduction of New Product X

[1646] 1.1. High performance

[1647] 1.2. Low price

[1648] 2. Key points of the proposal

[1649] 2.1. A suitable solution for a particular company

[1650] The generated documents are sent to the terminal via the server.

[1651] User feedback and corrections

[1652] The user reviews the generated sales presentation materials and enters requests for revisions or additions. For example, they might instruct, "Please add an introductory paragraph to Chapter 1." The terminal resends the user's feedback to the server, which analyzes the feedback and generates a new prompt. The generation AI model regenerates the sales presentation materials based on this new prompt, and this revised material is sent back to the terminal via the server.

[1653] By repeating this process, users can efficiently create satisfactory sales materials. Furthermore, this system allows for repeated revision and improvement of materials generated based on user input and feedback, thereby improving the quality of materials used in sales negotiations.

[1654] As described above, the system of the present invention significantly improves the efficiency of creating sales materials by automating the sales material creation process using a generative AI model and enabling rapid revisions based on user feedback.

[1655] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1656] Step 1:

[1657] Users log in to the system using a terminal.

[1658] Specific steps: The user enters their user ID and password and clicks the "Login" button. The system sends the authentication information to the server, and if authentication is successful, the next screen is displayed.

[1659] Input: User ID, Password

[1660] Output: User authentication result, next operation screen

[1661] Step 2:

[1662] The user enters the necessary information into the input form to begin creating the sales presentation materials.

[1663] Specific operation: The user enters information such as "Introduction to new product X," "Target customer: A certain company," "Features: High performance, low price," and "Layout: Simple," and then clicks the "Submit" button.

[1664] Input: Each item in the sales presentation materials (new product name, target customers, features, layout, etc.)

[1665] Output: Request to send input information

[1666] Step 3:

[1667] The terminal sends the information entered by the user to the server via an HTTP POST request.

[1668] Specific operation: The terminal converts the input data into JSON format and sends it to the server.

[1669] Input: Information from sales materials entered by the user.

[1670] Output: Send data in JSON format

[1671] Step 4:

[1672] The server parses the received JSON data and generates prompt messages to send to the AI ​​model.

[1673] Specific operation: The server uses a Python script to parse the JSON data and generates a prompt message that reads, "Create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. The layout should be simple."

[1674] Input: Information from business negotiation materials sent in JSON format

[1675] Output: Prompt message to send to the generated AI model

[1676] Step 5:

[1677] The server sends the generated prompt message to the AI ​​model, requesting it to generate initial data.

[1678] Specific operation: The server sends a prompt message to the AI ​​generation model via an HTTP POST request. The AI ​​generation model generates sales materials based on the prompt message and sends them back to the server.

[1679] Input: Prompt text for the generated AI model

[1680] Output: Initial data generated by a generative AI model

[1681] Step 6:

[1682] The server sends the generated initial data to the terminal and displays it to the user.

[1683] Specific operation: The server uses an HTTP POST request to send the generated data to the terminal in JSON format. The terminal displays the received data to the user.

[1684] Input: Initial data returned from the generated AI model

[1685] Output: Display of initial materials in a format viewable by the user.

[1686] Step 7:

[1687] The user reviews the generated document and enters any necessary corrections or additional requests.

[1688] Specific actions: The user reviews the document, enters specific feedback such as "Please add an introductory paragraph to Chapter 1," and clicks the "Submit" button.

[1689] Input: User requests for modifications or additions

[1690] Output: Request to send correction instructions

[1691] Step 8:

[1692] The terminal then sends the user's correction instructions back to the server.

[1693] Specific operation: The terminal converts the modification request into JSON format and sends it to the server via an HTTP POST request.

[1694] Input: User requests for modifications or additions

[1695] Output: Sending correction instructions in JSON format

[1696] Step 9:

[1697] The server analyzes the received correction instructions and generates a new prompt message.

[1698] Specific operation: The server uses a Python script to analyze the feedback data and generates a new prompt message: "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X."

[1699] Input: Correction instructions in JSON format

[1700] Output: New prompt message to send to the generated AI model

[1701] Step 10:

[1702] The server sends a new prompt message to the AI ​​model, requesting it to generate the revised document.

[1703] Specific operation: The server sends a prompt message to the generating AI model via an HTTP POST request. The generating AI model generates revised data based on the prompt message and sends it back to the server.

[1704] Input: New prompt message to the generated AI model

[1705] Output: Revised document generated by an AI model

[1706] Step 11:

[1707] The server sends the revised document to the terminal and displays it to the user.

[1708] Specific operation: The server sends the revised document to the terminal in JSON format using an HTTP POST request. The terminal displays the received document to the user.

[1709] Input: Revised data returned from the generated AI model

[1710] Output: Display of the revised document in a format viewable by the user.

[1711] Step 12:

[1712] The user performs a final review, and once the materials meet their quality standards, they are used in business negotiations.

[1713] Specific actions: The user reviews the document one last time and, if necessary, submits a revision request, or reviews the document one last time and downloads or prints it.

[1714] Input: User's final confirmation

[1715] Output: Finalization of documents for use in business negotiations.

[1716] (Application Example 1)

[1717] 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".

[1718] In modern business negotiations and customer service at retail stores, it is crucial to be able to quickly prepare promotional and explanatory materials. However, creating these manually is time-consuming and inefficient. Furthermore, quickly gathering customer feedback is not easy. To solve these problems and improve customer satisfaction, there is a need for an automated material generation system utilizing generative artificial intelligence.

[1719] 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.

[1720] In this invention, the server includes means for automatically creating materials using generative artificial intelligence, means for modifying materials based on user feedback, means for transmitting user requests from a terminal to the server, means for generating and updating sales materials and promotional materials via a smart device, and means for incorporating customer feedback and regenerating materials. This makes it possible to provide sales materials and promotional materials quickly and efficiently, and to immediately reflect customer feedback.

[1721] "Generative artificial intelligence" refers to artificial intelligence that has the ability to generate new information or content based on input data.

[1722] "Methods for automatically creating documents" refers to a system that automatically creates documents using generative artificial intelligence based on user requests.

[1723] "Means of modifying materials based on user feedback" refers to methods of modifying existing materials using generative artificial intelligence to reflect user opinions and requests.

[1724] "Means of sending user requests from a terminal to a server" refers to a function that allows a user to send instructions to a server from their device for creating or modifying business negotiation materials.

[1725] "Means of sending prompts from a server to a generative artificial intelligence" refers to a method by which a server analyzes the user's request and sends instructions (prompts) based on that analysis to the generative artificial intelligence.

[1726] "A means of returning and displaying generated materials on a terminal" refers to a mechanism in which a server sends materials created by a generative artificial intelligence to a user's terminal, and the user can view and display them.

[1727] "Means for generating and updating sales materials and promotional materials via smart devices" refers to methods for generating sales materials and promotional materials using devices such as smart glasses and smartphones, and updating them as needed.

[1728] "Methods for incorporating customer feedback and regenerating materials" refers to a system that collects opinions and requests provided by customers and then regenerates materials with necessary updates based on that feedback.

[1729] A "smart device" refers to a glasses-type device or mobile phone equipped with internet connectivity and application execution capabilities.

[1730] This invention provides a system that automatically creates sales materials and promotional materials using generative artificial intelligence, and modifies and regenerates the materials based on user feedback. This system consists of a terminal, a server, and generative artificial intelligence.

[1731] System Configuration

[1732] terminal

[1733] The terminal utilizes smart devices (such as smart glasses or smartphones). Users use this terminal to input requests for the creation of business negotiation materials, and to review and modify the generated materials.

[1734] server

[1735] The server receives request data sent from the user via the terminal, analyzes it, and sends prompts to the generative artificial intelligence. The main functions of the server are as follows:

[1736] Analyze user requests and generate prompts.

[1737] A prompt is sent to the generative artificial intelligence, and the generated material is received.

[1738] The received documents are sent back to the user's device.

[1739] Generative artificial intelligence

[1740] Generative artificial intelligence generates sales materials and promotional materials based on prompts received from the server. The generated materials are sent back to the server and displayed again on the user's device.

[1741] Program Processing Description

[1742] Hardware:

[1743] Smart glasses (e.g., Google Glass)

[1744] Smartphones (e.g., iPhone, Android devices)

[1745] Server Computer

[1746] software:

[1747] Flask (a Python-based web framework)

[1748] requests (a Python module for sending HTTP requests)

[1749] APIs for generative AI models (e.g., OpenAI GPT, etc.)

[1750] The server analyzes user requests sent from smart devices and generates prompts for generative artificial intelligence. The generative AI model then creates prompt statements that generate materials. For example, a prompt might read: "A customer is requesting detailed information about the special features of new product Y. New product Y is highly durable and energy-efficient. Please create promotional materials that explain this in a way that does not require specialized knowledge."

[1751] This prompt is sent to a generative artificial intelligence system, the server receives the generated material, and sends it back to the terminal for display. The user can review the generated material, provide corrections or additional feedback, the server analyzes it again, and sends it to the generative AI model as a new prompt.

[1752] Specific example:

[1753] One scenario envisioned is that when a customer asks for details about a new product in a store, staff use smart glasses to instantly generate information and display it on a screen.

[1754] Customer question: "I would like to know more details about the special features of product X."

[1755] Staff operation: The staff member voice-inputs the following into the smart glasses: "Please generate documentation about the special features of the new product X."

[1756] System processing: Generates a prompt message, sends it to the generation AI model, and displays the generated document on the terminal.

[1757] This allows users to immediately provide materials to respond to customers and to quickly gather customer feedback.

[1758] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1759] Step 1:

[1760] User request input

[1761] Users use their devices (smart glasses or smartphones) to input requests for the creation of sales materials or promotional materials. For example, they might use the voice input function of their smart glasses to input a request such as, "Please create an introductory document for new product X." This input data is processed within the device and sent to the server.

[1762] Input: Request for creation of sales materials (e.g., introductory materials for new product X)

[1763] Output: Requested data

[1764] Step 2:

[1765] Sending request data

[1766] The terminal sends user input data to the server. The data is sent to the server in JSON format as an HTTP POST request. This process ensures the data is delivered to the server and ready for analysis.

[1767] Input: Request data

[1768] Output: HTTP POST request to the server

[1769] Step 3:

[1770] Server-based request data analysis

[1771] The server analyzes the received request data and creates a prompt to send to the generative artificial intelligence. For example, if a user requests, "Please create an introductory document for new product X," the server will generate a prompt such as, "Please create an introductory document for new product X. The target customers are general consumers. Its features are high performance and low price."

[1772] Input: Request data in an HTTP POST request

[1773] Output: Prompts for generative artificial intelligence

[1774] Step 4:

[1775] Send a prompt

[1776] The server sends the generated prompt to the generative AI. It sends the prompt as an API request to the generative AI, requesting the generation of data. At this time, an HTTP POST request is made to the generative AI's API endpoint.

[1777] Input: Prompt

[1778] Output: API request to a generative artificial intelligence system

[1779] Step 5:

[1780] Data generation

[1781] Generative artificial intelligence generates sales materials and promotional materials based on prompts. These generated materials are then sent back to the server. For example, a document containing sections such as "Introduction to New Product X," "High Performance," and "Low Price" is generated.

[1782] Input: Prompt

[1783] Output: Generated document

[1784] Step 6:

[1785] Return of generated documents

[1786] The server returns the data received from the generative artificial intelligence to the terminal. The data is sent as a response to an HTTP POST request and displayed on the terminal. The user can visually confirm the generated data.

[1787] Input: Generated document

[1788] Output: HTTP POST response to the terminal

[1789] Step 7:

[1790] Displaying documents and entering feedback

[1791] The user reviews the generated document on their device and provides feedback as needed. For example, they might enter a correction request such as, "Please add an introductory sentence to Chapter 1." This feedback data is then sent back to the server.

[1792] Input: Generated materials and feedback

[1793] Output: Feedback data

[1794] Step 8:

[1795] Sending feedback data

[1796] The device resends the user's feedback data to the server. The data is sent again to the server in JSON format as an HTTP POST request, and is ready for regeneration.

[1797] Input: Feedback data

[1798] Output: HTTP POST request to the server

[1799] Step 9:

[1800] Regeneration prompt generation

[1801] The server analyzes the feedback data and generates a new prompt. For example, it might generate a new prompt such as, "Please add an introductory sentence to Chapter 1 of the product introduction document for new product X," and send it to the generative artificial intelligence.

[1802] Input: Feedback data in an HTTP POST request

[1803] Output: New prompt

[1804] Step 10:

[1805] Regeneration and final transmission of documents

[1806] The server sends a new prompt to the generative artificial intelligence, which generates a revised version of the document. The generated document is sent back to the server and then transmitted to the terminal. The user then makes a final review of the regenerated document and uses it for business negotiations or promotions.

[1807] Input: New prompt

[1808] Output: Regenerated materials

[1809] Through the steps outlined above, users can quickly and efficiently generate, modify, and review sales materials and promotional materials.

[1810] 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.

[1811] This invention relates to a system that combines generative artificial intelligence and an emotion engine to automatically create and modify business negotiation materials. This system analyzes user input data, automatically creates materials using generative artificial intelligence, and further has the function of recognizing the user's emotional state and adjusting the content of the materials.

[1812] Specific Embodiments

[1813] User input

[1814] The user logs into the terminal and begins creating the sales presentation materials. The user enters the requirements for the sales presentation materials (purpose, target customer, features, desired layout, etc.) into a dedicated input form. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, the features are high performance and low price, and the layout should be simple."

[1815] Utilizing the Emotion Engine

[1816] The device analyzes the user's emotions in real time through the camera and microphone while the user is inputting data. The emotion engine analyzes data such as changes in facial expressions and tone of voice to recognize the user's emotional state. For example, it collects different emotional data depending on whether the user is excited or calm.

[1817] Data transmission on the device

[1818] The device combines user input data and sentiment data, converts it to JSON format, and sends it to the server. This transmission is done via an HTTP POST request, and the necessary data is passed to the server.

[1819] Server-based data analysis and prompt generation

[1820] The server parses the received JSON data. Based on the analysis results, it generates a prompt to send to the generative artificial intelligence. This prompt includes the user's requests and sentiment data. For example, it might generate text such as, "Please create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price. The user is excited, so please make the tone of the document cheerful."

[1821] Initial document creation using generative artificial intelligence

[1822] The generative artificial intelligence generates initial materials based on prompts received from the server. The generated materials are then sent back to the server. The generated materials reflect the tone and content of the user's emotional state, taking into account data from the emotion engine. For example, a document like the following might be generated:

[1823] 1. Introduction of New Product X

[1824] 1.1. High performance

[1825] 1.2. Low price

[1826] 1.3. Significant improvements can be expected by using this innovative product!

[1827] 2. Key points of the proposal

[1828] 2.1. A suitable solution for a particular company

[1829] Sending documents via server

[1830] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays the data to the user, allowing the user to review it.

[1831] User feedback

[1832] The user reviews the generated sales materials and enters requests for revisions or additions. Throughout this process, the sentiment engine monitors the user's emotions and collects data such as which parts the user shows the most interest in. For example, the user can give instructions such as, "Please add an introductory sentence to Chapter 1. Also, please emphasize the pricing information more."

[1833] Sending additional requests from the device

[1834] The device converts the user's correction instructions and sentiment data into JSON format and sends it back to the server as an HTTP POST request.

[1835] Server-based re-analysis of data and prompt generation

[1836] The server then analyzes the user's feedback and sentiment data it receives again and generates a new prompt. For example, it might generate a prompt such as, "Add an introductory paragraph to Chapter 1 of the new product X introduction document. Write it in a tone that strongly emphasizes the pricing information."

[1837] Regeneration by generative artificial intelligence

[1838] The generative artificial intelligence regenerates the document based on new prompts received from the server. It then sends the revised document back to the server. This revised document incorporates user feedback and sentiment data, such as highlighting price information.

[1839] Server-based transmission of revised documents

[1840] The server sends the regenerated document to the terminal and displays it to the user. The user can review the corrected document again and provide further correction instructions if necessary.

[1841] User's final confirmation

[1842] The user performs a final review, and once the sales materials are satisfactory, they are used in the sales negotiation. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the materials are aligned with the user's intentions and emotions.

[1843] As described above, the system of the present invention, by combining generative artificial intelligence and an emotion engine, can efficiently and accurately create and modify business negotiation materials and reflect the user's emotional state.

[1844] The following describes the processing flow.

[1845] Step 1:

[1846] The user logs into the terminal and begins creating the sales presentation materials. The user enters the requirements for the sales presentation materials (purpose, target customer, features, desired layout, etc.) into a dedicated input form. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, the features are high performance and low price, and the layout should be simple."

[1847] Step 2:

[1848] The emotion engine uses the camera and microphone built into the device to analyze the user's emotions in real time. It collects data such as changes in facial expressions and tone of voice to recognize the user's emotional state. For example, if the user is talking happily, the emotion will be recognized as "joy."

[1849] Step 3:

[1850] The device combines user input data and sentiment data, converts it to JSON format, and sends it to the server via an HTTP POST request. The transmitted data includes the purpose of the deal, target customers, characteristics, desired layout, and sentiment data.

[1851] Step 4:

[1852] The server analyzes the JSON data received from the terminal. Based on data such as the purpose and characteristics of the business negotiation, as well as user sentiment data, it generates prompts to send to the generative artificial intelligence. For example, a prompt such as "Please create an introductory document for new product X. The target customer is a certain company, and its features are high performance and low price. The user seems to be enjoying themselves, so please make the tone of the document cheerful." might be generated.

[1853] Step 5:

[1854] The generative artificial intelligence generates initial sales materials based on prompts received from the server. At this stage, the tone and content of the materials are adjusted considering the user's emotional data. The generated materials are sent back to the server. For example, the following document is generated:

[1855] 1. Introduction of New Product X

[1856] 1.1. High performance

[1857] 1.2. Low price

[1858] 1.3. This innovative product will enrich your life even further!

[1859] 2. Key points of the proposal

[1860] 2.1. A suitable solution for a particular company

[1861] Step 6:

[1862] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays the data to the user, allowing the user to review it.

[1863] Step 7:

[1864] The user reviews the displayed sales materials and enters requests for revisions or additions. If revision requests are made, the device uses the emotion engine again to analyze the user's emotions and acquire emotion data. For example, a user might submit a revision request such as, "Please add an introductory sentence to Chapter 1. Also, please emphasize the pricing information more."

[1865] Step 8:

[1866] The device converts the user's correction instructions and sentiment data into JSON format and sends them to the server again via an HTTP POST request.

[1867] Step 9:

[1868] The server analyzes the feedback and sentiment data it receives and generates new prompts. For example, it might generate a prompt such as, "Add an introductory sentence to Chapter 1 of the new product X introduction document. Write it in a tone that emphasizes the pricing information."

[1869] Step 10:

[1870] The generative artificial intelligence regenerates the material based on the new prompt received from the server. At this stage, the re-feedback sentiment data is also taken into consideration. The revised material is sent back to the server. For example, the following revised material is generated:

[1871] 1. Introduction of New Product X

[1872] 1.1. High performance

[1873] 1.2. Low price

[1874] 1.3. This innovative product will enrich your life even further!

[1875] 1.4. Implementing XYZ products offers an opportunity to significantly improve your business.

[1876] 2. Key points of the proposal

[1877] 2.1. A suitable solution for a particular company

[1878] 2.2. Special pricing offer

[1879] Step 11:

[1880] The server sends the regenerated document to the terminal and displays it to the user. The user can review the corrected document again and provide further correction instructions if necessary.

[1881] Step 12:

[1882] Once the user has made a final review and is satisfied with the completed document, it is used in the sales negotiation. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the document always align with the user's intentions and emotions.

[1883] The above outlines the specific processing flow in a sales negotiation document creation system that combines generative artificial intelligence and an emotion engine.

[1884] (Example 2)

[1885] 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".

[1886] Conventional document creation systems generate documents in a fixed pattern without considering user emotions, making it difficult to create documents that reflect user intentions and feelings. Furthermore, users must manually revise documents after creation, highlighting the need for more efficient workflows.

[1887] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for the user to log in to the terminal and input requests, means for analyzing the user's emotional state using a camera and microphone, means for transmitting the user's input data and emotional data from the terminal to the server in JSON format, means for the server to generate a prompt based on the user's requests and emotional data and transmit it to a generative artificial intelligence, means for the generative artificial intelligence to generate materials based on the prompt and send them back to the server, and means for the server to transmit the generated materials to the terminal and display them. This makes it possible to efficiently create materials that reflect the user's intentions and emotions.

[1888] A "user" refers to a person who uses the system to create documents.

[1889] A "terminal" refers to an electronic device used by a user to manipulate input data. Examples include personal computers and smartphones.

[1890] An "emotion engine" refers to software or hardware that uses cameras and microphones to analyze a user's emotional state.

[1891] "JSON format" is a data serialization format that refers to a method of storing and exchanging data based on JavaScript object notation.

[1892] A "server" refers to a central control unit that receives user input data and emotion data, performs analysis, and sends prompts to the generative artificial intelligence.

[1893] A "prompt" refers to text data or commands used to instruct a generative artificial intelligence system to generate data.

[1894] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates materials based on prompts.

[1895] "Documents" refer to documents and presentation materials generated for purposes such as business negotiations and proposals.

[1896] "Feedback" refers to correction instructions or additional requests made by users regarding materials they have generated.

[1897] This invention relates to a system that automatically creates and modifies business negotiation materials by combining generative artificial intelligence and an emotion engine. This system analyzes user input data and emotion data, automatically creates materials using generative artificial intelligence, and further has the function of recognizing the user's emotional state and adjusting the content of the materials.

[1898] 1. User input

[1899] The user logs into the terminal and enters the requirements for the sales materials through a dedicated input form. The user enters these items using a keyboard and mouse. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, its features are high performance and low price, and the layout should be simple."

[1900] 2. Utilizing the Emotional Engine

[1901] The emotion engine analyzes the user's facial expressions and voice in real time through the camera and microphone connected to the device. This allows it to detect the user's emotional state. For example, it can distinguish between when the user is excited and when they are calm. The emotion engine analyzes this data and uses that information to inform subsequent processing.

[1902] 3. Data transmission from the device

[1903] The terminal combines the user's input data and sentiment data, converts it to JSON format, and sends it to the server. This transmission is done using an HTTP POST request. For example, the following JSON data is generated:

[1904] json

[1905] {

[1906] "subject": "Introduction document for new product X",

[1907] "target_customer": "A certain company",

[1908] "features": ["high performance", "low price"],

[1909] "layout": "simple",

[1910] "emotion": "excitement"

[1911] }

[1912] 4. Server-based data analysis and prompt generation

[1913] The server parses the received JSON data and generates a prompt to send to the generative artificial intelligence based on the user's requests and sentiment data. The generated prompt is text data containing the user's requests and sentiment data. For example, a prompt such as "Please create an introductory document for new product X. The target customer is a certain company, and its features are high performance and low price. The user is excited, so please make the tone of the document cheerful." might be generated.

[1914] 5. Initial document creation using generative artificial intelligence

[1915] The generative artificial intelligence generates initial material based on prompts received from the server. The generated material is then sent back to the server. The generated material reflects the user's emotional state in tone and content. For example, the following document might be generated:

[1916] 1. Introduction of New Product X

[1917] 1.1. High performance

[1918] 1.2. Low price

[1919] 1.3. Significant improvements can be expected by using this innovative product!

[1920] 2. Key points of the proposal

[1921] 2.1. A suitable solution for a particular company

[1922] 6. Sending documents via server

[1923] The server sends the initial data received from the generative artificial intelligence to the terminal. The terminal displays the data to the user, allowing the user to review it.

[1924] 7. User Feedback

[1925] The user reviews the generated sales materials and enters requests for revisions or additions. For example, they might give instructions such as, "Please add an introductory sentence to Chapter 1. Also, please emphasize the pricing information more." Throughout this process, the emotion engine monitors the user's emotions and collects data such as which parts they show the most interest in.

[1926] 8. Sending additional requests from the device

[1927] The terminal converts the user's correction instructions and sentiment data into JSON format and sends it back to the server as an HTTP POST request. The server parses the received data and generates a new prompt. For example, a prompt such as "Add an introductory sentence to Chapter 1 of the new product X introduction document. Write it in a tone that strongly emphasizes the pricing information." might be generated.

[1928] 9. Regeneration by generative artificial intelligence

[1929] The generative artificial intelligence regenerates the document based on the new prompt and returns the revised document to the server. This revised document incorporates user feedback and sentiment data.

[1930] 10. Server-based submission of revised documents

[1931] The server sends the regenerated document to the terminal for the user to review. The user can then review the corrected document again and provide further correction instructions if necessary.

[1932] 11. User's final confirmation

[1933] The user makes a final review, and only uses the materials in a sales negotiation once they are satisfactory. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the materials are aligned with the user's intentions and emotions.

[1934] The above is a specific embodiment of the system of the present invention. This system can analyze user input data and emotional data, and efficiently and accurately create and modify materials using generative artificial intelligence.

[1935] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1936] Step 1:

[1937] The user logs into the terminal and begins creating sales materials. They enter the requirements for the sales materials (purpose, target customer, features, desired layout, etc.) into the input form. For example, they might enter, "I want to create an introductory document for new product X. The target customer is a certain company, its features are high performance and low price, and the layout should be simple." The input data includes purpose, target customer, features, desired layout, etc. The output is the requirements entered by the user.

[1938] Step 2:

[1939] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time. The emotion engine acquires changes in the user's facial expressions and voice tone as input data and recognizes the user's emotional state (excitement, calmness, etc.). As a result of the analysis, the user's emotional data is obtained. For example, if the user is excited, the emotion engine collects that data and outputs the state of excitement.

[1940] Step 3:

[1941] The terminal combines user input data and sentiment data and converts it into JSON format. The data processing involves combining requirements and sentiment data. The resulting JSON data includes the following format:

[1942] json

[1943] {

[1944] "subject": "Introduction document for new product X",

[1945] "target_customer": "A certain company",

[1946] "features": ["high performance", "low price"],

[1947] "layout": "simple",

[1948] "emotion": "excitement"

[1949] }

[1950] Step 4:

[1951] The terminal sends the converted JSON data to the server as an HTTP POST request. The input contains data in JSON format, and the output verifies that the data is sent correctly to the server.

[1952] Step 5:

[1953] The server parses the received JSON data and generates prompts to send to the generative artificial intelligence based on the user's requests and sentiment data. Data processing includes parsing the JSON data and converting it into prompts. For example, the generated prompts will be in the following text format:

[1954] "Please create a presentation document for our new product, X. The target customer is a specific company, and its key features are high performance and low price. The user is excited, so please make the document have a bright and positive tone."

[1955] Step 6:

[1956] The server sends the generated prompt to the generative AI, requesting it to generate initial data. The input includes the prompt, and the output is the initial data generated by the generative AI.

[1957] Step 7:

[1958] The generative artificial intelligence generates initial data based on prompts and sends it back to the server. For data processing, the generative AI performs text generation, and the generated data is obtained as output. For example, the following document is generated:

[1959] 1. Introduction of New Product X

[1960] 1.1. High performance

[1961] 1.2. Low price

[1962] 1.3. Significant improvements can be expected by using this innovative product!

[1963] 2. Key points of the proposal

[1964] 2.1. A suitable solution for a particular company

[1965] Step 8:

[1966] The server sends the initial data received from the generative artificial intelligence to the terminal and displays it to the user. The input includes the generated data, and the output confirms that the user can view the data.

[1967] Step 9:

[1968] The user reviews the generated document and enters requests for corrections or additions. For example, they might give instructions such as, "Add an introductory sentence to Chapter 1. Also, emphasize the pricing information more." The input includes user feedback, and the output is the feedback received.

[1969] Step 10:

[1970] The terminal converts the user's correction instructions and sentiment data into JSON format and sends it back to the server as an HTTP POST request. As part of the data processing, it is converted back to JSON format. The output is the JSON data sent to the server.

[1971] Step 11:

[1972] The server analyzes the re-received data and generates a new prompt. The input includes JSON data, and the output is a new prompt. For example, a prompt such as "Add an introductory sentence to Chapter 1 of the new product X introduction document. Write it in a tone that strongly emphasizes the pricing information." might be generated.

[1973] Step 12:

[1974] The generative artificial intelligence regenerates the document based on the new prompt and returns the revised document to the server. In terms of data calculation, the document is regenerated based on the revision instructions, and the revised document is obtained as output.

[1975] Step 13:

[1976] The server sends the regenerated document to the terminal for user review. It ensures that the input includes the corrected document and that the user can review the document again as output.

[1977] Step 14:

[1978] The user performs a final review, and once the document is satisfactory, it is used in the business negotiation. The input includes the final document, and the output is the finalized, reviewed document. Because the emotion engine constantly monitors the user's emotional state, the tone and content of the document will be aligned with the user's intentions and emotions.

[1979] The above describes the specific flow of the program processing of this system and the actions performed at each step.

[1980] (Application Example 2)

[1981] 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".

[1982] Current automated document creation systems generate documents based on static user input data, but they struggle to respond to user emotional states or real-time feedback. Furthermore, because the tone of documents is not adjusted based on customer emotions during sales negotiations and sales activities, it is not possible to create documents that effectively appeal to customer interest and emotions. This limits the effectiveness of sales negotiations and sales activities.

[1983] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for automatically creating materials using generative artificial intelligence, means for modifying materials based on user feedback, means for transmitting user requests from a terminal to the server, means for transmitting prompts from the server to the generative artificial intelligence, means for returning and displaying the generated materials to the terminal, means for analyzing the user's emotional state using an emotion engine, means for adjusting the tone of the materials based on the analyzed emotional data, and means for collecting user input and emotional data via a smart device. This makes it possible to create materials and adjust the tone based on the user's emotional state and real-time feedback.

[1984] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates text and documents based on input data.

[1985] "Means for automatically creating documents" refers to a function that automatically generates sales materials and explanatory documents based on user requests.

[1986] "Means for modifying documents" refers to a function that modifies and updates already generated documents in response to user feedback.

[1987] A "terminal" refers to a device used by a user, such as a computer or smart device used for inputting information or receiving data.

[1988] A "server" is a computer system that processes and stores data on a network and responds to requests from other terminals.

[1989] A "prompt" is input text data used to instruct a generative artificial intelligence system to create or modify documents.

[1990] An "emotion engine" is a technology that analyzes and recognizes a user's emotional state in real time based on their facial expressions, tone of voice, and other factors.

[1991] "Emotional data" refers to data about the user's emotional state, analyzed by the emotion engine.

[1992] "Tone adjustment" refers to changing the content and wording of a document according to the user's emotional state.

[1993] A "smart device" is an internet-connected terminal equipped with a camera and microphone that can collect user input and emotional data.

[1994] This invention uses a system that combines generative artificial intelligence and an emotion engine to automatically create and modify sales materials, and to provide real-time emotional support. The specific system configuration consists of a smart device used by the user, a server, generative artificial intelligence, and an emotion engine.

[1995] Program generation

[1996] This system's program includes the following elements:

[1997] 1. Acquire customer input data and sentiment data using smart devices.

[1998] 2. Send data to the server and generate a prompt.

[1999] 3. Generative artificial intelligence generates and modifies documents based on prompts.

[2000] 4. The server sends the generated document back to the terminal and displays it on the terminal.

[2001] Hardware and software to use

[2002] hardware

[2003] Smart devices: These are internet-connected terminals equipped with cameras and microphones, such as smart glasses and smartphones, that collect user input and emotional data. Each device can analyze the user's facial expressions and voice tone in real time.

[2004] software

[2005] Emotion Engine: Uses the Affectiva API to analyze the user's emotional state and sends it to the server as emotion data.

[2006] Generative Artificial Intelligence: Uses the OpenAI GPT-3 model to generate and modify documents based on prompts.

[2007] Data processing and data calculation

[2008] Data collection

[2009] The device uses its camera and microphone to collect the user's facial expressions and voice tone, and analyzes them through an emotion engine (Affectiva API). The analyzed data is converted to JSON format and sent to the server as an HTTP POST request.

[2010] Prompt generation

[2011] The server analyzes the received data and generates prompts based on the user's input requests and sentiment data. For example, the following prompt message may be generated:

[2012] Please create a presentation document for our new product, X. The target customer is a specific company, and its key features are high performance and low price. Since the user is excited, please use a bright and positive tone in the document.

[2013] Document generation and correction

[2014] Generative artificial intelligence (OpenAI GPT-3) generates initial material based on prompts. This material reflects the user's emotional state (for example, a brighter tone if the user is excited). The generated material is sent back to the server, which then transmits it to the terminal.

[2015] Display and Feedback

[2016] The terminal displays the generated document to the user. The user reviews the document and enters any necessary corrections or additional requests. This feedback is also analyzed through the emotion engine and sent back to the server. Based on the feedback and emotion data, the server generates a new prompt and requests the generative artificial intelligence to regenerate it.

[2017] Specific example

[2018] The user begins a business negotiation with a customer while wearing smart glasses in a store. If the customer shows interest in the new product X, the smart glasses' camera and microphone analyze the customer's facial expressions and voice in real time, and collect emotional data through the emotion engine (Affectiva API). When the user inputs, "I want to create an introductory document for the new product X. The target customer is a certain company, and its features are high performance and low price, with a simple layout," the server generates the following prompt text and sends it to the generative artificial intelligence (OpenAI GPT-3).

[2019] Please create a presentation document for our new product, X. The target customer is a specific company, and its key features are high performance and low price. Since the user is excited, please use a bright and positive tone in the document.

[2020] The generated materials will contain specific descriptions of "high performance" and "low price...

Claims

1. A method for automatically creating documents using generative artificial intelligence, A means of revising materials based on user feedback, A means of sending user requests from the terminal to the server, A means of sending a prompt from the server to a generative artificial intelligence, A means of returning the generated materials to the terminal and displaying them, A system that includes this.

2. The system according to claim 1, which analyzes user requests and converts them into prompts.

3. The system according to claim 1, which sends correction instructions as a re-prompt to initial data generated by a generative artificial intelligence.

Images